[{"data":1,"prerenderedAt":1874},["ShallowReactive",2],{"blog-article:\u002Fblog\u002Fcall-sentiment-analysis-dashboard":3},{"doc":4,"translations":287,"related":330,"prev":1360,"next":1574},{"id":5,"title":6,"author":7,"authorAvatar":8,"authorRole":9,"body":10,"category":242,"coverAlt":243,"dateModified":244,"datePublished":245,"description":246,"draft":247,"extension":248,"faq":249,"featured":247,"heroImage":268,"lang":269,"meta":270,"navigation":271,"path":272,"pillar":273,"readingMinutes":274,"seo":275,"seoTitle":276,"stem":277,"tags":278,"tldr":284,"translationKey":285,"__hash__":286},"blog_en\u002Fblog\u002Fcall-sentiment-analysis-dashboard.md","Call Sentiment Analysis: The Real-Time Response-Rate Dashboard","Totem Studio",null,"Totem Team",{"type":11,"value":12,"toc":233},"minimark",[13,32,37,43,63,67,74,78,81,85,90,105,112,116,131,138,150,157,163,167,170,174,182,195,201,223,226],[14,15,16,17,21,22,25,26,31],"p",{},"Are you having a good month? If your answer starts with \"I think so…\", you're flying blind. Totem's dashboard swaps that gut feeling for three numbers that actually move the business: how fast you respond and how much you cover outside your hours (the ",[18,19,20],"strong",{},"response rate",": the AI picks up inbound instantly, 24\u002F7, so what matters is speed and what you recover, not a \"% answered\"), what happened in each conversation (the outcome), and — the piece you couldn't see before — ",[18,23,24],{},"call sentiment analysis",", that is, how the customer felt conversation by conversation. And it's not about building a separate dashboard or exporting to a spreadsheet on Sundays: the analytics live in the same place as your conversations, leads and calendar, in real time. This is a tour inside the dashboard, so you can ",[27,28,30],"highlight",{"c":29},"violet","stop guessing",".",[33,34,36],"h2",{"id":35},"from-i-think-were-doing-fine-to-per-call-data","From \"I think we're doing fine\" to per-call data",[14,38,39,40],{},"The problem with flying by feel isn't that you're always wrong. It's that you don't know when you're wrong. A slow month and a good one look too much alike from the inside, and by the time you notice something's off, you've already lost three weeks of calls. ",[27,41,42],{"c":29},"Intuition is great for people; it's terrible for numbers.",[14,44,45,46,48,49,52,53,56,57,62],{},"The dashboard puts figures on what used to be a feeling. The first thing you see is the ",[18,47,20],{},", which changes meaning with AI. It's not \"how much do you answer?\" — you answer almost everything, because the AI picks up calls in ~1 second and replies to WhatsApp, Instagram, Messenger and web chat right away, 24\u002F7 — it's ",[18,50,51],{},"how fast"," and ",[18,54,55],{},"how much you recover outside your hours",". The dashboard separates what gets handled during your hours from what the AI covers at night, on weekends and during spikes, and it marks the time to first response by channel. And on the calls the AI makes outbound — follow-ups, callbacks — you do see a rate that moves: how many pick up. Because the ",[58,59,61],"a",{"href":60},"\u002Fblog\u002Fai-virtual-receptionist-answers-instantly","AI receptionist picks up the phone in ~1 second, 24\u002F7",", that gap of nights, weekends and spikes stops being a black hole and becomes a line you can look in the eye.",[64,65],"stat-group",{":items":66},"[{\"value\":\"60%\",\"label\":\"Less response time\",\"sublabel\":\"According to our clients\"},{\"value\":\"+55%\",\"label\":\"Leads treated as a priority\",\"sublabel\":\"According to our clients\"},{\"value\":\"+35%\",\"label\":\"Close rate\",\"sublabel\":\"According to our clients\"}]",[14,68,69,70,73],{},"Those figures come from client results, not a universal promise; your number depends on your volume, your industry and your team. But they illustrate what changes when you stop guessing: when the dashboard shows you, live, how many contacts you handle and how fast, ",[18,71,72],{},"the bar rises on its own"," because you finally know where it is.",[33,75,77],{"id":76},"the-three-customer-service-metrics-that-actually-matter","The three customer service metrics that actually matter",[14,79,80],{},"Three layers, one screen. There's no need to learn twenty KPIs; the customer service metrics that pay the bills are these three: response rate, outcome and sentiment.",[82,83],"mockup-analytics",{"caption":84},"Speed, outcome and sentiment in real time",[86,87],"comparison-table",{":columns":88,":rows":89},"[\"Layer\",\"What it tells you\",\"What you use it for\"]","[[\"Response rate\",\"How fast you respond and what you recover after hours; on outbound, how many pick up\",\"Measure speed and coverage, not a '% answered' that the AI already keeps near 100%\"],[\"Outcome\",\"What happened: appointment, follow-up, not interested\",\"See where the funnel drops off\"],[\"Sentiment\",\"How the customer felt in the conversation\",\"Spot friction before they leave\"]]",[14,91,92,93,95,96,99,100,104],{},"The ",[18,94,20],{}," tells you the pace at which work comes in, what you recover outside your hours and — on outbound — how many calls pick up. The ",[18,97,98],{},"outcome"," tells you what happened inside: whether the call ended in a booked appointment, a scheduled follow-up or a \"no, thanks.\" And because the AI moves the lead across the board based on that outcome — ",[58,101,103],{"href":102},"\u002Fblog\u002Fautomate-sales-pipeline-without-zapier","the funnel moves itself, no Zapier"," — what you see on the dashboard and what you see on the Kanban tell the same story, without you reconciling anything by hand.",[14,106,107,108,111],{},"The third layer, ",[18,109,110],{},"sentiment",", is the one almost nobody had until now. And it deserves its own section.",[33,113,115],{"id":114},"call-sentiment-analysis-the-signal-you-couldnt-see-before","Call sentiment analysis: the signal you couldn't see before",[14,117,118,119,122,123,126,127,130],{},"Answering everything instantly sounds perfect. But if half of those conversations end with the customer annoyed, the number is lying to you by omission. ",[27,120,121],{"c":29},"Quantity isn't quality."," Call sentiment analysis is the reading that was missing: the dashboard processes the transcript of every call and every chat and classifies the customer's tone — positive, neutral, negative — so you see not just ",[18,124,125],{},"how many"," conversations, but ",[18,128,129],{},"how"," they went. It works the same in voice as in WhatsApp, Instagram or web chat, so the same satisfaction gauge works for every channel.",[132,133],"image-figure",{"align":134,"alt":135,"caption":136,"src":137},"wide","Three call cards in navy, each with a colored dot (teal, bone, coral) from the sentiment analysis that classifies the customer's tone as positive, neutral or negative","Every conversation carries its sentiment color: at a glance you know where there was friction and where everything went smoothly.","\u002Fimg\u002Fblog\u002Fpanel-tasa-respuesta-sentimiento-tiempo-real-wide.webp",[14,139,140,141,145,146,31],{},"What's interesting isn't the label, it's what it lets you do. You filter by negative sentiment and, in seconds, you have in front of you the conversations where something went sideways: a question the agent couldn't answer, a wait that annoyed someone, a customer asking for something you don't cover yet. That's gold for ",[58,142,144],{"href":143},"\u002Fblog\u002Fhow-to-train-an-ai-receptionist","training your AI receptionist"," on your knowledge, and also for knowing when it's worth having a person step in sooner. Because if a conversation is getting tense, a teammate picks it up in one click with the full context — a warm handoff, without the customer repeating anything — and ",[58,147,149],{"href":148},"\u002Fblog\u002Fai-to-human-handoff-with-context","you don't lose the human touch",[151,152,154],"callout",{"type":153},"info",[14,155,156],{},"Sentiment is an indicative signal — one more reading on the table, not a verdict. It's there to show you where to put your attention, not to grade anyone. The analysis runs on conversations that are already handled with an AI disclosure, with a handoff to a person as a trust best practice and with EU hosting by default.",[158,159,160],"pull-quote",{},[14,161,162],{},"What doesn't get measured gets managed by gut feeling. And gut feeling never warns you about the conversation you're going to lose tomorrow.",[33,164,166],{"id":165},"what-a-team-decides-when-it-sees-analytics-in-real-time","What a team decides when it sees analytics in real time",[14,168,169],{},"Data for its own sake is worthless; what matters is what you do with it. Here's what changes in practice when the dashboard stops being an ornament and starts guiding the week.",[171,172],"step-timeline",{":steps":173},"[{\"title\":\"You see where to add support, you don't guess it\",\"description\":\"The dashboard shows you which hours and which channel the volume concentrates in, and how much the AI covers outside your hours. You add people where it truly helps, not blindly.\"},{\"title\":\"You prioritize by quality, not just volume\",\"description\":\"You cross sentiment with outcome: the positive leads that didn't close are your next call.\"},{\"title\":\"You turn friction into training\",\"description\":\"The conversations with negative sentiment tell you what's missing in your knowledge base. You fix it.\"},{\"title\":\"You measure ROI with your own numbers\",\"description\":\"Recovered calls, booked appointments and no-shows prevented come straight from the dashboard, no spreadsheet to rebuild.\"}]",[14,175,176,177,181],{},"Notice that none of those decisions requires building anything new. The analytics are native: they live where the conversations happen, in real time, and you open them with the ",[58,178,180],{"href":179},"\u002Fblog\u002Fcrm-universal-search-cmd-k","built-in search that finds any lead instantly",", along with any call, in an instant. Nothing separate that someone has to maintain.",[14,183,184,185,189,190,194],{},"And when the end of the month comes, the dashboard becomes your ledger. The entries that actually pay — answered calls that used to slip away, appointments the AI created on your calendar, confirmed reminders — are already measured. You just add your ticket and your cost per hour, as we explain in ",[58,186,188],{"href":187},"\u002Fblog\u002Fai-receptionist-roi-first-month","how to measure an AI receptionist's ROI in the first month",". If you want to see how far this goes, fine print and all, the ",[58,191,193],{"href":192},"\u002Fblog\u002Fai-receptionist-results-small-business","real results on bookings, no-shows and enrollment"," are broken down honestly.",[132,196],{"align":197,"alt":198,"caption":199,"src":200},"normal","Coral needle on a matte clay gauge marking a rising response-rate curve over a teal dial, next to a receipt tape for calculating ROI, on a navy background","By month's end the dashboard already carries the numbers that pay the bills: you just add your ticket and your cost per hour.","\u002Fimg\u002Fblog\u002Fpanel-tasa-respuesta-sentimiento-tiempo-real-inline.webp",[202,203,204],"key-takeaways",{},[205,206,207,211,214,217,220],"ul",{},[208,209,210],"li",{},"The dashboard replaces the 'I think we're doing fine' with three numbers: response rate, outcome and sentiment.",[208,212,213],{},"With AI, the response rate is speed and coverage: you answer inbound instantly and 24\u002F7, and you see how fast and what you recover outside your hours; on outbound, how many calls pick up.",[208,215,216],{},"Sentiment per conversation is the signal that was missing: it measures how it went, not just how many there were.",[208,218,219],{},"You filter by negative sentiment to spot friction and improve your knowledge base or step in on time.",[208,221,222],{},"Everything is native and real-time: no separate dashboard, with EU hosting by default.",[14,224,225],{},"Flying by feel is expensive because the mistake doesn't warn you: you simply lose calls until a slow month wakes you up. With per-call data in front of you, you see that slow month coming and you fix it sooner. That's the difference between driving while watching your dashboard and driving while staring in the rearview mirror.",[227,228],"cta-banner",{"button-link":229,"button-text":230,"text":231,"title":232},"\u002Fcontact","Talk to the team","Tell us your call and message volume and we'll set up a live tour of the dashboard — response rate, sentiment and outcome. Live in 48-72 hours, no contract.","We'll show you your dashboard with your own data",{"title":234,"searchDepth":235,"depth":235,"links":236},"",3,[237,239,240,241],{"id":35,"depth":238,"text":36},2,{"id":76,"depth":238,"text":77},{"id":114,"depth":238,"text":115},{"id":165,"depth":238,"text":166},"Use case","Matte clay customer service analytics dashboard: a coral needle marking a rising response-rate curve and a teal icon for per-call sentiment analysis, on a navy background","2026-06-28","2026-05-19","Call sentiment analysis, response rate and outcome in one real-time dashboard. See how every customer feels and stop running on gut feel.",false,"md",[250,253,256,259,262,265],{"question":251,"answer":252},"What exactly does the response rate measure?","Because the AI picks up in ~1 second and replies to WhatsApp, Instagram, Messenger and web chat messages right away, 24\u002F7, inbound is handled almost entirely; that's why the number isn't a '% answered' — it would be practically 100% — but how fast you respond and how much you recover outside your hours (nights, weekends, spikes) that used to slip away. The dashboard separates it for you into inside and outside your hours. And on the calls the AI makes outbound — follow-ups, callbacks — you do see a real contact rate: how many pick up.",{"question":254,"answer":255},"How is sentiment calculated per call?","The analysis runs on the transcript of each conversation and classifies the customer's tone (positive, neutral or negative). It's not a score you set by hand: it's an automatic signal per conversation that you can filter and cross with the outcome. It's indicative, one more reading, not an absolute verdict.",{"question":257,"answer":258},"Do I have to build a dashboard or connect another tool?","No. The analytics are native to the platform: they live in the same place as your conversations, leads and calendar. There's no export to a spreadsheet or a separate BI tool to maintain. You find it instantly in the built-in search, in real time.",{"question":260,"answer":261},"Where is the dashboard's data processed?","Data is hosted in the EU by default — a product choice, not a legal requirement. GDPR doesn't mandate that data stay physically in the EU; its Chapter V permits transfers outside the EEA with adequate safeguards, and if you handle the data of EU residents, GDPR applies. The AI disclosure comes standard, and offering a handoff to a person is our trust best practice. Sentiment analysis works on conversations that are already handled under those rules. This is informational, not legal advice.",{"question":263,"answer":264},"What is sentiment analysis for in customer service?","To see the quality of your conversations, not just the quantity. You filter by negative sentiment and, in seconds, you have in front of you the calls and chats where there was friction: an unanswered question, a long wait or something you don't cover yet. That tells you what to improve in your knowledge base and when it's worth having a person step in.",{"question":266,"answer":267},"Does sentiment analysis work on calls and on WhatsApp?","Yes. Sentiment is calculated on the transcript of each conversation, whether it's a voice call or a chat on WhatsApp, Instagram, Messenger, email or web chat. Everything is measured in the same dashboard, so you compare the customer's tone by channel without jumping between tools.","\u002Fimg\u002Fblog\u002Fpanel-tasa-respuesta-sentimiento-tiempo-real-cover.webp","en",{},true,"\u002Fblog\u002Fcall-sentiment-analysis-dashboard","Platform","7",{"title":6,"description":246},"Call