The slide deck is locked
Sign in below to open the deck and the rest of the write-up.
What we covered
The session is built around one artefact: a Sri Lanka tourist guide agent that answers by voice, calls tools mid-conversation, and can be cut off mid-sentence without losing the thread. Everyone leaves having built it.
- How AI communication moved from request-response to a persistent, interruptible stream.
- The model ecosystem underneath: Gemini's native audio, and what ADK adds on top of it.
- WebSockets versus WebRTC, and the cases where each is the right transport.
- ADK's architecture: the high-level system, then the tool-calling loop that does the real work.
- Writing it: initialisation, the WebSocket endpoint, custom tool definitions, and interruption handling.
- Observability with LangFuse, so a non-deterministic conversation is still debuggable after the fact.
- Deployment and scaling: what changes between one caller and a thousand.
Members only
Keep reading
The slide deck and the rest of this write-up are free, sign in with Google and they stay unlocked on this device.
No newsletter, no spam. Your email is used to keep you signed in.