Pydantic AI introduces using coding agents to trace and improve workflows
Understand this story
Duncan McKinnon of Pydantic AI introduces a method for tracing data and improving workflows with coding agents: using Logfire's coding agent tracing feature to record model calls, tool calls, and request responses, then letting agents query historical sessions with SQL through the Logfire MCP server. According to his article, the purpose of doing this is to hand tracing data back to coding agents for optimization across models, users, teams, and companies.
AI overview based on source reports · Updated 18 hr ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Pydantic AI ArticlesUsing coding agent traces to improve your workflows
This article explains why coding harnesses need observability, since model invocations, tool calls, retries and dead ends happen out of view, and describes how Logfire's coding agent tracing captures model invocations, tool call execution and request/response pairings across sessions. It walks through use cases including dashboards for productivity, cost and time, monitoring a software factory, reusing past session context across harnesses, and turning repeated struggles into skills, with an example where a skill took dashboard panel creation from 3/12 to 12/12 passing cases. It closes with an evaluation workflow that compares reviewer harnesses on a dataset of five code review cases, where Codex with gpt-6-luna scored highest overall at 3.93, ahead of Cursor at 2.80 and Claude Code at 2.60.
Activity for this story
- Current comparable activity
- 5
- Peak comparable activity
- 7Nov 14 05:00
- Change in the past 24 hours
- –
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.