Tutorials
Voice first — LiveKit, latency, barge-in, the parts that break on a real call. Earlier agent-runtime notes live below.
Start here
Phone agents need dates, room types, and callback numbers. The instinct is a CallState dataclass and next_question(). LiveKit Agents already solved that with AgentTask and TaskGroup — here's the hotel receptionist that shows how.
Also
Earlier
A 7-part series from 2026. Kept because the URLs still get hits — not because it is what I am building now.
Every new agent project starts with the same hand-rolled loop. Part 1 of the Mastra series: define a typed agent, wire tools with createTool, and add memory so it survives the next turn — without rebuilding the plumbing again.
Agents decide. Workflows guarantee. Part 2: typed multi-step pipelines with sequencing, parallelism, branching, loops, and human-in-the-loop suspend & resume — for the steps where order isn't up for a vote.
Refresh the tab. Approve a delete. Hand off a subtask. Part 3: Mastra's AgentController adds sessions, modes, subagents, and tool approvals — the layer that turns a loop into something users can depend on.
Ten seconds of silence looks identical to a crash. Part 4: wire agent.stream() into a UI — tokens, tool calls, and custom progress events — so users watch the work happen instead of staring at a spinner.
A confident answer with no source is still a hallucination waiting to happen. Part 5: chunk, embed, store, query — wire a retrieval pipeline under your agent so it answers from your documents, with citations.
Forty-page scrape. Human approval that takes a day. A cron job at 3am. Part 6: background tasks, crash-proof durable agents, and heartbeats — machinery for work that doesn't fit in one request.
The demo sounds sharper. Production quietly gets worse. Part 7 — the series finale: deterministic checks, model-graded scorers, CI gates, and live sampling so 'it seems better' becomes '0.86, up from 0.71'.
Topics