Sentiment Analysis + Response Rate Dashboard","blog\u002Fcall-sentiment-analysis-dashboard",[24,279,280,281,282,283],"customer service analytics dashboard","real-time sentiment analysis","response rate metrics","customer sentiment analysis","call center analytics","Call sentiment analysis classifies the customer's tone — positive, neutral or negative — over each conversation's transcript. In Totem's dashboard it crosses the response rate (with AI, mostly speed and coverage: inbound is answered instantly, 24\u002F7, so you see how fast and how much you recover after hours) and each call's outcome, in real time. No separate dashboard to build: analytics live where conversations happen, so you decide with per-call data, not a gut feeling.","panel-tasa-respuesta-sentimiento-tiempo-real","5hYiCw8OvMyXTvfzb0WvZzTKS4tH30d94f345mPzAfI",[288,290,295,298,302,307,312,316,321,326],{"lang":269,"language":289,"path":272,"title":6},"en-US",{"lang":291,"language":292,"path":293,"title":294},"es","es-ES","\u002Fblog\u002Fpanel-tasa-respuesta-sentimiento-tiempo-real","Análisis de sentimiento en llamadas: el panel con tasa de respuesta en tiempo real",{"lang":296,"language":296,"path":297,"title":294},"es-419","\u002Fblog\u002Flatam\u002Fpanel-tasa-respuesta-sentimiento-tiempo-real",{"lang":299,"language":299,"path":300,"title":301},"fr","\u002Fblog\u002Fanalyse-sentiment-appels-taux-de-reponse","Analyse de sentiment des appels : le tableau de bord avec taux de réponse en temps réel",{"lang":303,"language":304,"path":305,"title":306},"de","de-DE","\u002Fblog\u002Fstimmungsanalyse-bei-anrufen-antworten","Stimmungsanalyse bei Anrufen: das Panel mit Echtzeit-Antwortrate",{"lang":308,"language":309,"path":310,"title":311},"pt-pt","pt-PT","\u002Fblog\u002Fanalise-sentimento-chamadas-respostas","Análise de sentimento nas ligações: o painel com taxa de resposta em tempo real",{"lang":313,"language":314,"path":315,"title":311},"pt-br","pt-BR","\u002Fblog\u002Fanalise-sentimento-chamadas-respostas-brasil",{"lang":317,"language":318,"path":319,"title":320},"sw","sw-KE","\u002Fblog\u002Fuchambuzi-wa-hisia-kwenye-simu","Uchambuzi wa hisia kwenye simu: dashibodi yenye kiwango cha majibu cha wakati halisi",{"lang":322,"language":323,"path":324,"title":325},"en-gb","en-GB","\u002Fblog\u002Fcall-sentiment-analysis-response-rate","Call sentiment analysis: the real-time response-rate dashboard",{"lang":327,"language":328,"path":329,"title":301},"fr-fr","fr-FR","\u002Fblog\u002Fanalyse-sentiment-appels-tableau-de-bord",[331,572,806,1156],{"id":332,"title":333,"author":7,"authorAvatar":8,"authorRole":9,"body":334,"category":242,"coverAlt":534,"dateModified":244,"datePublished":535,"description":536,"draft":247,"extension":248,"faq":537,"featured":247,"heroImage":556,"lang":269,"meta":557,"navigation":271,"path":558,"pillar":273,"readingMinutes":274,"seo":559,"seoTitle":560,"stem":561,"tags":562,"tldr":569,"translationKey":570,"__hash__":571},"blog_en\u002Fblog\u002Fmulti-location-crm-channels-by-branch.md","Franchise & Multi-Location CRM: Give Every Branch Its Own WhatsApp and Channels",{"type":11,"value":335,"toc":526},[336,343,347,350,353,356,361,365,368,371,384,389,393,400,403,410,413,420,424,427,430,435,442,447,450,458,462,465,469,472,491,497,501,519],[14,337,338,339,342],{},"Yes: a CRM for franchises and multi-location businesses—five clinics, a hotel chain, a network with twenty sites—can split phone numbers, WhatsApp and channels across every unit, so that ",[27,340,341],{"c":29},"each branch sees only its own customers and HQ sees everything"," from a single dashboard. You don't need to open a standalone account per location or reconcile spreadsheets at month-end. That's exactly what TotemAI's family-and-subteams structure solves, and it's the difference between \"a tool for one business\" and \"a tool for a group of businesses.\"",[33,344,346],{"id":345},"the-problem-with-running-multiple-locations-on-one-tool","The problem with running multiple locations on one tool",[14,348,349],{},"Most customer-service platforms assume there's a single business behind them: one number, one inbox, one team. That works beautifully for a single clinic or a lone real estate office. But the moment you grow to two locations, open a franchise, or run several brands, that model breaks.",[14,351,352],{},"The problem isn't technical—it's about boundaries. The Austin clinic's customer isn't the Dallas clinic's customer. A rep at one branch shouldn't see the leads next door. The franchisor wants to measure how each location is doing without asking for screenshots. And every branch wants its own number, its own WhatsApp and its own identity, even when the brand is shared.",[14,354,355],{},"When you try to solve that by dumping everything into one inbox, you get the usual mess: crossed leads, reps seeing what isn't theirs, and an HQ that's in the dark until it asks for the monthly spreadsheet. When you solve it by opening a separate account per location, you lose the group view and multiply your admin work by the number of sites.",[158,357,358],{},[14,359,360],{},"A group isn't one big team. It's several teams that share a brand but serve different customers. The tool has to understand that difference.",[33,362,364],{"id":363},"franchise-crm-one-hq-one-subteam-per-branch","Franchise CRM: one HQ, one subteam per branch",[14,366,367],{},"The family structure starts from a simple idea: there's an HQ (the \"family\") and, hanging off it, as many subteams as you have branches, sites, countries or brands. Each subteam is a full-fledged team inside TotemAI, with its own lead board, its own conversations and its own calendar. The difference is that they all sit under the same umbrella—just like a franchisor and its franchisees, or a head office and its regional branches.",[14,369,370],{},"The key is splitting channels by location. HQ creates the family once and, from there, assigns each subteam what belongs to it: its own phone number, its own WhatsApp channel, its Instagram, its Messenger, its SMS, its email and its web chat. The Dallas branch answers on the Dallas WhatsApp; Austin, on its own. Same dashboard, separate identities, one shared brand.",[14,372,373,374,378,379,383],{},"And underneath, the machinery is the same as always for each branch: the AI answers calls in ~1 second and messages right away, 24\u002F7, and a human picks up the conversation in one click with full context. If you want to see how that shared inbox works from the inside, we cover it in detail in ",[58,375,377],{"href":376},"\u002Fblog\u002Fwhatsapp-shared-inbox-for-teams","how to put your whole team on one WhatsApp number"," and in ",[58,380,382],{"href":381},"\u002Fblog\u002Funified-inbox-whatsapp-instagram-calls","managing WhatsApp, Instagram, Messenger and calls in one place",". The family doesn't change that experience for the branch—it replicates it, cleanly, in every subteam.",[132,385],{"align":134,"alt":386,"caption":387,"src":388},"One team vs a multi-location CRM: on the left a single team box, on the right a tree of subteams by branch in matte clay on a navy background","One team vs a family with subteams: the same CRM, split by location.","\u002Fimg\u002Fblog\u002Ffamilia-y-subequipos-repartir-canales-wide.webp",[33,390,392],{"id":391},"what-hq-sees-and-what-each-branch-sees","What HQ sees, and what each branch sees",[14,394,395,396,399],{},"Here's the detail that makes it usable. Each subteam sees only its own: its leads, its calls, its chats, its calendar. ",[27,397,398],{"c":29},"The rep at the Denver branch opens the app and sees their customers, not Miami's",". That prevents the mess and, along the way, keeps each book of business separated the way it should be.",[82,401],{"caption":402},"HQ compares every branch in one dashboard",[14,404,405,406,409],{},"HQ, by contrast, has the group view. It can see the aggregated activity of every subteam and compare how each location is doing: lead volume, conversations, booked appointments and per-call sentiment analysis. It's the same real-time analytics we explain in ",[58,407,408],{"href":272},"inside the dashboard: response rate and live sentiment",", but summed across the whole family. The franchisor stops asking for screenshots and starts comparing real numbers, branch by branch.",[64,411],{":items":412},"[{\"value\":\"60%\",\"label\":\"less response time, according to our clients\"},{\"value\":\"24\u002F7\",\"label\":\"every branch answers day, night and holidays\"},{\"value\":\"1 dashboard\",\"label\":\"for the whole family, with a per-subteam view\"}]",[14,414,415,416,31],{},"And because the apps are native on iOS and Android as well as the web, every member of every branch works from wherever they are without missing a single call. We cover it in ",[58,417,419],{"href":418},"\u002Fblog\u002Fanswer-business-calls-desktop-and-mobile","how calls ring at once on web, iOS and Android",[33,421,423],{"id":422},"per-location-permissions-and-consolidated-billing-without-the-chaos","Per-location permissions and consolidated billing, without the chaos",[14,425,426],{},"A group doesn't just split customers: it splits responsibility and money. The family structure separates the two and makes clear who manages what at each location and what each one uses, even though payment is centralized at HQ.",[14,428,429],{},"HQ decides the permissions. It can give each location manager control over their subteam (their members, their channels, their calendar) without opening the door to the rest of the family. A branch manager runs their own patch; a family admin runs the whole. No one sees more than they should.",[132,431],{"align":197,"alt":432,"caption":433,"src":434},"Per-location permissions in a franchise CRM: a coral master key in matte clay opens several teal locks, one per site, on a navy background","Each key opens only its own location; HQ keeps the master: per-site permissions and one central invoice with usage broken out.","\u002Fimg\u002Fblog\u002Ffamilia-y-subequipos-repartir-canales-inline.webp",[14,436,437,438,31],{},"Billing is centralized at HQ: a single payment for the whole family, without opening an account or an invoice per site. What does get broken out is usage—the dashboard categorizes by subteam what each branch spends: minutes, messages, templates—so you can see who's using what without reconciling spreadsheets, even though the invoice is one. And here's the reassuring part worth repeating: it's a fixed monthly plan, with a pool of included minutes and messages that usage draws down. That keeps the cost predictable month to month, and if usage spikes one month, you top it up with a one-time add-on. We go deeper in ",[58,439,441],{"href":440},"\u002Fblog\u002Fai-voice-agent-pricing-flat-rate-vs-per-minute","why your pricing is predictable",[86,443],{":columns":444,":highlightColumn":445,":items":446},"[\"\",\"Without subteams\",\"With subteams\"]","2","[{\"feature\":\"Splitting channels\",\"a\":\"Everyone shares one number\u002FWhatsApp\",\"b\":\"Each branch with its own channels\"},{\"feature\":\"Lead visibility\",\"a\":\"Everything mixed in one inbox\",\"b\":\"Each branch sees only its own\"},{\"feature\":\"Group view\",\"a\":\"The monthly spreadsheet, by hand\",\"b\":\"Aggregated dashboard for HQ\"},{\"feature\":\"Billing\",\"a\":\"One invoice that's hard to split\",\"b\":\"Central, broken out by site\"}]",[14,448,449],{},"In the table, column A is \"one team for the whole group\" and B is \"family with subteams.\" The difference isn't a handful of features: it's order.",[14,451,452,453,457],{},"The compliance baseline is the same across the whole family, so the same guarantees apply in every subteam—there's no branch that's \"less compliant\" than another. Two nuances worth getting right. First, the notice that a customer is being served by an AI: if you take calls from or handle the data of EU residents, the EU AI Act requires you to disclose it to the user, unless it's already obvious (Regulation (EU) 2024\u002F1689—the AI Act—art. 50.1); operating purely in the US, treat it as best practice and what the FTC and state law expect, not an EU mandate. Second, the option to escalate to a person, which we offer as good service—not because the GDPR imposes it across the board: the \"right to human intervention\" under GDPR art. 22.3 only arises with solely automated decisions that produce legal or similarly significant effects, and a booking or reception bot normally doesn't make that kind of decision. As for where the data lives, the GDPR does not require it to sit physically in the EU: it also allows processing outside the European Economic Area as long as valid transfer safeguards are in place (Regulation (EU) 2016\u002F679—the GDPR—Ch. V, arts. 44–46). Totem hosts to the EU standard as a product choice, not because any law makes it—so the guarantee travels to every branch. This takes away the franchisor's risk of one location going rogue. We go deeper in ",[58,454,456],{"href":455},"\u002Fblog\u002Fgdpr-compliant-ai-customer-service","the GDPR and AI Act compliance Totem builds in",", applied equally branch by branch.",[33,459,461],{"id":460},"when-you-need-a-multi-location-crm-and-when-you-dont","When you need a multi-location CRM (and when you don't)",[14,463,464],{},"Let's be honest: not everyone needs a family. If you have a single location, or one team serving a single book of business, the family structure is overkill. A regular team is simpler and does exactly what you need. Setting up subteams for no reason just adds layers.",[466,467],"myth-vs-reality",{":items":468},"[{\"myth\":\"The more subteams, the more organized I am.\",\"reality\":\"Subdividing for no reason adds admin. The family makes sense when you have genuinely separate books of business.\"},{\"myth\":\"To run multiple locations I need an account per location.\",\"reality\":\"An account per location takes away the group view. The family gives you separate branches with a shared dashboard.\"},{\"myth\":\"Splitting channels means splitting the brand too.\",\"reality\":\"Each subteam answers on its own number, but the brand and standards stay shared.