{
"icp": "consultants, coaches, B2B SaaS sales teams, agencies, and professional services already running their scheduling on Calendly",
"capabilities": {
"availability": {
"headline": "Captures the website inquiry or caller as a Calendly invitee, books the meeting live on the call, and feeds one unified conversion pipe for your website forms AND your AI Receptionist.",
"lede": "Every caller who lands on the line becomes a real Calendly invitee (on the right Event Type, on the right host's calendar, with name, email, timezone, and call-summary answers populated against the Event Type's custom questions). AND the same lead event flows through one unified pipe (with the same shape, same source attribution, and same server-side conversion path used by your website forms) so your CRM business logic and your Google / Facebook / LinkedIn Ads both stay in sync.",
"cards": [
{
"num": "A.01",
"title": "Every caller becomes a Calendly invitee, not a missed scheduling link",
"body": "The AI Receptionist captures name, email, phone, and call intent. Then AnyCRM writes the invitee onto the right Event Type, on the right host's calendar, DURING the call. No \"I'll text you my Calendly link\". The booking is already done by the time the caller hangs up."
},
{
"num": "A.02",
"title": "Books the right Event Type for the right duration",
"body": "A 15-minute intro lands on the 15-minute Event Type. A 60-minute strategy session lands on the 60-minute one. AnyCRM maps caller intent to the host's existing Event Type catalogue. Never to a duration Calendly doesn't already model, and never to an Event Type that doesn't exist on this host's Calendly page."
},
{
"num": "A.03",
"title": "Sends the lead event straight to your CRM. You decide what happens next.",
"body": "AnyCRM does not pretend to know your deal-creation rules. Every invitee-create and every reschedule sends a lead event straight to your CRM (with source: \"AI Receptionist Call\" or source: \"AI Receptionist Web\") where YOUR business logic takes over. Open the Deal, set the stage, assign the pipeline, route the workflow. We set up the receiving end inside your CRM for you during onboarding, tuned to your industry and your client configuration. AnyCRM doesn't get in the way of policy you've already encoded."
}
],
"apiSummary": "The AI Receptionist asks AnyCRM for availability against the routed-to host's Event Type and gets back open slots in the caller's timezone. No double bookings. The host's busy time is always respected. Every AnyCRM call validates the slot against Calendly's available-times response inside the booking call itself, assembles the custom-question answers against the Event Type's frozen question list, stamps the invitee record with the caller's IANA timezone, and sends the lead event straight into your CRM tagged with AI Receptionist Call or AI Receptionist Web. The same lead also feeds the AnyCRM Conversion Lift pipeline (covered in the next capability) so your Google, Facebook, and LinkedIn Ads start optimising against the call and chat leads that actually pick up the phone.",
"tools": [
"getCalendlyAvailability",
"createCalendlyContactMeeting"
],
"curl1Path": "/mcp/tools/getCalendlyAvailability",
"curl2Path": "/mcp/tools/createCalendlyContactMeeting",
"pipeIntro": "Most businesses run two completely separate conversion-tracking stacks. One for the website (forms, chatflows, page-load pixels) and a totally absent one for the phone and the AI Receptionist. So Google Ads and Facebook Ads only learn from form-fills, the bidding optimises for the wrong audience, attribution is broken, and analytics double-count or miss real conversations entirely. AnyCRM closes that gap by running BOTH surfaces through a single conversion pipe.",
"pipeStages": [
{
"stage": "1. Capture",
"body": "A lead arrives either through your website form / chatflow OR through the AI Receptionist on phone / chat. Either way, AnyCRM produces the same clean lead-event shape, tagged at source with either AI Receptionist Call, AI Receptionist Web, or your website's form identifier. One vocabulary across both surfaces."
},
{
"stage": "2. Deliver to your CRM",
"body": "AnyCRM sends the lead event straight to your CRM, into the receiving flow we wired up for you at onboarding. Your business logic decides what happens next: which Deal, which pipeline, which stage, which workflow, which team channel. You don't have to maintain two sets of rules. Web leads and AI Receptionist leads both arrive through the same door."
},
{
"stage": "3. Fire server-side conversion to your ad platforms",
"body": "The same lead event fires server-side into Google Ads, Facebook Ads, and your analytics platform, using the origin of the domain you registered with AnyCRM. Server-side means the conversion can't be blocked by ad-blockers, doesn't degrade under iOS / Safari tracking restrictions, and lands with full attribution context."
},
{
"stage": "4. Optimise, attribute, report",
"body": "Because website conversions AND AI Receptionist conversions flow through the same pipe with the same source taxonomy, your Google Ads bid strategy now optimises against real revenue (not just form-fill noise), your Facebook Ads campaigns see the high-intent traffic that picks up the phone, your analytics platform sees a single unified funnel, and attribution stops fragmenting between web and voice."
}
],
"outcomes": [
"Higher ROAS. Ad bidding optimises against actual conversations and booked Calendly events, not against the noisy subset of leads that happen to fill a form.",
"Lower ad costs. Once Google Ads and Facebook Ads learn what a real lead looks like, they stop spending against lookalikes of low-quality form-fills.",
"Enriched analytics. Every conversation surface (web form, web chat, phone call, AI Receptionist chat) feeds the same event shape into your analytics, so funnels are complete instead of half-blind.",
"Correct attribution. A caller who first saw a Google Ad, then visited the site, then phoned three days later gets attributed end-to-end. Voice traffic stops being invisible to your marketing stack.",
"One source of truth for lead policy. Your CRM's flow owns deal-creation, pipeline assignment, and stage routing. AnyCRM doesn't drift out of date because AnyCRM never tried to own that policy in the first place."
],
"whyThisIsBetter": "Most competitor AI Receptionists try to maintain rules for when a Deal is created, what pipeline it goes in, and which source tag to apply. That approach breaks the moment your business changes, and it ignores the conversion-tracking surface entirely. AnyCRM inverts the responsibility. AnyCRM stays focused on the conversation (capture, route, book, reschedule, cancel) and delivers a clean lead event to the two destinations that matter: your CRM (for business logic) and your ad platforms server-side (for conversion optimisation, attribution, and ROAS). This is a custom service baked into the AI Receptionist package. We configure the lead-receiving flow inside your CRM AND the server-side conversion tracking at onboarding, matched to your specific industry, ad mix, and analytics setup.",
"honestAside": "We'll be candid: as far as we can tell, none of our competitors have thought of this yet. They sell AI Receptionists as a phone-answering product. AnyCRM treats the AI Receptionist as one of two equally weighted entries into a unified lead-event pipe, and that's where the real compounding value sits."
