# Squad playbooks: agent teams for real engineering work

> A squad is a leader agent plus members whose jobs you write. These playbooks show the setup, the objective to paste, the limits to use and what you get at the end.

- Canonical: https://runtallos.com/squads

- [Best of three: crack a hard problem three ways](https://runtallos.com/squads/best-of-three.md): Best-of-three squad playbook: three AI agents attempt the same objective in separate worktrees, a leader compares the results and recommends one.
- [Close a bug straight from the ticket](https://runtallos.com/squads/bug-from-ticket.md): Squad playbook: paste a Linear, Jira, GitHub or GitLab link and AI agents reproduce the bug with a failing test, fix it and review the fix.
- [Build + review: refactor with a reviewer on watch](https://runtallos.com/squads/build-and-review.md): Build + review squad playbook: one AI agent builds, another reviews, and they loop until the reviewer approves. Nothing reaches you before that.
- [Run maintenance on a schedule with a squad](https://runtallos.com/squads/scheduled-maintenance.md): Scheduled squad playbook: save a build + review squad once and Tallos runs it every weekday, leaving a reviewed dependency upgrade for you to accept.
- [Ship a feature end to end with a squad](https://runtallos.com/squads/ship-a-feature.md): A squad playbook to ship a feature with AI agents: a leader splits API, UI and tests across members, checks each part and hands you one branch to accept.
- [Raise test coverage in parallel with a squad](https://runtallos.com/squads/test-coverage.md): Test coverage squad playbook: a leader assigns one module to each of four copies of the same AI agent, then merges every new test into one branch.

---

Run your agents in parallel with Tallos: https://runtallos.com/signup