\"}]",[14,470,471],{},"When is it a yes? When you have several business units with different customers under one umbrella: a group of med spas or dental practices with multiple locations, a network of real estate offices by area, a hotel chain, a franchise of driving schools, hair salons or restaurants, or any home-services business with branches by city. If that's you, the family stops being a luxury and becomes the only way not to lose control.",[202,473,474],{},[205,475,476,479,482,485,488],{},[208,477,478],{},"The family structure splits numbers, WhatsApp and channels across subteams.",[208,480,481],{},"Each branch sees only its own leads and conversations; HQ sees the group's aggregated activity.",[208,483,484],{},"Per-subteam permissions and one central invoice with usage broken out by site: each manager runs their own patch without the chaos.",[208,486,487],{},"Each plan is a fixed monthly one with included minutes and messages, and the AI-disclosure notice (AI Act, art. 50) and GDPR-grade safeguards Totem builds in apply the same in every subteam.",[208,489,490],{},"Worth it when you have several books of business; for a single location, a regular team is enough.",[14,492,493,496],{},[27,494,495],{"c":29},"A well-run group shows in how boring month-end is",": no one asking for screenshots, no one seeing anyone else's leads, no one arguing over who spent what. If you run multiple locations and still do it with standalone accounts and spreadsheets, this structure is going to take a lot of noise off your plate.",[33,498,500],{"id":499},"official-sources","Official sources",[205,502,503,512],{},[208,504,505,506],{},"AI Act (Regulation (EU) 2024\u002F1689), art. 50 (transparency) and art. 113 (application) — ",[58,507,511],{"href":508,"rel":509},"https:\u002F\u002Feur-lex.europa.eu\u002Feli\u002Freg\u002F2024\u002F1689\u002Foj\u002Feng",[510],"nofollow","EUR-Lex",[208,513,514,515],{},"GDPR (Regulation (EU) 2016\u002F679), art. 22 (automated decisions) and Ch. V, arts. 44–46 (international transfers) — ",[58,516,511],{"href":517,"rel":518},"https:\u002F\u002Feur-lex.europa.eu\u002Flegal-content\u002FEN\u002FTXT\u002F?uri=CELEX:32016R0679",[510],[227,520,523],{"label":521,"to":522},"See plans and set up your family","\u002Fpricing",[14,524,525],{},"Tell us how many locations you have and we'll set up your family-and-subteams structure live in 48–72 hours. No lock-in, and two months free if you choose the annual plan.",{"title":234,"searchDepth":235,"depth":235,"links":527},[528,529,530,531,532,533],{"id":345,"depth":238,"text":346},{"id":363,"depth":238,"text":364},{"id":391,"depth":238,"text":392},{"id":422,"depth":238,"text":423},{"id":460,"depth":238,"text":461},{"id":499,"depth":238,"text":500},"Franchise CRM: a matte-clay tree with a central coral node (HQ) connected to four teal nodes, each branch with its own WhatsApp and calls channel icon","2026-06-18","One CRM for franchises and multi-location businesses: give every branch its own number, WhatsApp and channels while HQ sees the whole group in one view.",[538,541,544,547,550,553],{"question":539,"answer":540},"Can each branch have its own number and its own WhatsApp?","Yes. HQ splits numbers and WhatsApp, Instagram, Messenger, SMS, email and web chat channels across the subteams. Each branch answers with its own identity, but everything lives on the same platform and under the same brand.",{"question":542,"answer":543},"Can the franchisor see what each branch is doing?","HQ sees the aggregated activity of every subteam: leads, conversations, appointments and sentiment analysis. Each branch, on the other hand, sees only its own channels and its own customers. HQ decides how permissions are split.",{"question":545,"answer":546},"Does this make the bill a lot more expensive?","HQ centralizes payment for the whole family into a single invoice; there's no invoice per branch. What does get broken out is usage: the dashboard categorizes by subteam what each site spends, so you can see who's using what even though payment is one. The plan is a fixed monthly one with included minutes and messages, so the cost is predictable month to month. There's no lock-in, and the annual plan includes two months free.",{"question":548,"answer":549},"When is this structure NOT worth it?","If you have a single location or one team serving a single book of business, you don't need a family: a regular team is enough and simpler. The family structure makes sense when you have several business units with separate customers under one umbrella.",{"question":551,"answer":552},"Can it manage multiple locations without opening an account for each one?","Yes, that's exactly the point of the family structure. Instead of a standalone account per site, you create a single family and hang one subteam per location off it. That way you keep the group view and avoid multiplying your admin work by the number of sites.",{"question":554,"answer":555},"What businesses does a multi-location CRM with subteams fit?","Groups of med spas or dental practices with multiple locations, networks of real estate offices by area, hotel chains, franchises of driving schools, hair salons or restaurants, and home-services businesses with branches by city: any business with several books of business under one brand.","\u002Fimg\u002Fblog\u002Ffamilia-y-subequipos-repartir-canales-cover.webp",{},"\u002Fblog\u002Fmulti-location-crm-channels-by-branch",{"title":333,"description":536},"Franchise & Multi-Location CRM: Channels by Site","blog\u002Fmulti-location-crm-channels-by-branch",[563,564,565,566,567,568],"multi-location CRM","franchise CRM","manage multiple locations from one platform","WhatsApp shared inbox for multiple locations","CRM for multi-location businesses","per-location phone numbers and channels","A CRM for franchises and multi-location businesses splits numbers, WhatsApp and channels by site: each branch sees only its own customers, and HQ sees everything from a single dashboard. TotemAI's family-and-subteams structure separates permissions by location and consolidates billing at HQ, with usage broken out per site—no account per branch and no reconciling spreadsheets at month-end.","familia-y-subequipos-repartir-canales","ESJNzog4jafG4-Z5WgtPCZrab5utV5PqEWthGQ3Mii4",{"id":573,"title":574,"author":7,"authorAvatar":8,"authorRole":9,"body":575,"category":242,"coverAlt":768,"dateModified":244,"datePublished":769,"description":770,"draft":247,"extension":248,"faq":771,"featured":247,"heroImage":790,"lang":269,"meta":791,"navigation":271,"path":192,"pillar":792,"readingMinutes":274,"seo":793,"seoTitle":794,"stem":795,"tags":796,"tldr":803,"translationKey":804,"__hash__":805},"blog_en\u002Fblog\u002Fai-receptionist-results-small-business.md","AI Receptionist Results for Small Business: +43% Bookings, −62% No-Shows, Double the Sign-Ups (With the Fine Print)",{"type":11,"value":576,"toc":760},[577,580,584,587,594,599,604,608,611,614,619,622,633,637,640,646,649,656,661,665,668,671,674,679,685,690,694,697,700,703,709,716,735,738,744,746],[14,578,579],{},"Yes, we see AI receptionist results in real small businesses: more bookings, fewer no-shows, and more sign-ups once it starts answering. But before we show you the numbers, the fine print matters — it's what separates an honest case study from an ad that promises what it can't deliver. These figures are examples of what we see according to our clients, not guarantees. What we can promise is the mechanism behind them: instant response 24\u002F7, reminders that confirm, and follow-up that doesn't fall through the cracks. That part is real, it lives inside the platform, and you're the one who measures it.",[33,581,583],{"id":582},"how-to-read-these-figures-examples-not-guarantees","How to read these figures: examples, not guarantees",[14,585,586],{},"There's a kind of marketing that slaps a giant \"+300%\" on the page and runs off. We prefer the opposite: to show you the figure and also the why, the limits, and what it depends on. Because a number without context doesn't help you decide — it manipulates you.",[14,588,589,590,31],{},"When we say we see more bookings or fewer no-shows, we're talking about improvements observed in real businesses that use Totem, not an audited average or a contractual promise. Your result will depend on things we don't control: how many contacts come in a day, how many used to go cold, which industry you compete in, and how good your offer is. AI doesn't work miracles on a business with no demand. What it does is ",[27,591,593],{"c":592},"coral","stop throwing away the demand you already have",[151,595,596],{"type":153},[14,597,598],{},"The honest rule of this article: every Totem figure is an example, \"according to our clients.\" External statistics are attributed by name. And there's no absolute guarantee, because that would be a lie.",[14,600,601,602,31],{},"The good news is you don't have to take any of this on faith. The platform shows you your response rate, your booked appointments, your no-shows, and even the sentiment of each call in real time, so you can measure your own result from the first month. If you want the step-by-step math, it's in ",[58,603,188],{"href":187},[33,605,607],{"id":606},"more-bookings-43-response-speed-and-247-capture","More bookings (+43%): response speed and 24\u002F7 capture",[14,609,610],{},"The first figure we see climb is bookings, and the reason isn't magic — it's speed. Most businesses lose customers not because their product is worse, but because they answer late. Two hours later, the next day, once they're out of the exam room. And by then the person has already messaged three competitors.",[64,612],{":items":613},"[{\"value\":\"~1 s\",\"label\":\"how long the AI takes to answer the phone, 24\u002F7\",\"trend\":\"up\"},{\"value\":\"24\u002F7\",\"label\":\"nights, weekends, and holidays included\",\"trend\":\"neutral\"},{\"value\":\"+50%\",\"label\":\"more appointments, according to our Totem clients\",\"trend\":\"up\"}]",[132,615],{"align":134,"alt":616,"caption":617,"src":618},"How an AI receptionist wins more bookings: a coral clay stopwatch marking a single second beside a tray of calendar slots filling up, clay style on navy","The booking is won in the first second: answering instantly, 24\u002F7, is what turns a late-night inquiry into a confirmed appointment.","\u002Fimg\u002Fblog\u002Fresultados-reales-agente-ia-reservas-ausencias-matriculacion-wide.webp",[14,620,621],{},"Speed matters because the window of opportunity is brutally short. According to a classic Harvard Business Review study, companies that respond to a lead within the first hour are nearly seven times more likely to qualify it than those that wait just one hour longer. A single person, running between appointments, can't keep up that pace. An AI receptionist can: it answers first, qualifies, offers real openings from your calendar synced with Google or Microsoft, and closes the appointment — even at eleven at night, which is when half the country is browsing from the couch.",[14,623,624,625,628,629,31],{},"The \"+43%\" in the headline is the kind of jump we see when a business goes from capturing only during office hours to capturing 24 hours a day and instantly. The fine print: that jump is huge if you used to lose half your calls after hours, and modest if you already answered nearly everything. ",[27,626,627],{"c":592},"Your margin is exactly the size of what slips away today",". That's ultimately the idea that ",[58,630,632],{"href":631},"\u002Fblog\u002Fai-receptionist-cost-vs-missed-call","your AI receptionist costs less than one missed call a day",[33,634,636],{"id":635},"fewer-no-shows-62-reminders-that-actually-confirm","Fewer no-shows (−62%): reminders that actually confirm",[14,638,639],{},"The second figure is the favorite of clinics, hair salons, and restaurants, because every empty slot is an idle chair or a table that isn't ringing up sales. Filling the calendar is half the battle; getting people to actually show up is the other half.",[641,642],"fx-decode",{"label":643,"sublabel":644,"value":645},"fewer no-shows","according to our Totem clients","−35%",[14,647,648],{},"The mechanism is simple and honest. Every confirmed appointment triggers a cadence of reminders by WhatsApp and, if needed, by voice, with active confirmation: the client confirms with one tap, and if they let you know they can't make it, that slot is freed up for your waitlist. The key is the channel. WhatsApp gets opened far more than SMS or email, so the reminder actually gets read instead of dying in an unopened inbox.",[14,650,651,652,31],{},"So what about the \"−62%\" in the headline? That's the good extreme: what we see in businesses that started from sky-high, disorganized no-show rates with no reminders at all. When you're coming from warning no one, the drop is spectacular. If you were already sending an SMS the day before, the improvement will be more modest. The cadence that works best, down to its timing, we break down in ",[58,653,655],{"href":654},"\u002Fblog\u002Fappointment-reminder-schedule-no-shows","the appointment reminder schedule that actually stops no-shows",[158,657,658],{},[14,659,660],{},"The difference isn't a calendar that looks full. It's a calendar that actually brings in revenue.",[33,662,664],{"id":663},"double-the-sign-ups-and-more-closes-follow-up-that-doesnt-fall-through-the-cracks","Double the sign-ups and more closes: follow-up that doesn't fall through the cracks",[14,666,667],{},"The third improvement is the most invisible and the most expensive to ignore: follow-up. This is where the headline's \"double the sign-ups\" lives — an example we see mostly at driving schools and tutoring centers, where the decision simmers slowly and almost no one enrolls on the first contact.",[14,669,670],{},"The classic problem is well summed up by InsideSales: 80% of sales need at least five follow-ups, but 92% of salespeople give up before the fifth. In other words, most people throw away the contact right before it was ripe. Not out of laziness, but because doing five follow-ups by hand, for every lead, without forgetting a single one, is humanly impossible when dozens come in a day.",[171,672],{":steps":673},"[{\"title\":\"The contact comes in\",\"description\":\"A question about driving lessons at 9:30 p.m., over WhatsApp.\"},{\"title\":\"A reply right away\",\"description\":\"The AI notes that it's an assistant, qualifies, and answers questions using your information.\"},{\"title\":\"The lead lands on the board\",\"description\":\"It shows up on the Kanban already qualified, with the full history.\"},{\"title\":\"Follow-up that isn't forgotten\",\"description\":\"A human-paced WhatsApp cadence; a single no stops the sequence instantly.\"},{\"title\":\"It moves itself based on the outcome\",\"description\":\"The AI moves the lead between stages without Zapier; your team steps in when it matters.\"}]",[132,675],{"align":197,"alt":676,"caption":677,"src":678},"An AI receptionist's automatic follow-up: a clay lead card advancing on its own through the columns of a Kanban board, with a teal WhatsApp icon trailing it, clay style on navy","Follow-up that doesn't slip: the lead moves itself across the board while the cadence keeps at it with tact and stops at a no.","\u002Fimg\u002Fblog\u002Fresultados-reales-agente-ia-reservas-ausencias-matriculacion-inline.webp",[14,680,681,682,31],{},"The AI keeps that conversation alive with human-paced cadences: it follows up with tact, without hounding, and stops the moment someone says \"no, thanks.\" Meanwhile, the lead moves itself across your Kanban board based on what happens on each call or message, without you having to drag cards or set anything up in Zapier. And when the delicate, high-value moment arrives, your team steps in with one click and the full context in front of them — none of that \"tell me the whole thing again from the start\" that cools people off. Doubling the sign-ups isn't about selling harder; ",[27,683,684],{"c":592},"it's about not losing the people who were already interested",[686,687],"stat",{"label":688,"value":689},"more closes, according to our clients, with automatic follow-up and human-paced cadences","+35%",[33,691,693],{"id":692},"the-fine-print-your-ai-receptionist-results-depend-on-your-volume-and-your-industry","The fine print: your AI receptionist results depend on your volume and your industry",[14,695,696],{},"Here's the section almost no one writes, and the most important one. These three figures aren't a promise we sign for you: they're what a solid mechanism produces when applied to a business that has demand. The size of your improvement depends on three levers that are yours, not ours.",[466,698],{":items":699},"[{\"myth\":\"The +43% is what I'm going to get.\",\"reality\":\"It's an example according to our clients. Your jump depends on how much you were losing before: huge if half slipped away, modest if you already captured nearly everything.\"},{\"myth\":\"If I add the AI, no-shows will drop 62% for sure.\",\"reality\":\"That −62% is the good extreme, in businesses that warned no one. If you were already sending reminders, the improvement will be more modest.\"},{\"myth\":\"Any business doubles its sign-ups.\",\"reality\":\"We see the doubling where the sale needs many follow-ups and they used to fall through. With low volume, the improvement is real but smaller.\"},{\"myth\":\"The figures apply the same to every industry.\",\"reality\":\"A clinic with 200 messages a day and a neighborhood hair salon don't start from the same place. More volume lost, more room for improvement.