},
"adsConversionLift": {
"headline": "Turns every call and chat into a real conversion event your Google, Facebook, and LinkedIn Ads can actually optimise against. So Cost per Lead drops, ROAS goes up, and CAC stops being a guess.",
"lede": "If you run paid Ads on Google, Facebook, or LinkedIn, here is the uncomfortable truth: those platforms only get smarter when they see real conversions. Today, a website form-fill counts. A real phone call from a high-intent buyer who picked up the phone at 7pm does NOT count. So Google bids harder on the audience that fills forms (often the cheaper, lower-intent one) and ignores the audience that actually calls. Cost per Lead looks fine. CAC quietly creeps up. ROAS looks misleading. AnyCRM fixes this. Every call and chat the AI Receptionist handles is sent as a real conversion event to Google Ads, Facebook Ads, AND LinkedIn Ads. The bidding algorithm finally sees what's actually working.",
"cards": [
{
"num": "1b.01",
"title": "Every phone call and every chat becomes a tracked conversion. Not just website form-fills.",
"body": "Today, Google Ads and Facebook Ads probably think your only conversions are website form-fills. That's why your Cost per Lead looks low but your sales team complains the leads are weak. The high-intent traffic is calling you instead of filling a form, and the Ad platforms have no idea. AnyCRM sends every call and every chat the AI Receptionist handles into your Ad platforms as a real conversion event. Suddenly Google, Facebook, and LinkedIn can see the FULL picture of who is converting from your Ads."
},
{
"num": "1b.02",
"title": "Lower Cost per Lead. Better ROAS. Smaller CAC.",
"body": "Once your Ad platforms can see the phone calls and chats as real conversions, they re-train on a better signal. Bidding shifts toward audiences that actually pick up the phone, not just the audience that loves filling out forms. In practice this means: Cost per Lead drops because you stop overpaying for low-intent form-fills; Return on Ad Spend goes up because the Ads now find people closer to ready-to-buy; and Customer Acquisition Cost shrinks because more of your Ad budget reaches buyers who will actually convert into customers."
},
{
"num": "1b.03",
"title": "The same pipe carries your website forms too. One source of truth across Ads, CRM, and Analytics.",
"body": "AnyCRM doesn't just track AI Receptionist conversions. It also runs your existing website forms and chatflows through the same pipeline. So a lead from a Google Ad that fills a form on your website AND a lead from a Facebook Ad that called the AI Receptionist three days later both end up tagged, attributed, and counted in exactly the same way. Your Ads platform stops double-counting, your analytics stop fragmenting, and your CRM stops being half-blind to where your leads actually came from."
}
],
"apiSummary": "Every invitee-create and reschedule fires through AnyCRM's Conversion Lift pipeline. The lead event lands inside your CRM for business logic, AND fires a real conversion event server-side into Google Ads, Facebook Ads, and LinkedIn Ads using the verified origin of your registered domain. Server-side means the conversion can't be blocked by ad-blockers, doesn't degrade on iOS or Safari, and arrives with full attribution context so the Ad platforms' bidding algorithms can re-train on it. Your existing website forms run through the same pipeline, so Web and Voice conversions feed the SAME training signal.",
"businessImpact": [
"Cost per Lead drops. Because Google, Facebook, and LinkedIn stop wasting your Ad budget on lookalikes of low-intent form-fillers, and start finding the audience that picks up the phone.",
"Return on Ad Spend (ROAS) goes up. Because the Ads now optimise toward conversations that actually close, not toward whichever cheap audience generates the most form submissions.",
"Customer Acquisition Cost (CAC) shrinks. Because a higher share of every Ad dollar reaches buyers ready to talk to a human (or in this case, your AI Receptionist).",
"Analytics get a complete funnel. Web and voice leads sit side by side, with the same source taxonomy. You stop seeing \"50% of revenue: unknown source.\"",
"Attribution stops fragmenting. A buyer who first clicked a Google Ad, then called the business three days later, finally shows up correctly attributed. Today, that buyer is invisible to your Ads stack.",
"You finally know if Ads are working. Most businesses cannot honestly tell you whether their Google or Facebook spend is profitable. With AnyCRM's Conversion Lift, you can."
],
"plainEnglishExample": "Imagine you spend $5,000/month on Google Ads. Today, you see 80 form-fills and assume that's the full picture. With AnyCRM running, you'll also see (say) 60 phone calls and 45 web chats the AI Receptionist booked into Calendly, all flowing into Google Ads as real conversions. Suddenly Google sees 185 conversions a month instead of 80. It re-trains on that bigger, better signal. Within weeks, the bidding finds you more of the right kind of buyer. Same $5,000 spend, more real conversations, lower Cost per Lead, higher revenue. That is what \"AI Receptionist with AnyCRM\" actually means for the bottom line. Not just \"it answers the phone.\"",
"tools": [
"createOrUpdatesCalendlyInvitee",
"createCalendlyContactMeeting"
]
},
"lifecycle": {
"headline": "Manages the full Calendly event lifecycle inside Calendly for anyone calling or chatting.",
"lede": "Every \"push the discovery call to Thursday\" or \"actually, cancel that\" lands with the AI Receptionist instead of in your email inbox. AnyCRM reschedules move the existing Calendly event to a new slot. Cancellations write the caller's reason onto the Calendly event so the host sees WHY the slot opened up. Instead of leaving a bare \"cancelled by invitee\" with no context.",
"cards": [
{
"num": "B.01",
"title": "Finds the event by email in a single step without needing a Calendly event UUID",
"body": "Customers DO NOT quote Calendly event UUIDs over the phone. We've tested with hundreds of callers and each time they were asked 'Can you tell me the event id from your email?', the response was the same: 'Why can't you find it yourself?'. AnyCRM gives the AI Receptionist an easy way to find the soonest upcoming Calendly event the caller is an invitee on. And the AnyCRM response forces the AI Receptionist to be human. It reads back the Event Type, the host, the date, and the time before changing anything."
