Virgent AI logoVirgent AI

Cal.com Agent v2 Demo

Cal.com AI Agents
API v2

This demo mirrors the new Cal.com AI agent guidance: use slots, bookings, reschedule, and cancel workflows on v2 endpoints with explicit versioning. It is built as an agent-style skill layer that can be attached to your main chatbot while preserving normal RAG and intent behavior.

Live Slot + Booking Demo

Demo is live. Complete human verification before scheduling actions.

Human verification (required for create, reschedule, cancel)

Scheduling actions are blocked until verification is complete.

Reschedule / Cancel

Use a booking UID. Reschedule and cancel require Cal.com API key permissions.

This demo shows our Cal.com agent integration. To actually book a call with our team, submit the contact form — we personally schedule every intro.

Demo Output

Run an action to see live output.

Business use case

What this demonstrates: A production-grade scheduling skill that plugs into an existing chatbot. It checks live availability, books, reschedules, and cancels meetings directly through Cal.com v2 — with human verification before any write action.

How it relates to your business: The moment a prospect says “let’s meet,” the agent locks a slot and sends the invite. No back-and-forth emails. No scheduling links that expire. No human admin required for routine booking changes.

Pain it solves: The four-email scheduling dance kills deals. Every day of delay halves response rates. And rescheduling is usually what breaks it.

Who it is for: Sales, CS, recruiting, and professional-services teams whose first task after every conversation is “get time on the calendar.”

Real-world examples:
  • Sales chatbot books a discovery call the moment a lead qualifies.
  • Support agent reschedules an on-site visit through conversation instead of a ticket.
  • Recruiter agent offers three available slots and commits the one the candidate picks.

How It Works

1) Detect scheduling intent from natural language.
2) Fetch live availability from `GET /v2/slots`.
3) Create booking with `POST /v2/bookings`.
4) Handle updates via reschedule/cancel endpoints.

Value Props

• Faster scheduling directly from chat.
• Less drop-off versus sending users away too early.
• Better qualification context attached to booking.
• Deterministic skill path for predictable outcomes.

Source Docs

Official Cal.com references used for this demo.

Architecture

User Chat
   │
   ▼
Intent Router (main site agent)
   │
   ├── non-scheduling ──► standard RAG + model routing
   │
   └── scheduling intent ─► Cal.com Scheduling Skill
                            │
                            ├── GET /v2/slots
                            ├── POST /v2/bookings
                            ├── POST /v2/bookings/{uid}/reschedule
                            └── POST /v2/bookings/{uid}/cancel

Want this in your production chatbot?

We can wire this Cal.com scheduling skill into your existing assistant without breaking core RAG and intent logic.

Book a build session
Virgent AI
Virgent AI
Powered by Multi Model · AG UI

VIRGENT AI · Multi Model · AG UI