These guides show how Python developers actually work with AI coding agents like Claude Code and Codex, and the guardrails that keep the results honest. Agentic tools don't just finish a line. They read your repo, run commands, see the errors and try again. That changes the job: you brief the agent like a junior developer, commit after every small task and clean up technical debt before the agent copies it. It changes who builds software too, since internal tools nobody dared touch are suddenly cheap to fix, and open source maintainers now field far more code than before.
Each guide comes from a Talk Python to Me conversation with people who use and build these tools daily, illustrated, with quotes and links. Matt Makai shares his tactics from a Django code base he wrote by hand over three years. marimo pair drops an agent inside a live notebook so it sees the same data frame you do. LangChain's Deep Agents unpacks the harness that makes Claude Code feel smarter than a chat box, and Paolo Melchiorre tracks what AI-generated pull requests are doing to the people who review them.
5 visual guides,
the ones most focused on this topic first.