},
{
"num": "B.02",
"title": "Reschedules in place and keeps the invitee answers clean",
"body": "Rescheduling moves the existing Calendly event to a new slot in a single confirmation, preserving the event UUID, the host, the Event Type, and the invitee's answers to the Event Type's custom questions. No cancel-then-rebook round-trip. Failed reschedules leave the original Calendly event untouched."
},
{
"num": "B.03",
"title": "Cancels with the reason recorded on the Calendly event",
"body": "When a caller cancels, AnyCRM sends the cancellation to Calendly with the caller's reason attached. The reason lands on the Calendly event, so the host opens the cancelled event and sees exactly why it fell through. Calendly fires its own cancellation email to the invitee. The AI Receptionist confirms it back on the call."
}
],
"apiSummary": "AnyCRM's search, reschedule, and cancel all accept just an email. The soonest upcoming Calendly event for that invitee email is resolved inside AnyCRM. No event UUIDs at the AI Receptionist layer.",
"tools": [
"searchCalendlyMeetings",
"updateCalendlyMeeting",
"cancelCalendlyMeeting"
],
"curl1Path": "/mcp/tools/searchCalendlyMeetings",
"curl2Path": "/mcp/tools/updateCalendlyMeeting",
"curl3Path": "/mcp/tools/cancelCalendlyMeeting"
},
"routing": {
"headline": "Routes every caller to the right Calendly host on the right Event Type. And honours the host who already owns the lead.",
"lede": "Calendly accounts are organisations of users, each with their own Event Types, durations, working hours, and timezones. At setup AnyCRM imports your Calendly organization members into its database and enriches each host with lane, expertise, languages, and a default Event Type per call intent. The AI Receptionist then routes each caller to the host who actually handles that lane and books on that host's Event Type.",
"cards": [
{
"num": "C.01",
"title": "Routes by host by name or by lane",
"body": "\"I want to talk to Sarah about pricing\" routes to Sarah's pricing-call Event Type. \"Whoever's free for a discovery call\" checks every team member whose lane is Discovery and presents the soonest slot across all of them. And the existing host on a returning invitee is always preserved."
},
{
"num": "C.02",
"title": "Per-host Event Types and durations",
"body": "Each Calendly host exposes their own Event Types: durations, custom questions, working hours. The AI Receptionist never books a 30-minute slot on a host who only offers 15s, and never quotes an Event Type that doesn't exist on this host's Calendly page."
},
{
"num": "C.03",
"title": "Falls back to the next available team member",
"body": "Host of choice has no openings in the caller's window? The AI Receptionist offers the next available team member on the same lane who runs the same Event Type kind, and confirms the swap before booking. Calendly's own round-robin Event Types are honoured where you already use them. We don't fight the host distribution Calendly is already running."
}
],
"apiSummary": "Team details live in AnyCRM's database, pulled once from Calendly at setup, enriched with lane, expertise, languages, and the default Event Type URI per call intent (valuable context for the AI Receptionist that Calendly's user object doesn't carry). Each host's Calendly user URI is kept on the record as the bridge for booking writes. At runtime, one read of the team roster matches caller → lane → host → Event Type. AnyCRM does NOT cache your deal pipelines, your stages, or your downstream lifecycle workflows. That policy stays inside your CRM, where it belongs.",
"tools": [
"listCalendlyOrganizationMembers",
"getCalendlyUserProfile"
],
"curl1Path": "/mcp/tools/listCalendlyOrganizationMembers",
"curl2Path": "/mcp/tools/getCalendlyUserProfile"
}
},
"setup": {
"headline": "Setup in 3 steps. Battle-tested on real Calendly accounts.",
"lede": "You connect Calendly once. AnyCRM imports your organization members, your Event Types, and your durations. AnyCRM also wires up the receiving end inside your CRM so lead events from the AI Receptionist land where your business logic can act on them. Then the AI Receptionist starts booking real Calendly events the same afternoon. No middleware. No prompt-engineering by you.",
"steps": [
{
"num": "S.01",
"title": "Connect Calendly (OAuth or Personal Access Token, 60 seconds)",
"body": "Authorize AnyCRM on your Calendly account via OAuth, or paste a Personal Access Token from Integrations → API & Webhooks. AnyCRM scopes to the least amount of access needed for the booking lifecycle. Nothing for billing, nothing for analytics, nothing for routing forms or workflows. You can revoke the OAuth grant at any time from your Calendly connected applications page (or rotate the Personal Access Token in Integrations → API & Webhooks)."
},
{
"num": "S.02",
"title": "Import the team. Lock in your Event Types. Wire up your CRM's lead-receiving flow.",
"body": "AnyCRM imports every active Calendly organization member as a bookable team member with lane, expertise, languages, timezone, and meeting-type duration. AnyCRM also freezes the Event Types (with their custom-question lists) so the AI Receptionist can only book Event Types you actually run, and locks inbound-call source attribution (always AI Receptionist Call or AI Receptionist Web) so reporting stays consistent. During onboarding we set up the receiving flow inside your CRM so the lead events from the AI Receptionist land where your business logic can act on them. AnyCRM does NOT replicate your deal pipelines, stages, or downstream workflows. Your CRM decides what happens after a lead is captured. AnyCRM just delivers a clean event."
},
{
"num": "S.03",
"title": "Drop the AI Receptionist on your phone line and your site",
"body": "Forward your business number to the AI Receptionist's number and paste the chat widget into your site. The same AI Receptionist (same team roster, same Calendly account, same lead-event pipe into your CRM and your ad platforms) answers both voice and web. Live the same afternoon."
}
],
"nativeAlternative": {
"headline": "Why not just use Calendly's scheduling link on its own?",
"body": "Calendly's scheduling link is excellent at one thing: a customer who already knows what they want, on a device, clicking the link in your email signature. It stops where the real work starts. It doesn't pick up the phone. A new caller at 9pm gets a missed call, not a Calendly invitee record. A form sits in the submissions queue until someone reads it. Calendly Routing (on Teams and Enterprise) qualifies and routes from web forms, but doesn't answer a voice call. The AI Receptionist is the layer BEFORE all of that. It picks up the call, asks the right qualifying questions, books the meeting as a native Calendly invitee on the right host's Event Type, writes a clean lead (with the source set to AI Receptionist Call or AI Receptionist Web and a call summary as the first note), AND sends the same lead event straight into your CRM's downstream business logic plus your ad platforms server-side. So your CRM workflows, your analytics, and your Google / Facebook Ads bidding all start optimising on a real conversation, not a name and a missed call."
