A question that has been on our minds lately is how to build a community around Pyrefly when AI is rapidly reshaping longstanding open source norms. I don't think anyone has fully figured this out yet, including us, but we're making some changes to Pyrefly's contributing guidelines that we think are a good start. Here's what we've seen change in open source and what we're doing about it.
Does adding type checking to an agentic workflow really help agents?
We ran an experiment recently to determine whether there are improvements in the success rate for completing different kinds of tasks. In theory, having a type checker present should help the agent catch type errors earlier, validate fixes incrementally as it works, and reduce the need for slow, test-driven iterative feedback loops.
This talk was originally presented at the PyCon US 2026 Typing Conference. The slides and edited transcript are provided below for your convenience.
Coding agents are writing more Python than ever. Tools like Claude, Copilot, Cursor, and Codex generate entire features with little-to-no user interaction. But in large projects, this generated code is prone to type errors, mismatched signatures, and subtle API misuse. Incorporating static analysis directly into the agentic loop can mean the difference between returning from your break with a production-ready feature or needing several more correction cycles.
Type checking sits right in the sweet spot for agents. It's fast enough for iterating small fixes, robust enough to catch issues of varying complexity, and actionable enough for an agent to make changes. In this post, we walk through how to integrate Pyrefly into your agentic workflow so that every piece of generated code can get type checked automatically.
TL;DR: We recommend:
AGENTS.md directive to ensure the project checks clean before finishing a feature.