Live LabsBuildersCoding agents3 hours

Put coding agents in your CI: review, fix and open pull requests

An AI-native team does not wait for someone to open a chat window. We run coding agents inside CI, on every pull request and issue, with limits on what they may change and a person who merges.

You leave with

A repo where an agent reviews every pull request and turns a labelled issue into a draft pull request a person merges.

How the time is spent

  1. I do45 minParam builds it live

    I label an issue and watch an agent open a pull request for it, then review another pull request in CI.

  2. We do72 minTogether, step by step

    We write the workflow, the instructions file and the rules on which paths the agent may touch.

  3. You do63 minOn your own code

    You add the agent to one of your own repos and measure what it fixed and what it got wrong.

What you will be able to do

Run agents in CI

Review and fix on every pull request, not only in a chat.

Limit what they change

Scope paths, tools and secrets per workflow.

Keep a human in the loop

An agent drafts, a person merges.

Starts from

Before you come

For
Engineers and tech leads making their team AI-native.
You need
A GitHub repo you can add a workflow to. An LLM API key.
Stack
GitHub Actions, Claude Code, Codex
Track
Hands-on agentic AI for engineers who ship.