},
"enrichmentSummary": "Every tool the AI Receptionist calls is an opinionated wrapper inside AnyCRM. AnyCRM does the messy work for you. Event Type URI resolution, organization-member lookup, timezone math, custom-question assembly, slot re-validation, error handling, lead-event delivery into your CRM, and server-side conversion tracking into your ad platforms. All of it happens before the LLM ever sees a response. So the AI Receptionist reasons over clean, AI-aligned payloads instead of raw Calendly internals.",
"enrichmentExamples": [
{
"title": "Booking the Calendly event",
"raw": "Writing an invitee straight into Calendly looks simple. But the create-invitee flow has tight contracts. The start time has to be a slot Calendly's available-times response just returned (an arbitrary ISO timestamp gets rejected). The Event Type URI has to belong to the right host. The invitee's answers have to be an array of question-and-answer objects keyed by the Event Type's exact custom-question text. Paraphrase the question even slightly and the answer silently drops off the invitee record. The host opens the booking and sees blanks where qualification answers should be.",
"mcp": "createCalendlyContactMeeting accepts name, email, phone, note, scheduled_datetime (a naive date and time, no offset needed), invitee_timezone, and the matched host. AnyCRM resolves the right Event Type URI from the lane, re-validates the slot against Calendly's available-times response inside the booking call itself, assembles the custom-question answers against the Event Type's frozen question list, converts the naive datetime to UTC against the invitee timezone, sends the lead event straight into your CRM (with source AI Receptionist Call or AI Receptionist Web), AND fires a server-side conversion event into your ad platforms using the origin of your registered domain. All in one AnyCRM call."
},
{
"title": "Finding an existing event to change",
"raw": "Calendly's list-events endpoint requires an organization or user URI plus filters: invitee email, status (must be active to exclude already-cancelled events), a start-time window, and a sort order. The response paginates. To get the invitee detail (with answers, timezone, reschedule URL) you then have to follow up with a per-event invitee fetch. Forget the active-status filter and the search returns long-cancelled events the caller probably forgot about. Forget the soonest-first sort and \"the soonest one\" is wherever pagination put it.",
"mcp": "searchCalendlyMeetings takes just an email. AnyCRM queries Calendly with the right filters, fans out the per-event invitee fetch for the top match, and returns a flat object with Event Type name, host name, start time (local + UTC), reschedule URL, and cancel URL. Already sorted soonest-first."
},
{
"title": "Cancelling with a reason",
"raw": "Calendly's cancellation endpoint accepts a reason string and that's it. But you have to know the event UUID, you have to know the invitee URI on that event for the cancellation to attribute correctly, and Calendly's own cancel URL (the one in reminder emails) is a separate user-facing flow that requires the invitee to click through. The caller on the phone has neither the UUID nor the URL. And a cancellation sent without a reason leaves the host with a bare \"cancelled by invitee\" and no context.",
"mcp": "cancelCalendlyMeeting takes email and reason. AnyCRM resolves the soonest upcoming event for that invitee email, calls the cancellation endpoint with the reason attached, and returns the cancelled event UUID and the recorded reason. All in one AnyCRM call. Calendly fires its own cancellation email to the invitee. The AI Receptionist reads the confirmation back on the call."
}
],
"alignmentSummary": "Every AnyCRM tool for Calendly follows the same AI-alignment contract, so the AI Receptionist never has to think about transport:",
"alignment": [
"Naive datetimes in, Calendly-native shape out. The AI Receptionist passes 2026-05-15T11:00:00 and a timezone string. AnyCRM converts to UTC for the booking, stamps the invitee record with the caller's IANA timezone, and validates against Calendly's available-times response.",
"Email is the identity. Cancel and reschedule never need an event UUID at the AI Receptionist layer. Email and soonest-upcoming resolves inside AnyCRM.",
"Event Type comes from setup, not the LLM. The AI Receptionist can't invent an Event Type or accidentally book a duration that doesn't exist on this host. It inherits the Event Type URI you configured at setup.",
"Custom questions are a frozen list. AnyCRM assembles the answers array against the Event Type's actual custom-question text, so answers always land on the invitee record instead of silently dropping.",
"Existing host assignments are sacred. If a returning invitee already has an active Calendly event with a host, AnyCRM preserves that host on the reschedule.",
"Cancellation always carries a reason. The host opens the cancelled event and sees exactly why it fell through, not a bare \"cancelled by invitee.\"",
"Every lead event leaves AnyCRM in two places at once. Your CRM gets the lead event so your business logic can run. Your ad platforms get the server-side conversion event so bidding optimises against real conversations. Both happen on the same AnyCRM call. No race conditions, no missing events.",
"Flat, deterministic shapes. Every AnyCRM response has the same top-level keys across every tool, so the AI Receptionist's prompt never grows with edge-case branching.",
"Errors are messages, not codes. A 4xx from Calendly (slot taken, Event Type inactive, invitee already booked) becomes a one-sentence reason the AI Receptionist can repeat to the caller without translation.",
"Idempotent reschedules. If a reschedule fails mid-flight, the original Calendly event is preserved. The customer never ends up with nothing."
],
"industryLine": "Currently running for consultants, coaches, agencies, B2B SaaS sales teams, recruiters, and solo operators. Anyone whose scheduling is in Calendly but whose phone keeps ringing after the link has already been sent.",
"teamsSetup": {
"headline": "Multi-host setup. Team roster, lanes & system-prompt assembly",
"body": "If you run more than one host on Calendly, AnyCRM imports the organization once, you link each host to the lanes they actually cover (Discovery / Demo / Strategy / Renewal), and AnyCRM bakes the result into the AI Receptionist's system prompt at setup time. Not at runtime. The AI Receptionist doesn't query your organization on every call. It already knows who handles what.",
"steps": [
"Team roster import. AnyCRM imports your Calendly organization members once and writes each one into its database keyed by crm_user_id (with name, role, lane, timezone, Calendly user URI, scheduling URL).",
"Per-host Event Types. For each host AnyCRM resolves the active Event Types (name, duration, slug, URI, custom-question list). One call per person, cached.",
"Lane visibility. Each lane is flagged Public, Private or Ignored. The AI Receptionist only routes to and books on Public lanes. You toggle this in the AnyCRM dashboard without re-deploying.",
"Lead-event receiving flow inside your CRM. During onboarding we wire up the flow inside your CRM that receives lead events from AnyCRM. That's where your deal-creation policy lives. AnyCRM doesn't try to own it.",
"System-prompt assembly. The cached team roster, lane, and Event Type JSON is prepended to the AI Receptionist's system prompt before the humaniser splits (personality, etiquettes, tone, speech style). So the AI Receptionist reads the team before it reads its own instructions.",
"Runtime stays minimal. On a live call the AI Receptionist makes at most one availability call and one booking call. Never a team roster lookup. Updates to hosts, lanes, or Event Types re-run the cache. The AI Receptionist picks them up on its next deploy."