\"}]",[14,701,702],{},"Put another way: the higher your volume and the more used to go cold, the bigger your jump. A business that gets four inquiries a day and already answered them all will notice a real but small improvement; one that gets two hundred and answered half, none after hours, is looking at the headline case. Neither is being misled, because we teach both of them to measure it.",[14,704,705,706,31],{},"And that's what makes any promise credible: that you can verify it. The dashboard shows you your real response rate, your bookings, your no-shows, and the sentiment of every conversation, with no makeup. You do the counting, not us. You'll find the full detail of how it works in ",[58,707,708],{"href":272},"the real-time response-rate and sentiment dashboard",[14,710,711,712,31],{},"One last piece of honesty, because it counts toward ROI: you pay a fixed monthly plan with a bundle of included minutes and messages, and usage draws down from that bundle. A fixed plan with an included bundle is easier to budget than a per-minute meter that runs away from you, and if you go over in a given month you extend with a one-off top-up. So when you calculate your result, the numerator is what you gain in bookings and the cost base is predictable. If you want to see the voice agent that holds all this together, it's in ",[58,713,715],{"href":714},"\u002Fblog\u002Fai-voice-agent-for-business","the AI voice agent for business",[202,717,718],{},[205,719,720,723,726,729,732],{},[208,721,722],{},"The figures (+bookings, −no-shows, +sign-ups) are examples according to our clients, not guarantees: your result depends on your volume and your industry.",[208,724,725],{},"More bookings comes from answering the phone in ~1 second, replying to messages right away, and capturing 24\u002F7; the jump is the size of what slips away today.",[208,727,728],{},"Fewer no-shows comes from WhatsApp and voice reminders with active confirmation, which actually get read and free up slots.",[208,730,731],{},"More sign-ups and closes comes from follow-up that doesn't slip: human-paced cadences that stop at a no, and a board that moves itself, without Zapier.",[208,733,734],{},"Everything is measurable in your own dashboard from the first month, and you pay a fixed monthly plan with included minutes and messages, so you know what you pay each month.",[14,736,737],{},"The right question isn't \"can you guarantee me a +43%?\" It's \"how much am I losing today by answering late, not confirming, and not following up?\" That number already exists in your business; you just can't see it right now. Turn it on, measure it, and decide.",[227,739],{"description":740,"primary-href":229,"primary-label":741,"secondary-href":522,"secondary-label":742,"title":743},"We get it live in 48-72 hours, with no lock-in, and you'll see your bookings, no-shows, and sentiment in your dashboard from the first month.","Book a demo","See plans","Measure your own result, not an ad's",[33,745,500],{"id":499},[205,747,748,754],{},[208,749,750,751],{},"EU AI Act (Regulation (EU) 2024\u002F1689), art. 50 (transparency) and art. 113 (application timeline) — ",[58,752,511],{"href":508,"rel":753},[510],[208,755,756,757],{},"GDPR (Regulation (EU) 2016\u002F679), art. 22 (automated decisions) and Ch. V (international transfers) — ",[58,758,511],{"href":517,"rel":759},[510],{"title":234,"searchDepth":235,"depth":235,"links":761},[762,763,764,765,766,767],{"id":582,"depth":238,"text":583},{"id":606,"depth":238,"text":607},{"id":635,"depth":238,"text":636},{"id":663,"depth":238,"text":664},{"id":692,"depth":238,"text":693},{"id":499,"depth":238,"text":500},"AI receptionist results for small business: three rising clay columns crowned with teal arrows, one in coral, with a floating asterisk marking the fine print, clay style on navy","2026-06-15","Real AI receptionist results for small business: +43% bookings, -62% no-shows and double the sign-ups, with the fine print on every figure.",[772,775,778,781,784,787],{"question":773,"answer":774},"Are these figures guaranteed?","No. These are results we see according to our clients — examples of what answering fast and following up produce, not a promise of numbers. Your result depends on your volume, your industry, and your offer. The honest thing is to show you the mechanism and let you measure it yourself.",{"question":776,"answer":777},"How do I know it'll work for me?","Measure it the first month. The platform shows you your response rate, booked appointments, no-shows, and sentiment in real time. If you get a lot of contacts a day and they go cold, the room for improvement is large; if you get four, it'll be smaller but just as measurable.",{"question":779,"answer":780},"What actually drives the drop in no-shows?","Automatic WhatsApp and voice reminders with active confirmation: the client confirms with one tap and, if they can't make it, that slot is freed up. WhatsApp gets opened far more than SMS or email, so the reminder actually gets read.",{"question":782,"answer":783},"Is this compliant with privacy and AI-disclosure rules?","We give you the tools to comply, though compliance depends on your setup and use. It comes switched on by default: a notice that people are talking to an AI at the start of every conversation (the transparency duty under Article 50.1 of the EU AI Act), the option to escalate to a person at any time as a UX best practice (GDPR Article 22 doesn't require offering a human in a booking conversation, because that isn't a solely automated decision with legal or similarly significant effects), and data hosted in the European Union. If you take calls from or handle data of EU residents, the EU AI Act and GDPR apply to you; if not, this is a premium, EU-grade baseline you get anyway, alongside US expectations like FTC guidance on AI and, for calls and texts, the TCPA. Note: GDPR doesn't require data to stay in the EU; it permits international transfers with the safeguards in its Chapter V — hosting in the EU is a product choice, not a legal requirement. This is informational and not legal advice.",{"question":785,"answer":786},"Which small businesses and industries does an AI receptionist work best for?","For businesses that get a lot of inquiries and appointments by phone or WhatsApp: clinics, hair salons, restaurants, driving schools, tutoring centers, and dental practices. The higher your volume and the more contacts used to go cold, the bigger your room for improvement. With low volume the improvement is real, but smaller.",{"question":788,"answer":789},"How much does an AI receptionist cost, and how is it billed?","You pay a fixed monthly plan with a bundle of included minutes and messages: the minutes the AI talks and the messages it sends count against that bundle, whether the call comes in or goes out. That's why the cost is predictable: you know what you pay each month, and if a spike leaves you short, you extend with a one-off top-up and can set a spend cap. There's no lock-in, the annual plan comes with two months free (prepaid and not refunded mid-term), and setup takes 48-72 hours.","\u002Fimg\u002Fblog\u002Fresultados-reales-agente-ia-reservas-ausencias-matriculacion-cover.webp",{},"No-shows",{"title":574,"description":770},"AI Receptionist Results: More Bookings, Fewer No-Shows","blog\u002Fai-receptionist-results-small-business",[797,798,799,800,801,802],"AI receptionist results","AI receptionist case study","more bookings fewer no-shows","reduce no-shows with AI","AI receptionist ROI","do AI receptionists work","An AI receptionist drives three improvements we see according to our clients: more bookings, fewer no-shows, and more sign-ups. These are examples, not guarantees. The mechanism is real and you measure it in your dashboard: it answers the phone in ~1 second and replies to your messages right away, 24\u002F7, with active-confirmation reminders and follow-up that doesn't slip. Your result depends on your volume and your industry.","resultados-reales-agente-ia-reservas-ausencias-matriculacion","fe8vd06yuo8zeJGlfwpnv0biLleMGooW2RUE_M1u9c8",{"id":807,"title":808,"author":7,"authorAvatar":8,"authorRole":9,"body":809,"category":242,"coverAlt":1117,"dateModified":244,"datePublished":1118,"description":1119,"draft":247,"extension":248,"faq":1120,"featured":247,"heroImage":1139,"lang":269,"meta":1140,"navigation":271,"path":1141,"pillar":1142,"readingMinutes":1143,"seo":1144,"seoTitle":1145,"stem":1146,"tags":1147,"tldr":1153,"translationKey":1154,"__hash__":1155},"blog_en\u002Fblog\u002Fai-agent-accounting-firms-rag.md","AI Agent for Accounting Firms: Answers From Your Own Knowledge (RAG)",{"type":11,"value":810,"toc":1109},[811,822,866,870,873,881,885,888,893,897,907,919,925,932,942,945,949,956,962,967,974,977,982,991,995,1001,1012,1018,1022,1025,1047,1054,1069,1076,1080,1087,1089,1103],[14,812,813,814,817,818,821],{},"If you run an accounting firm, a bookkeeping practice, or any professional-services firm, you already know the pattern: half your morning goes to answering the same ten questions. \"What documents do I need for my tax return?\", \"How long do I have to file?\", \"How much do you charge to form an LLC?\". Legitimate questions, repeated endlessly, eating time you should be billing. The answer isn't hiring another person for the phone, or putting up an FAQ page nobody reads. It's an ",[18,815,816],{},"AI agent for accounting firms"," that answers ",[27,819,820],{"c":29},"with your own knowledge"," — your procedures, your fees, your deadlines — qualifies the case, and books the consultation with you. The AI handles the repetitive stuff; the complex work, the part that actually matters, stays with you.",[202,823,825],{"title":824},"In 30 seconds",[205,826,827,833,844,854,860],{},[208,828,829,832],{},[18,830,831],{},"Repeat questions"," (requirements, deadlines, fees) eat billable hours that shouldn't touch a professional.",[208,834,835,836,839,840,843],{},"With ",[18,837,838],{},"RAG",", the agent answers from ",[18,841,842],{},"your real documentation",", not internet generalities. What it doesn't know, it hands off.",[208,845,846,847,52,850,853],{},"It ",[18,848,849],{},"qualifies the case",[18,851,852],{},"books the consultation"," with Google\u002FMicrosoft Calendar sync, no waiting, 24\u002F7.",[208,855,856,859],{},[18,857,858],{},"Draft Helpers"," leave the draft ready so your team just reviews instead of writing from scratch.",[208,861,862,865],{},[18,863,864],{},"Compliance",": AI disclosure (AI Act transparency), escalation to a person, and data hosted in the EU — key in sensitive fields.",[33,867,869],{"id":868},"the-repeat-questions-that-devour-billable-time","The repeat questions that devour billable time",[14,871,872],{},"At a firm, the problem isn't the volume of hard work. It's the noise around it. For every case that needs your judgment, twenty questions come in that anyone with the information in front of them could handle: which documents to bring, how much time is left to file, what a filing costs, whether last week's return is ready yet. Every interruption pulls you out of deep work and, worse, many land after hours: at nine at night, on a Saturday, right when the client remembers.",[14,874,875,876,880],{},"The cost isn't just the minute on the call. It's the context switch, the queue of unanswered WhatsApp messages, and the clients who — getting no quick reply — cool off or go to another firm. And it's expensive professionals' time spent on tasks that don't require a degree. The bill for not answering in time is higher than it looks, as the breakdown of ",[58,877,879],{"href":878},"\u002Fblog\u002Fcost-of-missed-calls-by-industry","how much missed calls cost by industry"," shows.",[641,882],{":duration":883,"text":884},"900","70% of inquiries don't need the professional",[14,886,887],{},"That's the opportunity. Most of what comes in by phone, WhatsApp, or email is informational: answers that already live in your head, in your old emails, and in your documents. The challenge was always that those answers were scattered and only you had them handy. A well-built AI agent makes them all available at once, on every channel, at any hour.",[132,889],{"align":134,"alt":890,"caption":891,"src":892},"AI agent for accounting firms checking the firm's knowledge base with RAG to answer a repeat question, on a matte navy background","The agent searches your real documentation before answering: it resolves the informational, and leaves the complex to the professional.","\u002Fimg\u002Fblog\u002Fagente-ia-despachos-servicios-profesionales-rag-wide.webp",[33,894,896],{"id":895},"what-a-rag-powered-ai-agent-is-for-an-accounting-firm","What a RAG-powered AI agent is for an accounting firm",[14,898,899,900,903,904,31],{},"Here's the piece that changes everything, no jargon. An out-of-the-box AI model knows a lot about the world and nothing about ",[18,901,902],{},"your firm",". It doesn't know your business-formation fee, or that you ask for specific documents for an estate matter, or your protocol when a client shows up with an IRS notice. If you let it fill in the gaps, it improvises — and at an accounting firm a made-up answer about a filing deadline or a requirement ",[27,905,906],{"c":29},"isn't a detail: it's a problem",[14,908,909,911,912,915,916,31],{},[18,910,838],{}," (retrieval-augmented generation) solves it. It means that, before answering, the agent ",[18,913,914],{},"searches your knowledge base"," for the relevant information and answers with that data, not with what it imagines. You feed it your own materials: internal procedures, fees, document checklists by filing, tax calendars, the FAQs you already answer a thousand times. The AI consults them in every conversation and ",[27,917,918],{"c":29},"speaks in your words",[14,920,921,922,924],{},"This is what separates a useful agent from a generic chatbot. Without RAG, the AI answers whatever a random search engine would say about income tax or a quarterly filing; with RAG, it answers what ",[18,923,902],{}," actually does, with your deadlines, your fees, and your way of asking for documents. And when your fee changes or a filing gets updated, you update the document in the knowledge base and the agent answers with the new version from the next conversation on — no retraining.",[151,926,929],{"title":927,"type":928},"What to put in a firm's knowledge base","tip",[14,930,931],{},"What your best admin would keep in their head: documents required per filing, deadlines and tax calendars, fees and payment methods, requirements for each service, protocols (\"if they bring an IRS notice, route to the tax team\"), real FAQs. The more specific, the more useful — and the less generic it sounds.",[14,933,934,935,938,939,31],{},"The practical upshot is clear. When someone asks \"What do I need to file my tax return?\", the agent doesn't recite a generic list from the internet: it lists ",[18,936,937],{},"your checklist",", the one you actually ask for. And when they ask something that isn't in your knowledge base, it doesn't improvise: it recognizes that and passes the conversation to a person on the team. That same grounding in your documentation is what makes the AI sound like your brand and not a brochure — something we dig into in ",[58,940,941],{"href":143},"how to train your AI receptionist",[466,943],{":items":944},"[{\"myth\":\"An AI at a firm will end up giving the wrong advice.\",\"reality\":\"Grounded in your knowledge base (RAG), it answers with your data on the informational stuff. Professional judgment it hands off; it doesn't improvise it.\"},{\"myth\":\"Setting this up is a months-long technical project.\",\"reality\":\"It's uploading your materials and approving the script. With TotemAI you're live in 48-72 hours, with no code.\"},{\"myth\":\"My clients want to talk to a person, not a bot.\",\"reality\":\"The bot handles the repetitive stuff instantly and passes the call to a person with the full context. The client can always ask to talk to you.