Meeting Bots on Butterbase

Meeting Bots on Butterbase

Guide for building features that spawn meeting bots via ctx.ai.meetings. Covers the four SDK methods, webhook handling, idempotency, and cost-aware design.

1. When to Use

Reach for this skill when your feature involves any of:

• Meeting notetaker — bot joins a recurring standup or sales call and stores a transcript.
• Sales call enricher — join a customer call, wait for bot.done, then run an LLM over the transcript to populate a CRM record.
• Interview pipeline — record and transcribe candidate interviews, then score against a rubric.
• Voice-of-customer transcripts — capture support or discovery calls; feed chunks into a RAG collection for future search.

If you need only audio/video file upload without a live meeting join, use manage_storage instead.

2. The Four SDK Methods

All methods return { data, error } — always check error before using data.

3. Typical Flow

1. Configure webhook — call manage_ai with action: "configure_meetings_webhook", passing forward_url pointing at a deployed Butterbase function or your own endpoint.
2. Start the bot — app calls bb.ai.meetings.start(...). Status begins as joining.
3. Bot joins — status progresses joining → waiting_room → in_call → recording. The bot.in_call_recording event fires.
4. Call ends — bot status moves to ended, then done once artifacts are processed.
5. Webhook fires bot.done — your handler receives the event. The bot's recordingUrl and transcriptUrl are now populated.
6. Fetch artifacts — download the recording or transcript using the URLs from bb.ai.meetings.get(id).