],
"note": "The end result: the AI Receptionist can match \"I'd like a 30-minute discovery call with someone on the sales team\" → the Discovery lane → that host's 30-minute Event Type → that host's Calendly availability → a booked Calendly invitee on the right host's calendar → a lead event delivered straight into your CRM → a server-side conversion event in your ad platforms. Without a single team roster query during the call."
}
},
"privacy": {
"headline": "Your Calendly data passes through AnyCRM. It doesn't stick.",
"lede": "AnyCRM processes your Calendly data to answer the call. Then forgets it. The only thing AnyCRM persists is a conversation history ID so the AI Receptionist can recognise a returning caller. Scheduled events, invitee answers, Event Types, organization members. All of it stays in Calendly, owned by your Calendly account.",
"cards": [
{
"kind": "stored",
"label": "What AnyCRM stores",
"body": "Conversation history IDs only. So the AI Receptionist can pick up where it left off if a caller hangs up and rings back. No call audio, no transcripts of invitee records, no caller PII."
},
{
"kind": "not-stored",
"label": "What AnyCRM doesn't",
"body": "Caller names, emails, phone numbers, Calendly event UUIDs, your Event Types beyond their identifiers, your scheduled-event data, your custom-question answers. None of it. AnyCRM reads what it needs, hands it to the LLM, fires the events, and discards the payload."
},
{
"kind": "data-lives",
"label": "Where data lives",
"body": "In your Calendly account and in whatever systems your CRM's flow forwards lead events to. Scheduled events, invitee answers, cancellation reasons all live in Calendly. Source-attributed (always AI Receptionist Call or AI Receptionist Web), attributed to AnyCRM in the audit log, revocable. AnyCRM does not build a shadow scheduler alongside yours."
},
{
"kind": "revoke",
"label": "Revocation",
"body": "Revoke the AnyCRM OAuth grant in your Calendly connected applications page (or rotate the Personal Access Token in Integrations → API & Webhooks) and the AI Receptionist loses access immediately. There is no \"export your data\" step because there is no data to export. It was never AnyCRM's to hold."
}
],
"scopesSummary": "Calendly uses OAuth scopes (or a Personal Access Token with the user's full permissions). Either way, AnyCRM only touches the smallest set of endpoints required for the booking lifecycle. Nothing for billing, nothing for routing-form analytics, nothing for workflows.",
"scopes": [
"Users + organization memberships (read). Read your organization roster at setup so the AI Receptionist knows who exists and which host owns which lane.",
"Event Types (read). Read each host's active Event Types (name, duration, slug, URI, custom questions) at setup and on re-sync.",
"Availability (read). Read availability windows for the routed-to host's Event Type at call time. The booking work.",
"Scheduled events + invitees (read + write). Read existing events (for reschedule and cancel), write new invitee records on the right host's Event Type, and post cancellations with a reason.",
"Not requested: billing / subscription data, routing forms, workflows, payments, your other integrations, deal-creation policy (that's your CRM's own flow's job)."
],
"surfaceNote": "Same OAuth grant any Calendly app uses. Just a smaller surface. AnyCRM holds the access and refresh tokens (every write is signed by AnyCRM's connected-app credentials, so each invitee and cancellation is attributable to AnyCRM in Calendly's audit log). The LLM never sees the token, and every tool call is logged with the operation name, never the raw payload."
},
"failureModes": [
{
"title": "Pushing the caller back to a Calendly link instead of booking on the call",
"raw": "The advertised \"Calendly integration\" on most AI Receptionists is actually a Zapier-style \"text the Calendly link to the caller\" action. My AI Front Desk's documented Calendly flow offers slots verbally, then texts the unique Calendly link mid-call so the caller can finalize details themselves through the public scheduling page. The caller still has to click through, fill in the page, and confirm. Drop-off is silent. Smith.ai's human receptionist tier historically books on the host's behalf through Calendly's public scheduling page, or sends the caller a scheduling link to fill in themselves afterwards (their newer AI Receptionist tier uses Calendly's Scheduling API directly, but the link-first pattern still shows up across their human flows). Goodcall markets a Calendly integration that books via Calendly's API on a per-agent setup, but the multi-Event-Type-per-host case is not exposed in published materials.",
"mcp": "AnyCRM does NOT text a link. AnyCRM books the Calendly invitee live on the call: resolves the host's Event Type URI from the lane, re-validates the slot against Calendly's available-times response, assembles the custom-question answers against the frozen question list, posts the invitee, and reads the confirmation back to the caller before they hang up. We do four checks where the Zapier-style \"send link\" action does one. That's why a meeting booked through AnyCRM is never an SMS the caller forgot to click on.",
"competitorsAffected": ["My AI Front Desk", "Smith.ai (human tier)", "Goodcall"]
},
{
"title": "Booking a slot that's already taken",
"raw": "Calendly will reject a start time that wasn't returned by the most recent available-times response. A naive AI Receptionist that holds availability in memory between turns of the conversation can hand the caller a slot another invitee just took. My AI Front Desk's Zapier-style action posts whatever it has at Calendly. The 422 comes back as a generic error, the AI Receptionist hears \"unavailable,\" and meanwhile the caller already heard \"you're booked.\" Goodcall documents its Calendly integration but does not expose a published guarantee that the slot is re-validated inside the booking call itself. Smith.ai's AI tier handles this through Calendly's Scheduling API, but the human tier booking through the public page has no way to atomically re-check the slot at commit.",
"mcp": "AnyCRM re-validates the slot against Calendly's available-times response inside the booking call itself. Never against a cached snapshot. An already-taken slot returns an error before the AI Receptionist can confirm. So the AI Receptionist says \"that one just went, can I offer 11:30?\" instead of confirming a collision. Three steps where Smith.ai/My AI Front Desk/Goodcall do one.",
"competitorsAffected": ["My AI Front Desk", "Goodcall", "Smith.ai (human tier)"]
},
{
"title": "Inventing Event Types and durations that don't exist on this host",