\"}]",[33,946,948],{"id":947},"qualifying-the-case-and-booking-the-consultation-with-the-professional","Qualifying the case and booking the consultation with the professional",[14,950,951,952,955],{},"Answering questions is fine, but the real value comes when the agent ",[18,953,954],{},"turns"," the conversation into something actionable. At a firm that means two things: separating the informational from what needs your judgment, and getting the consultation onto your calendar without a single back-and-forth email.",[14,957,958,959,961],{},"The agent qualifies as it talks. Is it an estate matter or a new business registration? An individual or a company? How urgent is it, what documents do they have? With those answers it decides: if it's an informational question, it resolves it and closes; if it needs the professional, it ",[18,960,852],{}," directly, with Google or Microsoft Calendar sync and reminders by WhatsApp or voice so nobody forgets. And it sends an active reminder that cuts no-shows, because a calendar full of empty slots costs you money too.",[64,963],{":items":964,"caption":965,"title":966},"[{\"value\":\"60%\",\"label\":\"shorter response time\",\"accent\":\"teal\"},{\"value\":\"+50%\",\"label\":\"more appointments booked\",\"accent\":\"violet\"},{\"value\":\"-35%\",\"label\":\"fewer no-shows\",\"accent\":\"magenta\"},{\"value\":\"24\u002F7\",\"label\":\"coverage without hiring\",\"accent\":\"teal\"}]","Results according to our clients; they vary by industry and setup.","What our clients see",[14,968,969,970,973],{},"Everything gets logged. Every conversation lands on a Kanban-style lead board where the AI itself moves the card based on the outcome — consultation booked, waiting on documents, routed to the tax team — without you touching anything and without wiring up Zapier-style integrations. We cover that self-moving funnel in depth in ",[58,971,972],{"href":102},"the funnel that moves itself",". The professional opens their calendar in the morning and finds qualified, sorted consultations, not an inbox of loose messages to triage.",[171,975],{":steps":976},"[{\"title\":\"The inquiry comes in\",\"body\":\"It picks up the call in ~1 second; on WhatsApp or web it replies right away, at any hour.\"},{\"title\":\"It answers with your knowledge\",\"body\":\"Via RAG it resolves the informational — documents, deadlines, fees — with your real data.\"},{\"title\":\"It qualifies the case\",\"body\":\"It tells apart the type of filing, the urgency, and whether it needs professional judgment.\"},{\"title\":\"It books or hands off\",\"body\":\"It puts the consultation on your calendar, or makes a warm handoff to a person with the full context.\"}]",[132,978],{"align":197,"alt":979,"caption":980,"src":981},"The firm's Kanban board where the AI agent moves a lead's card toward a consultation booked on the calendar, on a matte navy background","Every conversation lands on the board and the AI moves the card based on the outcome: consultation booked, waiting on documents, or routed.","\u002Fimg\u002Fblog\u002Fagente-ia-despachos-servicios-profesionales-rag-inline.webp",[14,983,984,985,988,989,31],{},"When things get complicated, the ",[18,986,987],{},"warm handoff"," kicks in: the AI passes the conversation to someone on the team with the full context, the history right there, without the client having to repeat themselves. You don't lose the human touch; you save it for where it counts. We cover the full mechanics in ",[58,990,149],{"href":148},[33,992,994],{"id":993},"draft-helpers-drafts-ready-so-your-team-just-reviews","Draft Helpers: drafts ready so your team just reviews",[14,996,997,998,1000],{},"There's a band of work that's neither an FAQ question nor a matter for your professional judgment: writing the follow-up email, confirming the appointment with a recap of what was discussed, asking for the missing documents. That's what the ",[18,999,858],{}," take on.",[14,1002,1003,1004,1007,1008,31],{},"With the lead's context in front of it — what was asked, what was agreed, which documents are missing — the AI proposes the message ",[18,1005,1006],{},"draft",". The team reads it, tweaks it if they want, and sends it. It's not the AI sending on its own: it's the AI writing and a person deciding. The difference for a firm is real: instead of writing every follow-up from scratch, your team just reviews. And because the same RAG runs underneath, the draft uses your information, not generic templates. We dig into it in ",[58,1009,1011],{"href":1010},"\u002Fblog\u002Fai-writes-lead-follow-up-messages","Draft Helpers and RAG",[158,1013,1015],{"accent":1014},"teal",[14,1016,1017],{},"The question isn't \"what does the AI know?\" but \"what do you let it decide?\". At a firm, the informational it resolves; the judgment, it hands off.",[33,1019,1021],{"id":1020},"compliance-and-data-residency-an-ai-agent-for-a-sensitive-field","Compliance and data residency: an AI agent for a sensitive field",[14,1023,1024],{},"An accounting or tax firm handles sensitive data: financial, asset, sometimes health or family information. Here, compliance isn't an add-on — it's the price of entry. And it's where a lot of tools cobbled together from loose parts fall down.",[14,1026,1027,1028,1031,1032,1035,1036,1039,1040,378,1043,31],{},"TotemAI builds compliance in. The agent ",[18,1029,1030],{},"discloses that it's an AI"," naturally at the start. In the US, that's simply best practice — the FTC treats undisclosed AI as potentially deceptive — and it's a hard transparency obligation under the EU AI Act (Regulation (EU) 2024\u002F1689 — the AI Act — art. 50.1) for any system that interacts with people, which applies directly if some of your callers are EU residents. We also always offer a ",[18,1033,1034],{},"way to reach a person",". A word on the legal nuance: at a firm, an agent that informs, qualifies, or schedules doesn't make \"solely automated decisions with legal or similarly significant effects,\" so GDPR's right to human intervention (art. 22) isn't triggered in these cases — we offer the human handoff as a trust best practice, not because a law forces it, and so no one is ever left without a way out. And ",[18,1037,1038],{},"data is hosted on European infrastructure",": no law requires data to physically stay in the EU (GDPR's Chapter V allows transfers abroad with adequate safeguards), but hosting in the EU is a product choice that simplifies compliance and gives peace of mind in sensitive fields. If you want the legal detail, it's in ",[58,1041,1042],{"href":455},"built-in compliance: AI disclosure, EU residency and handoff",[58,1044,1046],{"href":1045},"\u002Fblog\u002Fwhere-is-your-chatbot-data-stored","where your chatbot's data is stored",[151,1048,1051],{"title":1049,"type":1050},"The golden rule at a firm","success",[14,1052,1053],{},"What the AI doesn't know, let it hand off — not make up. And whatever calls for professional judgment, let it book with you. One fewer answer but a well-served client is worth more than ten brilliant answers and one blown deadline.",[14,1055,1056,1057,1061,1062,1066,1067,31],{},"The pattern is the same across other services that live on qualifying well before handing off to the professional. You'll see it identically in ",[58,1058,1060],{"href":1059},"\u002Fblog\u002Fai-receptionist-driving-schools-tutoring","driving schools and tutoring centers, which qualify enrollments while class is in session",", and if you want the map by vertical, the ",[58,1063,1065],{"href":1064},"\u002Fblog\u002Fai-agents-by-industry-what-to-automate-first","playbook by industry"," sorts out which run on booking and which run on leads. The technology underneath — a voice agent that answers, qualifies, and connects to your team — is the same one we explain in ",[58,1068,715],{"href":714},[14,1070,1071,1072,1075],{},"And a note that eases the budget: with TotemAI you pay a ",[18,1073,1074],{},"fixed monthly plan"," with minutes and messages included, so the cost is predictable month to month. If a spike leaves you short, you top up with a one-time add-on and you can set a spend cap; you know what you pay each month.",[227,1077],{"cta":1078,"title":1079,"to":229,"variant":1014},"Book a free demo","Put an AI agent to work answering with your firm's knowledge",[14,1081,1082,1083,1086],{},"If you'd rather see the plans and start on your own, take a look at ",[58,1084,1085],{"href":522},"TotemAI's options",": live in 48-72 hours, no long-term contract, and a fixed monthly plan with minutes and messages included.",[33,1088,500],{"id":499},[205,1090,1091,1097],{},[208,1092,1093,1094],{},"AI Act (Regulation (EU) 2024\u002F1689), art. 50 (transparency) and art. 113 (application timeline) — ",[58,1095,511],{"href":508,"rel":1096},[510],[208,1098,1099,1100],{},"GDPR (Regulation (EU) 2016\u002F679), art. 22 (automated decisions) and Chapter V (international transfers with safeguards) — ",[58,1101,511],{"href":517,"rel":1102},[510],[1104,1105,1106],"fine-print",{},[14,1107,1108],{},"This guide is informational and not legal advice; if in doubt, consult your DPO or a lawyer.",{"title":234,"searchDepth":235,"depth":235,"links":1110},[1111,1112,1113,1114,1115,1116],{"id":868,"depth":238,"text":869},{"id":895,"depth":238,"text":896},{"id":947,"depth":238,"text":948},{"id":993,"depth":238,"text":994},{"id":1020,"depth":238,"text":1021},{"id":499,"depth":238,"text":500},"AI agent for accounting firms: a coral document folder connected by teal threads to an assistant that answers from the knowledge base, on a matte navy background","2026-06-04","An AI agent for accounting firms answers repeat questions from your own knowledge base (RAG), qualifies each case, and books the consultation.",[1121,1124,1127,1130,1133,1136],{"question":1122,"answer":1123},"What is a RAG-powered AI agent for a professional-services firm?","It's an assistant that, before answering, checks your knowledge base (procedures, fees, requirements, FAQs) and answers with your real information, not generalities. RAG stands for retrieval-augmented generation: the AI retrieves your documentation and answers anchored to it, so it doesn't make anything up.",{"question":1125,"answer":1126},"Can it give legal or tax advice without a professional?","No, and it shouldn't. The agent handles informational questions (requirements, deadlines, documents, fees), qualifies the case and books the consultation. Professional judgment — the actual advice — always stays with the person at the firm. You draw that line and the AI respects it.",{"question":1128,"answer":1129},"Is it compliant for a field that handles sensitive data?","The agent is built to fit GDPR and processes data on a valid legal basis, but no tool guarantees compliance on its own: it depends on how you configure it. It discloses that it's an AI (the AI Act's transparency duty), always offers an escalation to a person, and data is hosted on European infrastructure. The handoff to a professional is warm and carries the full context, so the client never has to repeat anything.",{"question":1131,"answer":1132},"How long until it's up and running?","With TotemAI you're live in 48-72 hours, with no code and no long-term contract. You upload your materials, approve the script and the agent starts answering by phone, WhatsApp and web.",{"question":1134,"answer":1135},"Which channels does an accounting firm's AI agent cover?","All of them at once: phone, WhatsApp and your website chat. The same knowledge base answers on every channel, so the client gets the same information whether they call at nine at night or write on a Saturday. Email also lands in the unified inbox, with one difference: there, the AI drafts the reply and a person reviews it before it goes out.",{"question":1137,"answer":1138},"What do I need to upload to build the firm's knowledge base?","Your own materials: documents required per filing, deadlines and tax calendars, fees, requirements by service, escalation protocols and the FAQs you already answer. The more specific, the better the agent answers and the less generic it sounds.","\u002Fimg\u002Fblog\u002Fagente-ia-despachos-servicios-profesionales-rag-cover.webp",{},"\u002Fblog\u002Fai-agent-accounting-firms-rag","By industry","8",{"title":808,"description":1119},"AI Agent for Accounting Firms (RAG-Powered)","blog\u002Fai-agent-accounting-firms-rag",[816,1148,1149,1150,1151,1152],"AI receptionist for professional services","RAG knowledge base chatbot","answer client questions from your own documents","qualify client intake with AI","book consultations with AI","An AI agent for accounting firms answers the repeat questions (requirements, deadlines, fees) from your own knowledge base (RAG), qualifies each case and books the consultation with the professional. The AI handles the repetitive work right away, 24\u002F7, and logs everything; the complex work stays with you. You approve what it knows and what it hands off; nothing is made up.","agente-ia-despachos-servicios-profesionales-rag","FYhmii1X4tgnu-ICm2g6Kx7luJpoz-a6XMzzNXcxy7g",{"id":1157,"title":1158,"author":7,"authorAvatar":8,"authorRole":9,"body":1159,"category":242,"coverAlt":1322,"dateModified":244,"datePublished":1118,"description":1323,"draft":247,"extension":248,"faq":1324,"featured":247,"heroImage":1343,"lang":269,"meta":1344,"navigation":271,"path":1345,"pillar":273,"readingMinutes":1346,"seo":1347,"seoTitle":1348,"stem":1349,"tags":1350,"tldr":1357,"translationKey":1358,"__hash__":1359},"blog_en\u002Fblog\u002Fmultilingual-ai-customer-service.md","Multilingual AI Customer Service, Without Hiring More People",{"type":11,"value":1160,"toc":1315},[1161,1172,1175,1179,1182,1185,1188,1194,1199,1203,1210,1213,1218,1224,1228,1231,1238,1241,1247,1251,1254,1258,1266,1271,1274,1293,1295,1308,1311],[14,1162,1163,1164,1167,1168,1171],{},"A prospect texts you on a Saturday night: \"¿Tienen disponibilidad para el próximo fin de semana?\" Nobody on your shift is comfortable replying in Spanish, so the message sits on read until Monday. By then they've already booked somewhere else. You didn't lose that sale on price or product: you lost it because nobody answered in the language the customer was asking in. ",[18,1165,1166],{},"Multilingual AI customer service"," solves exactly that: the AI detects the language of each message or call and replies in that same language, instantly, so you serve customers in several languages ",[27,1169,1170],{"c":29},"without hiring more people"," or setting up a shift per language.",[14,1173,1174],{},"That's what TotemAI does. The AI answers first on WhatsApp, Instagram, Messenger, your website chat, voice, and text; it understands which language you're being written in and replies in kind; and when a person is needed, someone on your team picks up the conversation in one click. Email is handled by the Draft Helper: it leaves a draft ready for you to review and send. Let's take it step by step.",[33,1176,1178],{"id":1177},"the-customer-who-hangs-up-because-nobody-speaks-their-language","The customer who hangs up because nobody speaks their language",[14,1180,1181],{},"The language barrier rarely shows up in a report. It isn't measured anywhere: the customer who calls, hears hesitation on the other end, and hangs up simply leaves no trace. But it's one of the most expensive leaks for any business that touches travel, private healthcare, or real estate. A traveler from Berlin, a buyer from Mexico City scouting a place to relocate, a French patient searching for a clinic: they all text or call, and for many of them English isn't their first language.",[14,1183,1184],{},"Until now, the only answer for serving customers in several languages was to hire. Someone who speaks Spanish at the front desk, another person who can get by in French, covering those languages at night and on weekends too… Costs spike and gaps remain anyway: nobody has a bilingual team on every shift. The language barrier overlaps with the hours barrier, and you lose international customers on both fronts at once.",[64,1186],{":items":1187},"[{\"value\":\"~1 s\",\"label\":\"To answer the phone, in the customer's language\"},{\"value\":\"24\u002F7\",\"label\":\"Nights, weekends, and peak season covered\"},{\"value\":\"60%\",\"label\":\"less response time, according to our clients\"}]",[14,1189,1190,1191,31],{},"Speed is the