Overview
Fill the schedule with the right visits. It learns from your booking history to recommend slot layouts and flag likely cancellations, and answers requests like “next week, preferably in the afternoon” with real free slots. Staff decide what changes.
How it works
Learns from the practice’s booking history: demand per visit type, visit durations, no-show and cancellation rates. It recommends slot layouts and where to place which visit type, and predicts which bookings are likely to be cancelled. Staff decide what to adopt; existing appointments are not moved on their own. It also answers individual appointment requests in natural language (e.g. “next week, preferably in the afternoon”): it looks at the real calendar and suggests up to three free slots, each with a score and a reason; booking a slot files it in the calendar and drafts the confirmation reply.
What Corti handles
- Reading booking history for demand, durations and no-show patterns
- Slot layout recommendations and cancellation predictions
- Understanding appointment requests in plain language and matching them to free slots
- Drafting the confirmation reply
What you build
- Read and write access to your calendar, exposed as tools
- The screen where staff review recommendations and suggested slots
- Your rules for visit types, durations and who can book what
Make it yours
- Write the instructions the agent follows
- Pick a larger model for harder problems, or a smaller one for speed and cost
- Pick the model the agent runs on
- Skip the thinking step when you want faster, cheaper answers
- Connect the tools and data sources it can use
- Choose how much effort the model puts into reasoning
- Decide who can see and use the agent
- …and much more