"raw": "Calendly's Event Types are not free text. Each one is a discrete record with a URI, a duration, a slug, and a fixed custom-question list. My AI Front Desk's Zapier-style action takes whatever the AI generates and posts it. There is no \"read this host's real Event Types first\" step in a Zapier path. So the AI offers a \"45-minute strategy session\" on a host who only runs 30s and 60s, and the booking 404s. Goodcall's setup links a single Event Type per agent in its published materials. A host running a 15-min intro, a 30-min discovery, AND a 60-min strategy session ends up either picking one as the default and ignoring the others, or running multiple agents. Neither maps to the multi-Event-Type-per-host reality of most Calendly accounts. Smith.ai's human receptionists work from a playbook of which Event Type to book. Fine on a Tuesday morning, less reliable on a Friday at 8pm with a relief receptionist.",
"mcp": "AnyCRM reads each host's real Event Types at setup (name, duration, URI, custom-question list) and bakes them into the AI Receptionist's system prompt as a frozen table. So when the AI Receptionist captures a lead, it CAN ONLY offer Event Types that actually exist on this host's Calendly page. This is one extra setup call per host that Smith.ai/My AI Front Desk/Goodcall don't make. And it's the difference between writes that always succeed and writes that 404.",
"competitorsAffected": ["My AI Front Desk", "Goodcall"]
},
{
"title": "Custom-question answers silently dropping off the invitee record",
"raw": "Calendly's create-invitee payload accepts a questions-and-answers array. But each entry's question string has to match the Event Type's custom-question text exactly. My AI Front Desk's Zapier surface has no way to assemble the answers array against the Event Type's exact text. Paraphrased answers either silently drop off the invitee record or land under the wrong question. Goodcall's public integration surface does not expose structured custom-question assembly. Qualification captured on the call typically lands as a free-text note rather than as structured answers on the Calendly invitee record. Smith.ai's human receptionists summarise qualification in a follow-up note rather than posting it onto the invitee's question fields. So the host opens the booking and sees blanks where the qualification answers should be.",
"mcp": "AnyCRM assembles the questions-and-answers array against the Event Type's frozen question list (cached at setup). So the question strings always match. The AI Receptionist can paraphrase in the conversation. AnyCRM writes the canonical question text to Calendly. Two extra setup steps where Smith.ai/My AI Front Desk/Goodcall do zero. And it's the difference between qualification that lands on the invitee record and qualification that the host has to dig for in a separate note.",
"competitorsAffected": ["My AI Front Desk", "Goodcall", "Smith.ai"]
},
{
"title": "Timezone drift on cross-region bookings",
"raw": "Calendly's invitee timezone is a discrete field on the booking payload, separate from the start time (which is UTC). My AI Front Desk's Zapier-style action does not expose explicit IANA timezone stamping on the invitee record. The booking can end up stamped with the host's timezone, so Calendly's reminder email renders in the host's TZ. The caller in London sees a reminder for 3pm Eastern, panics, and emails to ask if the meeting moved. Goodcall's integration handles standard timezone conversion but does not expose per-call IANA stamping on the invitee record in published materials. Smith.ai's human receptionists rely on what the caller says on the line, with no structural enforcement that the invitee record's timezone field is set correctly.",
"mcp": "AnyCRM passes the caller's IANA timezone (Europe/London) alongside the naive datetime. AnyCRM converts to UTC for the start time AND stamps the invitee timezone field with the caller's TZ. Reminder emails render in the caller's local time. The AI Receptionist reads the confirmation back in the caller's local time too. Two checks where Smith.ai/My AI Front Desk/Goodcall do one.",
"competitorsAffected": ["My AI Front Desk", "Goodcall", "Smith.ai (human tier)"]
},
{
"title": "Cancelling without a reason on the Calendly event",
"raw": "Calendly's cancellation endpoint accepts a reason string. My AI Front Desk's Zapier-style cancel action does not expose populating the cancellation reason in published materials. The host opens the cancelled event and sees a bare \"cancelled by invitee.\" Goodcall's reschedule and cancel surfaces are not part of the advertised feature set in the same way booking is. The lifecycle case typically falls back to the customer clicking the cancel URL in their Calendly reminder email, so no reason gets attached. Smith.ai's receptionists ask the caller why, but on the human tier the cancellation lands as a follow-up note rather than as a reason on the Calendly event itself.",
"mcp": "AnyCRM's cancellation is multi-step: find the soonest upcoming event, capture the caller's reason on the call, send the cancellation to Calendly with the reason attached, AND confirm the cancelled event UUID and recorded reason in the response. The reason lands on the Calendly event. The host opens it and sees exactly why it fell through. Three operations where Smith.ai/My AI Front Desk/Goodcall do one (and usually the wrong one).",
"competitorsAffected": ["My AI Front Desk", "Goodcall", "Smith.ai (human tier)"]
},
{
"title": "Encoding your deal-creation policy in the prompt or in middleware",
"raw": "My AI Front Desk ships a Zapier-style \"Create Deal\" / CRM-log action that fires on every inbound call. There is no \"only create the Deal if the caller is actually ready to buy\" logic. The action is single-step. So every call becomes a stage-1 Deal in the default pipeline, clogging your forecast with unqualified records. Worse, the moment you change your pipeline structure or add a new stage, you have to go back into Zapier and rebuild the zap. Goodcall's CRM-side actions apply whatever default behaviour the underlying integration shipped with. Change your business, and the connector keeps doing what it did six months ago. Smith.ai's AI tier and human receptionists work from playbooks that drift out of date as your real CRM policy evolves.",
"mcp": "AnyCRM does not encode your deal policy at all. AnyCRM sends a clean lead event straight to your CRM, into the receiving flow we wire up for you at onboarding. YOUR flow decides what happens: new pipeline? Update the flow. New stage? Update the flow. New source-tag scheme? Update the flow. AnyCRM's behaviour stays consistent because AnyCRM's job stops at the conversation. Smith.ai/My AI Front Desk/Goodcall can't separate these concerns because their architecture forces business policy into either Zapier middleware or a hardcoded action.",