lever. A classic Lead Connect study, cited by InsideSales, found that 78% of customers buy from whoever responds first. If that \"first\" is also in their language, the advantage multiplies. On why response speed decides almost everything, we go deeper in ",[58,1192,1193],{"href":60},"the AI receptionist that answers in ~1 second",[132,1195],{"align":134,"alt":1196,"caption":1197,"src":1198},"Multilingual AI customer service by voice: a matte coral switchboard headset with three teal waves branching out toward bone-colored language pennants on a navy background","A single line serves every customer in their own language, instantly.","\u002Fimg\u002Fblog\u002Fatencion-multilingue-sin-contratar-mas-gente-wide.webp",[33,1200,1202],{"id":1201},"how-multilingual-ai-customer-service-works-by-voice-and-chat","How multilingual AI customer service works, by voice and chat",[14,1204,1205,1206,1209],{},"The part that surprises almost everyone is that ",[27,1207,1208],{"c":29},"you don't have to build an agent per language",". You don't set up \"the Spanish bot\" and \"the German bot\" separately. The AI detects the language of each incoming message and replies in that same language, naturally, whether it comes in by chat or by phone.",[14,1211,1212],{},"And where does it get the answers? From your own knowledge. You upload your prices, services, hours, and policies once—your knowledge base—and the AI answers with that information in the language of whoever's asking. It doesn't translate canned phrases: it says what your business would say, in German, French, or Spanish, as the case may be. It works the same for chat and voice: an AI voice agent answers the phone and handles the call in the caller's language, with no \"press 1 for English\" menus, resolving or booking directly.",[151,1214,1215],{"type":153},[14,1216,1217],{},"Language detection and multilingual replies come standard, in voice and chat. It's not a separate module or an extra charge per language: it's how Totem's AI works from day one.",[14,1219,1220,1221,31],{},"And one billing detail worth being clear about: Totem is a flat monthly plan with a bundle of included minutes and messages. AI usage draws down that bundle—a call it handles spends minutes, inbound or outbound—and if you go over in a given month, you top up with a one-time add-on and can set a spend cap. The upside is predictability: you know what you pay each month. If you want to hear how it sounds today, we cover it in ",[58,1222,1223],{"href":714},"AI voice agent for business",[33,1225,1227],{"id":1226},"serving-multiple-languages-without-hiring-the-human-steps-in-when-needed","Serving multiple languages without hiring: the human steps in when needed",[14,1229,1230],{},"The AI is excellent at the repetitive stuff and available when no one else is. But there are moments when a customer needs a person: a complaint, a negotiation, a delicate case, a situation that goes off-script. That's where the hybrid model makes the difference.",[14,1232,1233,1234,1237],{},"With TotemAI, anyone on your team picks up the conversation in one click. It's a warm handoff: whoever steps in gets the full thread, with everything the AI has already gathered, and in the customer's language. The customer doesn't repeat a thing. And here's the nuance almost nobody accounts for: ",[27,1235,1236],{"c":29},"your team doesn't need to be fluent in that language to follow the conversation",", because they have in front of them the context the AI already understood and summarized. The human touch is preserved without language being a wall.",[466,1239],{":items":1240},"[{\"myth\":\"To serve several languages, you have to hire someone per language.\",\"reality\":\"The AI detects and replies in each customer's language; one team covers every language, in voice and chat.\"},{\"myth\":\"A multilingual AI loses the personal touch.\",\"reality\":\"The AI covers the immediate stuff; your team steps in with one click, with the context summarized, exactly when it adds the most.\"},{\"myth\":\"Serving European customers with AI is a legal headache.\",\"reality\":\"The AI discloses that people are talking to an AI (transparency under AI Act art. 50.1) and can escalate to a person; if you handle EU residents' data, the GDPR applies.\"}]",[14,1242,1243,1244,31],{},"And, of course, a customer can always ask to speak with a person: the AI offers that escalation path at any time. It's worth clearing up the usual myth: the GDPR doesn't grant a \"general right to talk to a human\" in customer service. The right to human intervention under GDPR art. 22 (and comparable regimes) arises only for decisions made solely by automated means that produce legal or similarly significant effects on the person; a bot that books, informs, or schedules normally doesn't fall under that. Even so, offering escalation to a person is a good trust practice, which is why it comes standard. On how that handoff works under the hood, we cover it in depth in ",[58,1245,1246],{"href":148},"you don't lose the human touch: handoff with context",[33,1248,1250],{"id":1249},"multilingual-service-by-industry-hotels-clinics-and-real-estate","Multilingual service by industry: hotels, clinics, and real estate",[14,1252,1253],{},"The pattern repeats in any business whose customers cross borders, but it stands out especially in three verticals we work with every day.",[86,1255],{":columns":1256,":rows":1257},"[\"Industry\",\"What multilingual AI customer service solves\"]","[[\"Hotels\",\"A guest asks at night and in their own language; the AI captures the direct booking with no OTA commission and routes every request.\"],[\"Clinics\",\"International patients comparison-shopping; the AI informs, qualifies, and books in their language, 24\u002F7, without overwhelming the front desk.\"],[\"Real estate\",\"Out-of-town buyers message about a listing; the AI replies instantly in their language and books the showing before they go cold.\"]]",[14,1259,1260,1261,1265],{},"At a hotel, answering first and in the guest's language is what turns a midnight inquiry into a direct booking instead of a commissioned one; we go deeper in ",[58,1262,1264],{"href":1263},"\u002Fblog\u002Fai-agent-hotels-direct-bookings","multilingual AI agents for hotels",". At a clinic or a real estate agency, the same logic applies: the lead who writes in another language is the one that goes cold fastest if nobody answers.",[132,1267],{"align":197,"alt":1268,"caption":1269,"src":1270},"Multilingual service for hotels and real estate: a matte coral hotel key with a teal tag showing a chat bubble with a bone-colored language pennant on a navy background","The same flow captures bookings and showings from out-of-town customers, in their language.","\u002Fimg\u002Fblog\u002Fatencion-multilingue-sin-contratar-mas-gente-inline.webp",[14,1272,1273],{},"And nothing gets lost along the way. Behind the scenes, every conversation lands on a Kanban-style lead board where the AI moves the contact based on what happens, and it's logged with its full history. The French customer who asked about an event space and went quiet is still right there, waiting for follow-up, not buried in an endless chat thread.",[202,1275,1276],{},[205,1277,1278,1281,1284,1287,1290],{},[208,1279,1280],{},"The AI detects the language of each message or call and replies in that same language: it answers the phone in ~1 second and replies to messages right away, 24\u002F7.",[208,1282,1283],{},"You don't build an agent per language: multilingual replies come standard, powered by your own knowledge base.",[208,1285,1286],{},"One team covers customers in multiple languages, with no hiring per language or per shift.",[208,1288,1289],{},"The one-click human handoff keeps the context summarized, so language is never a wall for your team.",[208,1291,1292],{},"Built to EU-grade standards: AI disclosure (transparency under AI Act art. 50.1), escalation to a person, and data handling under the GDPR—a strict baseline that holds up even if you serve EU customers.",[33,1294,500],{"id":499},[205,1296,1297,1302],{},[208,1298,1093,1299],{},[58,1300,511],{"href":508,"rel":1301},[510],[208,1303,1304,1305],{},"GDPR (Regulation (EU) 2016\u002F679), art. 22 (automated decisions) and Chapter V (international transfers) — ",[58,1306,511],{"href":517,"rel":1307},[510],[14,1309,1310],{},"Setting it up isn't a months-long project: TotemAI goes live in 48–72 hours, with no lock-in. The Pro plan (€179\u002Fmo plus applicable tax, the most popular) comfortably covers voice plus chat; with the annual plan, two months are free. And because it's a flat monthly plan with included minutes and messages, serving multiple languages carries a predictable cost: you know what you pay each month.",[227,1312],{"buttonHref":229,"buttonText":230,"description":1313,"title":1314},"We'll show you how the AI replies in each person's language, by voice and chat, and hands off to your team when needed. Live in 48–72 h, no lock-in.","Serve every customer's language, this week",{"title":234,"searchDepth":235,"depth":235,"links":1316},[1317,1318,1319,1320,1321],{"id":1177,"depth":238,"text":1178},{"id":1201,"depth":238,"text":1202},{"id":1226,"depth":238,"text":1227},{"id":1249,"depth":238,"text":1250},{"id":499,"depth":238,"text":500},"Multilingual AI customer service: a matte coral conversation bubble sprouting three teal threads with bone-colored language pennants on a navy background","Multilingual AI customer service replies in each customer's language by voice and chat, 24\u002F7. One team covers every language without extra hires.",[1325,1328,1331,1334,1337,1340],{"question":1326,"answer":1327},"How many languages can the AI handle?","The AI detects the language of each message or call and replies in that same language, in both chat and voice. That covers virtually all international customers without you having to hire staff per language or per shift.",{"question":1329,"answer":1330},"Do I have to set up each language one by one?","No. You don't define an agent per language: detection and replying in the customer's language come standard. You provide your knowledge (prices, services, policies) once and the AI uses it to answer in the language of whoever's asking.",{"question":1332,"answer":1333},"What if the customer prefers to talk to a person?","They can ask at any time. The AI answers first and, in one click, someone on your team picks up the conversation with the full history in front of them—a warm handoff—in the customer's language, without them having to repeat themselves.",{"question":1335,"answer":1336},"Is it GDPR-compliant if I serve EU customers?","It's built to help you comply, but compliance depends on how you configure and use it. The AI discloses that people are talking to an AI—a transparency obligation under the EU AI Act (art. 50.1 of Regulation (EU) 2024\u002F1689)—it can escalate to a person whenever a customer asks, and if you take calls from or handle data of EU residents, the GDPR applies. GDPR doesn't require data to stay physically in the EU: it permits international transfers with appropriate safeguards (Chapter V of the GDPR). If you operate in the US, regimes like the TCPA (calls and texts) and CCPA (data) may also apply. This is informational and not legal advice; consult your data protection officer or a lawyer.",{"question":1338,"answer":1339},"Which languages does it handle best for customers in the US?","The most common languages of international customers reaching a US business—Spanish, French, and German, on top of English—are handled naturally by voice and chat. Because the AI detects the language of each message, there's no fixed list: it replies in whatever language you're written in.",{"question":1341,"answer":1342},"Is it cheaper than hiring someone who speaks other languages?","Usually, yes. Instead of adding a person per language and per shift, one team covers every language with the AI up front. Plus, you pay a flat monthly plan with included minutes and messages, so you know what customer service costs each month.","\u002Fimg\u002Fblog\u002Fatencion-multilingue-sin-contratar-mas-gente-cover.webp",{},"\u002Fblog\u002Fmultilingual-ai-customer-service","6",{"title":1158,"description":1323},"Multilingual AI Customer Service, No Extra Hires","blog\u002Fmultilingual-ai-customer-service",[1351,1352,1353,1354,1355,1356],"multilingual AI customer service","multilingual customer support without hiring","multilingual AI receptionist","answer customers in any language","multilingual voice and chat AI","serve international customers with AI","Multilingual AI customer service detects the language of each message or call and replies in that same language—answering the phone in ~1 second and messages right away, 24\u002F7—with no per-language hires. When a person is needed, your team picks up in one click with full context, in the customer's language. One team covers Spanish, French, or German (or any of 40+ languages) without extra hires or a shift per language.","atencion-multilingue-sin-contratar-mas-gente","w7WF57DepkWlHlT5-knENaLFJ_xWwLWo56_dB0SsPrw",{"id":1361,"title":1362,"author":7,"authorAvatar":8,"authorRole":9,"body":1363,"category":242,"coverAlt":1536,"dateModified":244,"datePublished":1537,"description":1538,"draft":247,"extension":248,"faq":1539,"featured":247,"heroImage":1558,"lang":269,"meta":1559,"navigation":271,"path":1560,"pillar":1142,"readingMinutes":274,"seo":1561,"seoTitle":1562,"stem":1563,"tags":1564,"tldr":1571,"translationKey":1572,"__hash__":1573},"blog_en\u002Fblog\u002Fai-voice-agent-restaurants.md","AI Voice Agent for Restaurants: Take Reservations Without Picking Up the Phone",{"type":11,"value":1364,"toc":1529},[1365,1368,1372,1375,1382,1385,1388,1392,1395,1399,1404,1407,1410,1413,1422,1426,1429,1432,1437,1444,1448,1451,1454,1457,1462,1467,1471,1478,1482,1485,1490,1493,1512,1524],[14,1366,1367],{},"Yes: an AI voice agent for restaurants can take reservations while your team is plating up, without anyone having to pick up the phone. It answers in about a second, checks real availability, confirms the table, and, if things get complicated, hands the call to a person with full context. What follows is how that fits into a real service, where it saves you empty tables, and what it costs (hint: a flat monthly plan with minutes and messages included, so you know what you pay each month).",[33,1369,1371],{"id":1370},"why-restaurants-lose-reservations-by-phone-during-the-rush","Why restaurants lose reservations by phone during the rush",[14,1373,1374],{},"Two in the afternoon. Dining room full, orders coming in, two servers for twelve tables. And the phone, ringing. Nobody can pick up without abandoning a guest who's already seated. So it rings, and rings, and eventually goes to voicemail or, worse, to nothing. The caller wanted a table for six on Friday. They hang up and call the place across the street.",[14,1376,1377,1378,1381],{},"That call wasn't an interruption. It was a reservation. And ",[27,1379,1380],{"c":29},"it just turned into an empty table on a Friday night",", which is exactly the night you can't afford to have gaps.",[14,1383,1384],{},"The problem isn't your team. It's physical: one person can't work the floor and the phone at the same time during the rush. And the phone always rings during the rush, because that's when people are thinking about eating. If you only have one line on top of that, the second reservation call hits a busy signal and that customer won't try again. Your restaurant's phone coverage, right when the most tables are on the line, is the first place customers slip away.",[64,1386],{":items":1387},"[{\"value\":\"~1 s\",\"label\":\"to answer, 24\u002F7\"},{\"value\":\"−35%\",\"label\":\"no-shows, according to our clients\"},{\"value\":\"+50%\",\"label\":\"more appointments and reservations booked\"},{\"value\":\"Flat\",\"label\":\"monthly plan, no surprises\"}]",[33,1389,1391],{"id":1390},"how-an-ai-voice-agent-for-restaurants-takes-reservations-by-voice-and-whatsapp-247","How an AI voice agent for restaurants takes reservations by voice and WhatsApp 24\u002F7",[14,1393,1394],{},"An AI voice agent picks up on the first ring, every time. It doesn't get tired, it isn't plating up, it doesn't have a bad day. And it isn't limited to the phone: the same assistant also handles WhatsApp, Instagram, Messenger, text, and web chat, all in a single dashboard. It doesn't matter which channel the customer reaches you on.",[1396,1397],"mockup-call",{"caption":1398},"The AI answers and takes the reservation live",[132,1400],{"align":134,"alt":1401,"caption":1402,"src":1403},"AI voice agent for restaurants confirming a reservation over WhatsApp on a coral smartphone, with a restaurant table in the background on navy","A single reservation comes in by voice or WhatsApp and confirms itself, without anyone on the floor touching the phone.","\u002Fimg\u002Fblog\u002Fagente-ia-restaurantes-reservas-sin-descolgar-wide.webp",[14,1405,1406],{},"Here's what it does on a normal reservation, without anyone on the floor stepping in:",[171,1408],{":steps":1409},"[{\"title\":\"Answers and introduces itself\",\"description\":\"Picks up in ~1 second and mentions, naturally, that it's an AI assistant. Asks how many people and for when.