Thanks — I’m responding to your question about running tool calls that update DB fields in the background. Short answer: Yes. You can run DB-updating tool functions asynchronously so they don’t block the agent’s conversation or UI. Options you can use: • Define the tool as an async function and perform the DB write with

await

so the agent remains non-blocking. • Use a fire-and-forget background task (e.g.,

asyncio.create_task(...)

) to start the update and return immediately with a task ID or confirmation. • If updates are long-running, have the tool schedule the work (background worker, job queue) and return right away. • Delegate the update to an external webhook/HTTP tool that performs the DB work asynchronously, letting the agent continue and optionally receive a callback later. • For user-facing flows, play a short “thinking” audio or status message while the background update runs to indicate progress. If you’d like, tell me: • Which runtime/language you’re using (Python, Node, etc.), • Whether the updates are short single-row writes or long batch jobs, • If you need confirmation/callback when the update completes. I’ll give a concise code example or recommended pattern for your environment. Sources: Tool definition and use | LiveKit docs | External data and RAG | LiveKit Docs | Announcing Agent Builder: A Pathway to Code