"competitorsAffected": ["My AI Front Desk", "Goodcall", "Smith.ai (AI tier)"]
},
{
"title": "Web leads and AI Receptionist leads run on two separate conversion-tracking stacks",
"raw": "Smith.ai, My AI Front Desk, and Goodcall all treat phone and chat conversions as separate from web form / chatflow conversions. None of them fire a real conversion event into Google Ads, Facebook Ads, or LinkedIn Ads when the AI Receptionist closes a Calendly booking. So your Ad platforms only see the website form-fills, the bidding optimises for that (lower-intent) audience, your Cost per Lead looks deceptively low, ROAS reporting becomes a fiction, and the high-intent traffic that picks up the phone stays invisible to your Ad stack. Calendly's own integration with Google Analytics and Meta Pixel (on Standard and above) tracks the booking page, not the conversation that led to it. So even on the web side, the attribution stops at the page-load. Worse, when these competitors DO fire any tracking, it's client-side. Blocked by ad-blockers and degraded under iOS / Safari tracking restrictions.",
"mcp": "AnyCRM runs your website conversions AND your AI Receptionist conversions through the same Conversion Lift pipeline. Same event shape, same source taxonomy, same delivery to your CRM, AND the same server-side conversion event into Google Ads, Facebook Ads, and LinkedIn Ads. Using the verified origin of your registered domain. Server-side means it can't be blocked client-side and doesn't degrade on iOS or Safari. The result is what Smith.ai/My AI Front Desk/Goodcall structurally can't deliver: lower Cost per Lead, higher ROAS, smaller CAC, complete analytics funnels, and attribution that doesn't fragment between web and voice.",
"competitorsAffected": ["Smith.ai", "My AI Front Desk", "Goodcall"]
}
],
"failureModesMeta": {
"headline": "How most AI Receptionists built on Smith.ai, My AI Front Desk, or Goodcall fail for consultants, agencies, B2B sales teams, and professional services that use Calendly. And why AnyCRM can't.",
"lede": "Most AI Receptionists fail on Calendly in the same handful of ways. SMS-the-link instead of book-on-the-call, slots taken between availability check and booking, invented Event Types, custom-question answers silently dropping off the invitee record, timezone drift on cross-region bookings, cancellations with no reason, hardcoded deal-creation rules that drift away from your real CRM policy, and conversion data that never reaches your ad platforms server-side. AnyCRM can't fail in any of these ways, because each failure was solved one layer down inside AnyCRM. And because AnyCRM delegates deal-creation policy to your CRM's own flow rather than trying to encode it, AND runs web and AI Receptionist conversions through a single unified conversion pipe instead of two disconnected stacks.",
"closer": "The AI Receptionist is honest because AnyCRM doesn't let it lie. And AnyCRM is sophisticated because it doesn't pretend to own policy that belongs inside your CRM, while quietly fixing the conversion-tracking gap nobody else has thought to close."
},
"comparisonTable": {
"headline": "AnyCRM vs Smith.ai, My AI Front Desk, Goodcall on Calendly",
"columns": [
{ "key": "anycrm", "label": "AnyCRM" },
{ "key": "smithai", "label": "Smith.ai" },
{ "key": "myaifrontdesk", "label": "My AI Front Desk" },
{ "key": "goodcall", "label": "Goodcall" }
],
"rows": [
{
"capability": "Live Calendly invitee booked DURING the call (not SMS the link)",
"anycrm": "Yes. Native Calendly invitee on the right host's Event Type, confirmed before the caller hangs up.",
"smithai": "Partial. AI tier books via Calendly's API; human tier often books through the public page or texts the link.",
"myaifrontdesk": "Partial. Documented Calendly flow texts the unique Calendly link mid-call for the caller to finalize.",
"goodcall": "Partial. Books via Calendly's API on a per-agent setup; multi-Event-Type-per-host not exposed in published materials."
},
{
"capability": "Slot re-validation inside the booking call (no race-condition collisions)",
"anycrm": "Yes. Always. Re-checked against Calendly's available-times response at commit.",
"smithai": "Partial on AI tier; not exposed on human tier.",
"myaifrontdesk": "Not exposed in published materials.",
"goodcall": "No published guarantee."
},
{
"capability": "Preserves the existing host on returning invitees",
"anycrm": "Yes. Existing host is sacred on reschedule.",
"smithai": "Implicit, not guaranteed.",
"myaifrontdesk": "Not exposed in published materials.",
"goodcall": "Depends on the underlying agent configuration."
},
{
"capability": "Routes by lane (Discovery / Demo / Strategy / Renewal)",
"anycrm": "Yes. Lane is part of AnyCRM's team roster.",
"smithai": "Manual; depends on the receptionist or playbook.",
"myaifrontdesk": "Lane routing not exposed in published Calendly materials.",
"goodcall": "Single-Event-Type-per-agent setup doesn't model lanes."
},
{
"capability": "Event Types and custom-question lists frozen from your real Calendly setup",
"anycrm": "Yes. Read at setup, baked into the prompt as a frozen table.",
"smithai": "Not API-enforced.",
"myaifrontdesk": "Not exposed in published materials.",
"goodcall": "Per-agent default, not per-host Event Type catalogue."
},
{
"capability": "Custom-question answers land on the invitee record (not in a separate note)",
"anycrm": "Yes. Answers assembled against the Event Type's exact question text.",
"smithai": "No. Qualification typically lands as a follow-up note.",
"myaifrontdesk": "Not exposed in published materials.",
"goodcall": "Not exposed in published materials."
},
{
"capability": "Invitee timezone stamped with the caller's IANA TZ (reminder emails in caller's local time)",
"anycrm": "Yes. Always.",
"smithai": "Manual / depends on receptionist.",
"myaifrontdesk": "Not exposed in published materials.",
"goodcall": "Not exposed in published materials."
},
{
"capability": "Cancellation carries the caller's reason on the Calendly event",
"anycrm": "Yes. Reason captured on the call, posted to the cancellation endpoint.",
"smithai": "Reason captured, but typically lands as a note rather than on the event.",
"myaifrontdesk": "Not exposed in published materials.",
"goodcall": "Reschedule / cancel not part of the advertised feature set."
},
{
"capability": "Reschedule in place (no cancel-then-rebook, preserves answers)",
"anycrm": "Yes.",
"smithai": "Manual.",
"myaifrontdesk": "Not exposed in published materials.",
"goodcall": "Falls back to caller clicking the reschedule URL."