\"},{\"title\":\"Checks real availability\",\"description\":\"Looks at your synced calendar or shift sheet and offers only slots that truly exist. No double bookings.\"},{\"title\":\"Confirms the table\",\"description\":\"Locks in the reservation, takes a name and a phone number, and puts it on your calendar instantly. The customer gets a confirmation by WhatsApp.\"},{\"title\":\"Handles changes and cancellations\",\"description\":\"If they call to move the time or cancel, it handles it on its own and frees the slot for another reservation to take.\"}]",[14,1411,1412],{},"The interesting part isn't just the new reservation. It's the last-minute change. \"Hey, turns out we're four, not six.\" \"Can we push it to nine thirty?\" Those calls, which normally eat up a minute of your server's time at the very peak of service, the agent handles without breaking a sweat. And when someone cancels, that slot becomes available again automatically for the next reservation.",[14,1414,1415,1416,1419,1420,31],{},"It also works in multiple languages, which helps if you get tourists: the agent takes the reservation in whatever language the caller speaks. If you want to see how this same booking logic applies to other appointment-based businesses, the ",[58,1417,1418],{"href":1064},"AI agents by industry playbook"," breaks it down, and to understand the technology under the hood there's the full guide to an ",[58,1421,1223],{"href":714},[33,1423,1425],{"id":1424},"reservation-reminders-that-curb-restaurant-no-shows","Reservation reminders that curb restaurant no-shows",[14,1427,1428],{},"The ghost reservation is the other hole money falls through. A table for eight on a Saturday that never shows, and you've turned away the people who would have come. According to restaurant-industry data compiled by OpenTable, around 20% of unconfirmed reservations end in a no-show. A large table that doesn't arrive on a Saturday can be the whole night's margin.",[14,1430,1431],{},"The defense against that isn't charging everyone a deposit (though sometimes it helps). It's active confirmation: a reminder by WhatsApp or voice a few hours ahead, with a clear button to confirm or cancel.",[151,1433,1434],{"type":928},[14,1435,1436],{},"People don't usually no-show out of bad faith. They miss because they forget, or because they're no longer coming and can't be bothered to call and cancel. A reminder with a one-tap cancel option takes away that friction and gets the slot back to you in time to fill it.",[14,1438,1439,1440,31],{},"When a customer cancels from the reminder, the slot opens up and you can offer it to another reservation or your waitlist. It's the difference between an empty table at nine and a table that earns. According to our clients, this reminder approach cuts no-shows by around 35%. We go deeper on the exact cadence that works in the ",[58,1441,1443],{"href":1442},"\u002Fblog\u002Fhow-to-reduce-no-shows","guide to reducing no-shows",[33,1445,1447],{"id":1446},"handing-off-to-your-team-only-when-its-truly-needed","Handing off to your team only when it's truly needed",[14,1449,1450],{},"This is where a good agent separates itself from a 1990s touch-tone menu. The AI doesn't try to solve everything. It handles the repetitive stuff (reservations, changes, hours, whether you have a patio, whether there are gluten-free options) and recognizes when a conversation needs a person.",[466,1452],{":items":1453},"[{\"myth\":\"If I bring in an AI, I lose the human touch that sets my restaurant apart.\",\"reality\":\"The AI takes the mechanical part. A large event, a serious allergy, a complaint: that goes to a person on your team in one click, with the full context of the call already written down.\"},{\"myth\":\"Customers get annoyed when they realize they're talking to a machine.\",\"reality\":\"They get annoyed when nobody picks up the phone. The agent says it's an AI and, if the caller asks to speak with someone, puts them through to a person. No menu mazes.\"}]",[14,1455,1456],{},"The handoff is warm: when the conversation jumps to your team, the person sees who's calling, what they wanted, and what's already been said. Nobody has to repeat anything. If you take reservations from or handle the data of EU residents, the EU AI Act (Regulation (EU) 2024\u002F1689) requires telling people they're talking to an AI, and a reservation bot is a limited-risk system, not high-risk; either way, disclosing it up front is good practice everywhere (and what the FTC and state law point toward), and the agent does it at the start. Letting a caller reach a person when they ask isn't a general legal requirement —a reservation bot doesn't make the kind of solely-automated decision with legal effects that GDPR Article 22 covers— but it is a trust best practice, and here it comes built in. Where EU residents' data is involved, it's handled under GDPR, with the Chapter V safeguards for any transfer; Totem holds to that EU-grade standard by default. This is informational, not legal advice.",[158,1458,1459],{},[14,1460,1461],{},"The AI doesn't replace your host. It takes forty reservation calls off their plate so they can be in the dining room, which is where they really add value.",[132,1463],{"align":197,"alt":1464,"caption":1465,"src":1466},"Warm handoff from the AI voice agent to the restaurant team: a teal headset passes a coral context card to a human hand on a navy background","The warm handoff: the AI handles the mechanical part and passes to a person the call that truly needs it, with full context.","\u002Fimg\u002Fblog\u002Fagente-ia-restaurantes-reservas-sin-descolgar-inline.webp",[33,1468,1470],{"id":1469},"what-it-costs-a-flat-monthly-plan-no-surprises","What it costs: a flat monthly plan, no surprises",[14,1472,1473,1474,1477],{},"This is the part that throws almost everyone, so let's get to it: with Totem you pay ",[27,1475,1476],{"c":29},"a flat monthly plan with minutes and messages included",". Usage draws from that allowance: the minutes the AI talks and the messages it sends count, whether the calls come in or go out. The advantage isn't that inbound is free, it's that you know what you pay each month; and if a packed Friday leaves your allowance short, you top up with a one-time add-on and can set a spend cap.",[641,1479],{"label":1480,"value":1481},"a monthly plan with minutes and messages included","Flat",[14,1483,1484],{},"For a restaurant, where the bulk of the volume is calls coming in looking for a table, this completely changes the math versus a traditional answering service with a per-minute meter that runs away: a flat plan with an included allowance is far easier to budget for.",[86,1486],{":columns":1487,":highlightColumn":1488,":items":1489},"[\"\",\"With an AI agent\",\"Traditional service\"]","1","[{\"feature\":\"How you pay\",\"a\":\"Flat monthly plan with an included allowance\",\"b\":\"Per-minute meter that runs away\"},{\"feature\":\"Availability\",\"a\":\"24\u002F7, including nights and holidays\",\"b\":\"Business hours\"},{\"feature\":\"Reservations and changes by WhatsApp\",\"a\":\"Yes, same agent\",\"b\":\"Usually not\"},{\"feature\":\"Anti-no-show reminders\",\"a\":\"Included\",\"b\":\"Separate or nonexistent\"}]",[14,1491,1492],{},"Plans run from Chat (€49\u002Fmo) and Voice (€99\u002Fmo) up to Pro (€179\u002Fmo, the most popular), all plus applicable tax, with annual billing working out to two months free, no lock-in, and live in 48–72 hours. Most restaurants start with voice plus WhatsApp because that's where the money is: the reservations.",[202,1494,1495],{},[205,1496,1497,1500,1503,1506,1509],{},[208,1498,1499],{},"During the rush nobody can pick up; every missed call is an empty table. The agent answers in ~1 second, every time.",[208,1501,1502],{},"It takes reservations and changes by voice and WhatsApp 24\u002F7, checking real availability so tables aren't double-booked.",[208,1504,1505],{},"Reminders with active confirmation cut no-shows by around 35% (according to our clients).",[208,1507,1508],{},"It hands your team only what truly needs a person, with a warm handoff and full context.",[208,1510,1511],{},"You pay for it with a flat monthly plan that includes minutes and messages: you know what you pay each month, and if a spike leaves you short you top up with a one-time add-on.",[14,1513,1514,1515,1518,1519,1523],{},"An AI voice agent won't make your kitchen better. But it will make sure ",[27,1516,1517],{"c":29},"everyone who wants to eat at your restaurant gets a table, instead of hanging up and calling the place next door",". And this isn't unique to hospitality: if you manage a schedule in any industry, see how the same ",[58,1520,1522],{"href":1521},"\u002Fblog\u002Fai-receptionist-hair-salons","AI booking assistant for hair salons and beauty studios"," works.",[227,1525],{"button-link":229,"button-text":1526,"text":1527,"title":1528},"Talk to us","Put an AI voice agent on your phone and WhatsApp 24\u002F7. Live in 48–72 hours, no lock-in, and with a flat monthly plan that includes minutes and messages.","Never let another reservation slip away",{"title":234,"searchDepth":235,"depth":235,"links":1530},[1531,1532,1533,1534,1535],{"id":1370,"depth":238,"text":1371},{"id":1390,"depth":238,"text":1391},{"id":1424,"depth":238,"text":1425},{"id":1446,"depth":238,"text":1447},{"id":1469,"depth":238,"text":1470},"AI voice agent for restaurants: a matte clay render of a table with a coral reserved sign and a teal headset floating over a navy background","2026-05-21","An AI voice agent for restaurants answers in ~1 second, takes reservations by phone and WhatsApp 24\u002F7 and cuts no-shows with reminders.",[1540,1543,1546,1549,1552,1555],{"question":1541,"answer":1542},"Does the AI voice agent sound like a robot on the phone?","Today an AI voice agent answers in English in about a second, with a natural voice. It says up front that it's an AI and, if the caller prefers, hands the call to a person on your team with full context.",{"question":1544,"answer":1545},"How does it connect to my reservation system?","The agent uses booking pages synced with your calendar (Google or Microsoft) or your shift sheet. It takes the reservation, checks real availability, and confirms it without anyone on the floor having to touch the phone.",{"question":1547,"answer":1548},"How much does it cost to handle the calls coming into the restaurant?","You pay a flat monthly plan with minutes and messages included. Usage draws from that allowance: the minutes the AI talks and the messages it sends count, whether inbound or outbound. If you run over in a given month, you top up with a one-time add-on and can set a spend cap, so the cost stays predictable.",{"question":1550,"answer":1551},"Does it also handle WhatsApp, not just the phone?","Yes. The same agent answers calls and messages from WhatsApp, Instagram, Messenger, text, and web chat, all in a single dashboard, so no table request goes unanswered.",{"question":1553,"answer":1554},"Does an AI voice agent help reduce restaurant no-shows?","Yes. It sends a reminder by WhatsApp or voice a few hours ahead with a button to confirm or cancel in one tap. When someone cancels, the slot frees up automatically for your waitlist. According to our clients, this approach cuts no-shows by around 35%.",{"question":1556,"answer":1557},"Can it handle several reservation calls at once during the rush?","Yes. Unlike a single phone line, the agent handles several reservations in parallel, so at the midday peak or on a packed Friday no call is lost to a busy signal.","\u002Fimg\u002Fblog\u002Fagente-ia-restaurantes-reservas-sin-descolgar-cover.webp",{},"\u002Fblog\u002Fai-voice-agent-restaurants",{"title":1362,"description":1538},"AI Voice Agent for Restaurants: Book Tables 24\u002F7","blog\u002Fai-voice-agent-restaurants",[1565,1566,1567,1568,1569,1570],"AI voice agent for restaurants","restaurant AI phone answering","take restaurant reservations 24\u002F7","reduce restaurant no-shows","never miss a reservation call","AI answers the restaurant phone","An AI voice agent for restaurants answers the phone in ~1 second and takes the reservations your team can't get to during the rush. It handles bookings and changes by voice and WhatsApp 24\u002F7, sends reminders that curb no-shows, and only passes a call to a person when it's genuinely needed. And you pay for it with a flat monthly plan that includes minutes and messages.","agente-ia-restaurantes-reservas-sin-descolgar","M9Qto-qBqg2L1_HTqjleO6HvOmOzj8HoeKUwKynyl8I",{"id":1575,"title":1576,"author":7,"authorAvatar":8,"authorRole":9,"body":1577,"category":1833,"coverAlt":1834,"dateModified":1835,"datePublished":1836,"description":1837,"draft":247,"extension":248,"faq":1838,"featured":247,"heroImage":1857,"lang":269,"meta":1858,"navigation":271,"path":1859,"pillar":1860,"readingMinutes":274,"seo":1861,"seoTitle":1862,"stem":1863,"tags":1864,"tldr":1871,"translationKey":1872,"__hash__":1873},"blog_en\u002Fblog\u002Fai-receptionist-pricing-minutes-messages.md","AI Receptionist Pricing Explained: Minutes, Messages, and Top-Ups",{"type":11,"value":1578,"toc":1824},[1579,1582,1585,1589,1592,1599,1606,1613,1616,1619,1624,1628,1635,1646,1654,1657,1661,1667,1670,1676,1683,1688,1692,1698,1701,1704,1716,1721,1725,1732,1735,1747,1758,1762,1766,1781,1784,1787,1791,1798,1817,1820],[14,1580,1581],{},"Totem is a flat monthly plan with a bundle of minutes and messages included. That usage splits across three places, and only three: the minutes the AI spends handling calls, the messages in your conversations, and the Meta-approved WhatsApp templates. Understand those three buckets and you understand your whole monthly bundle. And with that, you'll know in thirty seconds whether what you need is a one-off top-up to refill your credit or a bigger plan.",[14,1583,1584],{},"The advantage of a flat plan with a bundle included is predictability: you know up front what you pay and what's in the price, instead of a per-minute meter that starts at zero and runs away. A business looks at the dashboard, sees its three buckets, and understands exactly where the spend comes from. That clarity is what completely changes what you'll actually end up paying.",[33,1586,1588],{"id":1587},"what-uses-up-your-bundle-minutes-messages-and-templates","What uses up your bundle: minutes, messages, and templates",[14,1590,1591],{},"Let's open up the three usage buckets of your AI agent, because each one is spent in a different way.",[14,1593,1594,1595,1598],{},"The first is ",[18,1596,1597],{},"minutes",". These are the time the AI spends handling calls, and they count whether it takes the call or places it: when the AI picks up a customer's call, or calls out to confirm an appointment, return a missed call, or follow up, that talk time draws minutes from your bundle. It's