Building production agents: the observability layer
Agents are still software, but traditional monitoring can't see what they actually do. A practitioner's case for treating observability as a first-class layer, and how we do it with Logfire.
5 stories
Agents are still software, but traditional monitoring can't see what they actually do. A practitioner's case for treating observability as a first-class layer, and how we do it with Logfire.
Connect Pydantic Logfire's MCP server to Cursor, Claude Code, or Codex and let your coding agent query real production traces, then build the dashboard and the alert that catch the next one.
AWSLambdaDurability checkpoints every model request, tool call, and MCP call as an AWS Lambda durable step. An invocation that times out or gets retried resumes from the last completed step instead of paying twice for work the agent already did.
A practical guide to Langfuse alternatives in 2026: what each one is licensed under, what its meter counts, who it suits, and when staying on Langfuse is the better call.
A practical guide to Sentry alternatives in 2026: who each one is actually for, how their pricing models differ, and where Sentry is still the right call.
Showing 5 of 5 stories
You're all caught up.
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news from PydanticAI Blog
Join 15,000+ AI enthusiasts