Have Copilot coding agent write and push code
A developer found the agent good at context and code, but it pushed to a branch leaving main empty and spent hours checking after being told to proceed.
AI pair programmer and coding agent inside GitHub.
GitHub Copilot suggests code in the editor, reviews pull requests and can take an issue and open a PR with a proposed fix.
A developer found the agent good at context and code, but it pushed to a branch leaving main empty and spent hours checking after being told to proceed.
Users report the agent sometimes fails to read terminal output and may undo correct code; workarounds include switching shells.
GitHub engineers used Copilot tools to have agents write most of an 800,000-line Rust rewrite of the Copilot runtime across 128 PRs, fixing a few regressions.
An author gave the Copilot coding agent two small changes on their own site; it opened draft PRs and the spacing change was good enough to merge.
The author used autopilot to iterate until done and /fleet to split work across parallel subagents, noting overhead on small tasks.
Copilot and Claude review each PR for bugs, missing tests and risky changes before a human looks, so reviewers can focus on design.
A commenter built a basic hiring agent loaded with competency definitions and levels for HR evaluation work.
Plan, execute and review a cross-cutting refactor in small batches, with Claude Code making the edits and GitHub Copilot reviewing each PR.
A founder set up CEO, CFO, COO, lawyer, accountant, marketing, CTO, and improver agents that share memory and consult each other.
Claude Code reads your coverage report, picks the riskiest untested modules and writes unit tests that pass, one small PR at a time.