counted by the call's real duration, to the second, with no rounding up to the next minute: a 1:57 call bills 1:57, not 2:00.",[14,1600,1601,1602,1605],{},"The second is ",[18,1603,1604],{},"messages",". Every message in your conversations over WhatsApp, text, Instagram, Messenger, or email counts as one message unit. It doesn't matter whether the AI writes it or someone on your team types it from the inbox: it's your business's messaging with your customers.",[14,1607,1608,1609,1612],{},"The third is ",[18,1610,1611],{},"WhatsApp templates",", the HSMs approved by Meta. These have their own cost logic because Meta charges for starting conversations, and we'll cover it in detail at the end.",[64,1614],{":items":1615},"[{\"value\":\"3\",\"label\":\"usage buckets: minutes, messages, and templates\"},{\"value\":\"1\",\"label\":\"flat plan with a bundle included and a spending cap\"},{\"value\":\"~1 s\",\"label\":\"how fast the AI picks up the phone\"}]",[14,1617,1618],{},"The point of keeping it split like this is that you can read your dashboard and understand where the spend comes from. If minutes spike one month, you know there were a lot of calls. If messages go up, it was the messaging. It's not an opaque number: it's your activity, broken down.",[132,1620],{"align":134,"alt":1621,"caption":1622,"src":1623},"AI agent usage: three clay gauges—minutes, messages, and WhatsApp templates—rising with use, next to a coral dial marking the plan's spending cap","Your bundle splits across three gauges—minutes, messages, and templates—that move with use, with a spending cap you set.","\u002Fimg\u002Fblog\u002Fminutos-mensajes-plantillas-consumo-top-ups-wide.webp",[33,1625,1627],{"id":1626},"the-real-value-a-flat-plan-with-a-bundle-included-and-a-spending-cap","The real value: a flat plan with a bundle included and a spending cap",[14,1629,1630,1631,1634],{},"Here's the part that puts people most at ease. ",[18,1632,1633],{},"You know what you pay up front."," Totem is a flat monthly price with a bundle of minutes and messages included, sized to your volume. It's not a meter that starts at zero and climbs with every second until a surprise bill lands: it's a number you can budget for.",[14,1636,1637,1638,1641,1642,1645],{},"That predictability is what really changes how you operate. A small business can go from not answering the phone to catching every call and every message, knowing exactly what its spending floor is that month. And if activity spikes one month, you have two safety nets: a ",[18,1639,1640],{},"spending cap"," you set and one-off ",[18,1643,1644],{},"top-ups"," for the peak.",[151,1647,1648],{"type":1050},[14,1649,1650,1651,31],{},"A flat plan is easier to budget for than a per-minute meter. You know what your bundle includes, you watch your activity draw it down on the dashboard, and you set a cap so there are no month-end surprises. We break it down fully in ",[58,1652,1653],{"href":440},"why a flat plan beats the per-minute meter",[14,1655,1656],{},"This changes the mindset you bring to choosing a plan. Instead of worrying \"in case they call a lot,\" you pick the tier whose bundle covers your usual volume of calls and messages, and you leave top-ups for the exceptional months. You size it to your real activity: how many calls the AI handles, how many reminders and follow-ups it sends, how many campaigns you run a month.",[33,1658,1660],{"id":1659},"top-ups-when-to-add-credit-and-how-to-set-a-cap","Top-ups: when to add credit and how to set a cap",[14,1662,1663,1664,1666],{},"One month you come up short. You launched a campaign, hit a good run of leads, the calendar filled up, and the reminders flew out. No problem: that's what ",[18,1665,1644],{}," are for—credit refills you add without touching your plan.",[171,1668],{":steps":1669},"[{\"title\":\"You spot the peak\",\"description\":\"The dashboard alerts you when your monthly bundle drops below a certain threshold. You don't find out at month-end with the bill: you see it coming.\"},{\"title\":\"You top up what you need\",\"description\":\"You add a refill of minutes or messages in a couple of clicks. The extra credit stacks on top of the plan and you keep going without slowing down.\"},{\"title\":\"You set a spending cap\",\"description\":\"You set a maximum limit. When it's reached, the platform stops drawing extra credit and alerts you to decide.\"}]",[14,1671,1672,1673,31],{},"That spending cap is the safety net. You set it once and forget it: no top-up will run away unless you decided it. If you hit the limit, the platform stops and asks you, instead of quietly charging on. For a business watching every dollar, ",[27,1674,1675],{"c":592},"that predictability is worth as much as the savings",[14,1677,1678,1679,1682],{},"The top-up is the tool for the ",[18,1680,1681],{},"exceptional",". A salon's holiday rush, a clinic's campaign month, a real estate agency's spike when it lists ten properties at once. You pay just that month's extra and go back to your normal pace.",[132,1684],{"align":197,"alt":1685,"caption":1686,"src":1687},"Spending cap on a top-up: a clay credit tank with a coral dial stopping the teal stream right at the set limit","The spending cap is the safety net: extra credit is cut off where you decide.","\u002Fimg\u002Fblog\u002Fminutos-mensajes-plantillas-consumo-top-ups-inline.webp",[33,1689,1691],{"id":1690},"top-up-or-upgrade-how-to-decide-by-recurrence","Top-up or upgrade: how to decide by recurrence",[14,1693,1694,1695,31],{},"So when do you top up and when do you change plans? The clue is a single word: ",[18,1696,1697],{},"recurrence",[466,1699],{":items":1700},"[{\"myth\":\"If I come up short, I just top up. A top-up is always the cheapest.\",\"reality\":\"A top-up is the cheapest for a single month. If you come up short three months in a row, the per-unit price built into a bigger plan beats topping up over and over.\"},{\"myth\":\"Upgrading means committing to more than I use.\",\"reality\":\"No lock-in: if you go over one month and not the next, you adjust. The plan isn't a cage—it's the tier where your usual usage is the best deal.\"}]",[14,1702,1703],{},"The practical rule: one short month, top up. Two or three short months in a row, move up a plan. When topping up stops being the exception and becomes the norm, you're overpaying by doing it à la carte. The higher plan includes more credit at a better per-unit price, and since there's no lock-in, you risk nothing by trying it.",[14,1705,1706,1707,1711,1712,31],{},"If you're not sure which tier you fit, the guide on ",[58,1708,1710],{"href":1709},"\u002Fblog\u002Fwhich-totemai-plan-to-choose","which TotemAI plan to choose"," places you among Chat, Voice, Pro, Studio, and Scale based on your real volume of minutes and messages. And if you want to understand the voice-minute price from the inside, it's broken down in ",[58,1713,1715],{"href":1714},"\u002Fblog\u002Fhow-much-does-ai-voice-agent-cost","how much an AI voice agent costs",[158,1717,1718],{},[14,1719,1720],{},"One short month is fixed with a top-up. Three short months in a row are fixed with a plan. Your own dashboard tells you the difference.",[33,1722,1724],{"id":1723},"meta-approved-whatsapp-templates-their-own-rate-and-per-unit-price","Meta-approved WhatsApp templates: their own rate and per-unit price",[14,1726,1727,1728,1731],{},"WhatsApp templates deserve their own section because they don't work like a normal message. Meta requires that any message that ",[18,1729,1730],{},"starts"," a conversation with a customer (an appointment reminder, a confirmation, a notification) use a pre-approved template, an HSM.",[14,1733,1734],{},"Those templates have their own pricing logic. Meta charges per template sent by type—utility, marketing, authentication—and that per-unit cost shows up in your usage separately from normal reply messages. It's not a platform whim: it's how WhatsApp Business bills at the source.",[151,1736,1737],{"type":153},[14,1738,1739,1740,1743,1744,1746],{},"A message that ",[18,1741,1742],{},"replies"," within the 24-hour window after the customer writes to you is conversational and counts as a normal message. A template that ",[18,1745,1730],{}," the conversation outside that window is an HSM and has its own price. Knowing how to tell them apart is half of controlling your WhatsApp spend.",[14,1748,1749,1750,1753,1754,31],{},"The good news is that templates are exactly where each dollar goes furthest. A WhatsApp appointment reminder costs pennies and, according to our clients, helps cut no-shows by up to 35%. ",[27,1751,1752],{"c":592},"A single recovered appointment pays for a lot of templates",". The channel's per-message price, with its categories and fine print, is laid out in full in ",[58,1755,1757],{"href":1756},"\u002Fblog\u002Fwhatsapp-business-api-pricing-2026","WhatsApp Business API: pricing per message in 2026",[86,1759],{":columns":1760,":items":1761},"[\"Action\",\"Usage\",\"Type\"]","[{\"feature\":\"The AI's minutes on the phone (taking or placing the call)\",\"consumo\":\"Minutes from the bundle\",\"tipo\":\"By real duration, to the second\"},{\"feature\":\"A message in your conversations (WhatsApp, text, email...)\",\"consumo\":\"1 message from the bundle\",\"tipo\":\"Per unit\"},{\"feature\":\"A reply within 24 hours\",\"consumo\":\"1 message\",\"tipo\":\"Conversational\"},{\"feature\":\"HSM template (starts a conversation)\",\"consumo\":\"Meta's per-unit price\",\"tipo\":\"Its own rate\"}]",[33,1763,1765],{"id":1764},"beyond-the-bundle-the-flat-add-on-rates","Beyond the bundle: the flat add-on rates",[14,1767,1768,1769,1772,1773,1776,1777,1780],{},"So far we've talked about the three usage buckets, but there's a second kind of extra worth having on the map: the ",[18,1770,1771],{},"flat rates"," for when you go past some structural limit of your plan. They don't run through the bundle or a top-up; they're a fixed per-unit price, the same across every plan. The two most requested: an extra ",[18,1774,1775],{},"booking page"," (€10\u002Fmo) if you open another location or service with its own calendar, and an extra ",[18,1778,1779],{},"teammate"," (€5\u002Fmo) if you add someone beyond the users your plan includes—both plus applicable tax. The rest—one-off messages above your bundle, templates, and the emails and drafts the AI writes—also has its per-unit rate, no surprises.",[1782,1783],"plan-extras",{},[14,1785,1786],{},"You see all of this broken down on the dashboard and the invoice, never hidden: if one month you activate an extra booking page, that €10 line shows up and that's it. Nothing runs away unless you activated it.",[33,1788,1790],{"id":1789},"the-whole-map-on-one-screen","The whole map, on one screen",[14,1792,1793,1794,1797],{},"If you take away one idea, let it be this: ",[27,1795,1796],{"c":592},"a flat plan, with no month-end surprises",". Your monthly bundle splits across minutes, messages, and templates; you watch it draw down on the dashboard and you set the pace. For the spikes, top-ups with a spending cap. For the usage that repeats month after month, a bigger plan with a better per-unit price.",[202,1799,1800],{},[205,1801,1802,1805,1808,1811,1814],{},[208,1803,1804],{},"Totem is a flat plan with a bundle of minutes and messages included, sized to your volume.",[208,1806,1807],{},"Three usage buckets: the AI's minutes on the phone, the messages in your conversations, and WhatsApp templates. Minutes count whether the AI takes or places the call.",[208,1809,1810],{},"Top up for the one-off peak, with a spending cap so you're never caught off guard.",[208,1812,1813],{},"If you come up short three months in a row, upgrade: the included per-unit price beats topping up piecemeal.",[208,1815,1816],{},"HSM templates have their own price because Meta charges to start a conversation; replies within 24 hours are a normal message.",[14,1818,1819],{},"The best part of having everything on one platform—voice, WhatsApp, Instagram, Messenger, text, email, and CRM—is that this breakdown lives in a single dashboard. You're not chasing invoices from four providers: you see your three buckets, in real time, with the analytics right beside them.",[227,1821],{"buttonLink":229,"buttonText":1526,"description":1822,"title":1823},"We'll build the math with your real volume of calls and messages. Live in 48–72 hours, and no lock-in.","Want to know which plan and how much credit fit your business?",{"title":234,"searchDepth":235,"depth":235,"links":1825},[1826,1827,1828,1829,1830,1831,1832],{"id":1587,"depth":238,"text":1588},{"id":1626,"depth":238,"text":1627},{"id":1659,"depth":238,"text":1660},{"id":1690,"depth":238,"text":1691},{"id":1723,"depth":238,"text":1724},{"id":1764,"depth":238,"text":1765},{"id":1789,"depth":238,"text":1790},"Guide","AI agent usage: three clay tanks—minutes, messages, and WhatsApp templates—filling with teal spheres from a coral dispenser on a navy background","2026-07-01","2026-05-18","How AI receptionist pricing works: what your monthly minutes and messages cover, and when to add credits instead of upgrading your plan.",[1839,1842,1845,1848,1851,1854],{"question":1840,"answer":1841},"What uses up my monthly bundle?","Three things: the minutes the AI spends handling calls, the messages in your conversations (WhatsApp, text, and so on), and the Meta-approved WhatsApp templates. Your plan includes a bundle of minutes and messages sized to your volume, and usage draws it down.",{"question":1843,"answer":1844},"Does the time the AI spends on the phone count as minutes?","Yes. Minutes are the time the AI spends talking on the phone, and they count whether it takes the call or places it: answering a call uses minutes just like making one. That's why the plan includes a bundle sized to your volume, with top-ups and a spending cap for the spikes.",{"question":1846,"answer":1847},"When should I add a top-up and when should I upgrade?","A top-up is for a one-off spike: a campaign, a busy month. If you come up short two or three months in a row, upgrading is the better deal, because the per-unit price built into a plan beats topping up piecemeal.",{"question":1849,"answer":1850},"Can I set a spending cap?","Yes. You can set a spending limit so top-ups never run away without you knowing. When the cap is reached, the platform stops drawing extra credit and alerts you to decide whether to top up or wait for the next cycle.",{"question":1852,"answer":1853},"What is a top-up and how do I add credit?","A top-up is a credit refill—minutes or messages—that you add in a couple of clicks without changing plans. The extra credit stacks on top of your monthly bundle and you keep running without slowing down. It's the tool for a one-off spike, not for recurring usage.",{"question":1855,"answer":1856},"Do WhatsApp templates cost the same as a regular message?","No. Meta-approved HSM templates have their own rate because WhatsApp Business charges for starting a conversation, by category (utility, marketing, or authentication). A message that replies within the 24-hour window does count as a normal conversational message.","\u002Fimg\u002Fblog\u002Fminutos-mensajes-plantillas-consumo-top-ups-cover.webp",{},"\u002Fblog\u002Fai-receptionist-pricing-minutes-messages","Pricing",{"title":1576,"description":1837},"AI Receptionist Pricing: Minutes, Messages, Top-Ups","blog\u002Fai-receptionist-pricing-minutes-messages",[1865,1866,1867,1868,1869,1870],"AI receptionist pricing explained","how AI receptionist minutes work","minutes vs messages billing","AI agent usage and add-on credits","top up vs upgrade plan","WhatsApp template pricing","Totem is a flat monthly plan with a bundle of minutes and messages included. Usage splits three ways: the AI's minutes on the phone, the messages in your conversations, and Meta's WhatsApp templates. Short one month? Add a top-up and set a spending cap. Short every month? Move up a plan. Here's the whole map, no fine print.","minutos-mensajes-plantillas-consumo-top-ups","I7S0q-OB54RZlh1v9Ie0bQ2ngBVqSII5LCa0Wrd9qq4",1785021931067]