},
{
"capability": "Deal-creation policy delegated to YOUR CRM's own flow",
"anycrm": "Yes. Lead event delivered straight into your CRM, into the receiving flow we wire up at onboarding.",
"smithai": "No. Policy lives in Zapier or in the receptionist's training.",
"myaifrontdesk": "No. Zapier-style CRM-log action.",
"goodcall": "No. Connector-default behaviour."
},
{
"capability": "Unified conversion pipe: web forms AND AI Receptionist → CRM + ad platforms server-side",
"anycrm": "Yes. Same shape, same source taxonomy, same server-side delivery to your CRM and your ad platforms.",
"smithai": "No. Web and voice run on separate stacks.",
"myaifrontdesk": "No. Web and voice run on separate stacks.",
"goodcall": "No. Web and voice run on separate stacks."
},
{
"capability": "Server-side conversion events sent to Google Ads, Facebook Ads, and analytics (origin = your registered domain)",
"anycrm": "Yes. Every call and chat lead lands server-side.",
"smithai": "No.",
"myaifrontdesk": "No.",
"goodcall": "No."
},
{
"capability": "Scale ceiling",
"anycrm": "Bounded by Calendly API limits, not by staffing.",
"smithai": "Human tier bounded by receptionist staffing; AI tier bounded by Calendly API limits.",
"myaifrontdesk": "Bounded by Zapier rate limits and action contracts.",
"goodcall": "Bounded by per-agent Event Type configuration."
}
],
"footer": "Every row in this table is solved one layer down inside AnyCRM. Not in the prompt. Not by humans. Not by Zapier."
},
"faqs": [
{
"q": "Does this actually work with my Calendly account?",
"a": "Yes. AnyCRM uses Calendly's official API via a standard OAuth grant (or a Personal Access Token). Every captured caller lands as a real Calendly invitee on the right Event Type, on the right host's calendar. With name, email, timezone, and call-summary answers populated against the Event Type's custom questions. Same Calendly UI, same Calendly reminder emails, same reschedule and cancel URLs your invitees already know."
},
{
"q": "Will it book on Event Types I don't actually offer?",
"a": "No. Setup imports each host's active Event Types as a frozen table. The AI Receptionist can only offer Event Types that exist on this host's Calendly page. Never a duration or kind you don't actually run."
},
{
"q": "Will it just text the caller a Calendly link instead of booking?",
"a": "No. AnyCRM books the invitee live on the call. The slot is re-validated against Calendly's available-times response at commit, the custom-question answers are assembled against the Event Type's frozen question list, and the booking is confirmed back to the caller before they hang up. That's the whole point. The SMS-the-link pattern is what most competitors do, and it's where their drop-off lives."
},
{
"q": "Can it route different callers to different hosts on my team?",
"a": "Yes. AnyCRM reads your Calendly organization roster once at setup. Every active member, with their lane (Discovery / Demo / Strategy / Renewal), default Event Type, and timezone. Caller intent matches to lane, lane matches to host, host's Event Type gets booked. Calendly's own round-robin Event Types are honoured where you already use them."
},
{
"q": "Where do the bookings actually live, Calendly or somewhere else?",
"a": "In Calendly. A booking is written as a native Calendly invitee on the routed-to host's Event Type. Same Calendly UI, same reminder emails, same reschedule and cancel URLs your invitees already know. You don't get a shadow scheduler. You get the AI Receptionist driving the Calendly you already run."
},
{
"q": "Can it cancel or reschedule a Calendly event from a phone call?",
"a": "Yes. The caller gives their email, AnyCRM finds the soonest upcoming Calendly event they're an invitee on, the AI Receptionist reads it back, and AnyCRM either reschedules in place (preserving the event UUID, the host, the Event Type, and the answers) or cancels with the caller's reason landed on the Calendly event itself. Not a bare \"cancelled by invitee.\""
},
{
"q": "What if a caller has two upcoming Calendly events?",
"a": "AnyCRM returns every upcoming event for that invitee email (Event Type, host, date, time) and the AI Receptionist asks which one to change before doing anything. It never assumes."
},
{
"q": "Does it handle timezones correctly?",
"a": "Yes. The AI Receptionist confirms the caller's country/timezone, AnyCRM converts the start time to UTC for the booking, AND stamps the invitee record with the caller's IANA timezone so Calendly's reminder emails render in the caller's local time. The AI Receptionist also reads the confirmation back in the caller's local time. No customer-facing UTC strings, no off-by-an-hour confirmations."
},
{
"q": "Does it create Deals?",
"a": "Not directly. AnyCRM stays focused on the conversation surface: capturing the caller, matching the right host, booking the Calendly invitee. Deal creation is YOUR business policy, and that policy lives inside your CRM, in the receiving flow we wire up for you at onboarding. Every invitee-create and every reschedule in AnyCRM sends a lead event straight into that flow (tagged with source AI Receptionist Call or AI Receptionist Web). Your flow decides which pipeline, which stage, which source tag, which workflow trigger. AnyCRM doesn't try to encode policy that will drift out of date the moment your business changes."
},
{
"q": "How does the conversion tracking work?",
"a": "Every lead event AnyCRM produces (from a phone call, a chat conversation, OR a website form / chatflow) flows through a single conversion pipe. It lands in your CRM for business logic. AND it fires server-side into Google Ads, Facebook Ads, and your analytics platform, using the origin of the domain you registered with AnyCRM. Server-side means the conversion can't be blocked by ad-blockers and doesn't degrade under iOS / Safari tracking restrictions. The result: higher ROAS, lower ad costs, enriched analytics, and attribution that doesn't fragment between web and voice. As far as we can tell, none of our competitors have built this yet."
},
{
"q": "What about my existing website forms? Do they go through the same pipe?",
"a": "Yes. That's the whole point. Web forms / chatflows AND the AI Receptionist produce the same lead-event shape with the same source taxonomy. They land in the same place in your CRM, and they fire the same server-side conversion event into your ad platforms. So your bid strategy optimises against unified, real conversions instead of fragmenting across web-only and voice-only stacks."
},
{
"q": "How long until it's actually booking Calendly events from calls?",
"a": "Most teams are live the same afternoon. The OAuth grant takes a minute. The organization-members and Event-Types import is automatic. We wire up the lead-receiving flow inside your CRM during onboarding. The phone integration is usually under an hour. Web chat is faster."
}
]
}