# Team: leading a team that ships with agents

URL: https://developertoolkit.ai/en/teams/
Description: For tech leads: roll agents out to a whole team, share one harness, keep the review queue moving, and bring skeptics, seniors and juniors along.

To lead a team that ships with agents, make the setup a team system, not one enthusiast's habit: roll out one repository at a time, share one versioned harness, fix review gates before adding parallel agents, and give seniors ownership of those gates. Each part of this hub names the Tech Lead Scorecard questions it answers.

You just got approval to roll agents out to all eight engineers on your team. Each of them already uses a different tool with private settings, CI checks only lint, and nobody has decided who reviews what an agent opens. You have to choose what to standardise first. These pages give you that order and a way to check it worked.

## Where should a tech lead start?

Take the [Tech Lead Scorecard](/en/lead-scorecard/) first (25 questions, about eight minutes). The [answer key](/en/lead-scorecard-guide/) maps each question to its page and names the evidence a 3-point answer needs. If you have no score yet, start from the symptom you see:

| What you see on the team | Start with | Scorecard questions |
| --- | --- | --- |
| Everyone configures their agent differently | [Shared agent rules](/en/cto-scorecard-guide/shared-agent-rules/) · [Developer onboarding](/en/cto-scorecard-guide/dev-onboarding-time/) | 1–4 |
| Agent pull requests wait days for review | [Running the review queue](/en/teams/review-queue/) | 6 (14, 15 related) |
| Plausible-but-wrong code reaches `main` | [The evidence bundle](/en/workflows/ship/evidence-bundle/) | 7 (5, 8 related) |
| Agents get tickets they cannot finish or verify | [Shaping a backlog for agents](/en/teams/agent-ready-backlog/) | 17 |
| Seniors re-review everything or opt out | [Skeptics and senior engineers](/en/teams/skeptics-and-seniors/) | 12 |
| Usage is patchy and nobody knows why | [Adoption roadmap](/en/teams/adopt/adoption-roadmap/) | 9–11 |
| Juniors ship code they cannot explain | [Upskilling a team](/en/teams/upskilling/) · [Growing junior developers](/en/teams/junior-developers/) (related) | 18 |

## Roll out: from one pilot repository to the whole team

A rollout moves one repository at a time, with a pilot, a support owner and an exit criterion written down before it starts. These pages answer questions 4 and 9–11.

- [Adoption roadmap for one repository](/en/teams/adopt/adoption-roadmap/)
- [Team onboarding and adoption](/en/teams/adopt/team-adoption/)
- [Project conversion playbook](/en/teams/adopt/project-conversion/)
- [Workflow transformation guide](/en/teams/adopt/workflow-transformation/)
- [Team adoption: measure effective workflow use](/en/cto-scorecard-guide/team-adoption-rate/)
- [Developer onboarding: prove one safe workflow](/en/cto-scorecard-guide/dev-onboarding-time/)
- [AI metrics panel: measure accepted delivery](/en/cto-scorecard-guide/ai-metrics-panel/)

The [roll-out hub](/en/teams/adopt/) also links the guides for teams switching from another tool.

## Shared harness: one setup instead of eight private ones

The [harness](/en/workflows/harness/) is the shared instruction core (`AGENTS.md`, with thin adapters such as `CLAUDE.md` and Cursor's Rules), skills, hooks and MCP servers every agent on the team loads. It lives in the repository and changes only through pull requests. These pages answer questions 1–3, 16 and 20, and they cover Claude Code, Codex and Cursor side by side.

- [Team collaboration: shared context and rules](/en/teams/adopt/team-collaboration/)
- [Shared agent rules: one core, tested adapters](/en/cto-scorecard-guide/shared-agent-rules/)
- [Documentation as context for every agent](/en/workflows/context/documentation-as-context/)
- [Shared skills: tested procedural capability](/en/cto-scorecard-guide/shared-skills/)
- [Shared hooks governance: reviewed runtime controls](/en/cto-scorecard-guide/shared-hooks-governance/)
- [Internal MCP servers: build only the missing interface](/en/cto-scorecard-guide/internal-mcp-servers/)

## Review and flow: keep the queue moving without rubber-stamping

Agents raise the arrival rate of pull requests; review capacity stays where it was. Fix the gates before you add parallel agents, or reviewers start approving without looking. These pages answer questions 5–8, 14, 15 and 17; the answer key lists the second page for each.

- [Running the review queue when agents open the pull requests](/en/teams/review-queue/)
- [Helping the team stop reading every diff](/en/teams/trust-transfer/)
- [Code quality gates](/en/workflows/test/code-quality/)
- [Layered pull-request review](/en/developer-scorecard-guide/layered-pr-review/)
- [Test: give the session a feedback loop](/en/method/lifecycle/test/)
- [Shaping a backlog for agents](/en/teams/agent-ready-backlog/)
- [Team PR review automation: evidence before approval](/en/cto-scorecard-guide/team-pr-review-automation/)
- [Team parallelism: isolate work and cap the queue](/en/cto-scorecard-guide/team-parallelism-tier2/)
- [Run a bounded PR review-fix loop](/en/developer-scorecard-guide/auto-pr-workflow/)
- [Million-line codebases: strategies for coding agents](/en/workflows/build/large-codebases/)

## People: skeptics, seniors, juniors and keeping current

The tools change weekly; the people decide whether the system holds. These pages answer questions 12, 18, 19 and 21.

- [Bringing skeptics and senior engineers along](/en/teams/skeptics-and-seniors/)
- [Growing junior developers when agents write the code](/en/teams/junior-developers/)
- [Upskilling a team for agentic engineering](/en/teams/upskilling/)
- [Keeping a team current when the tools ship weekly](/en/teams/keeping-current/)
- [Knowledge sharing: version evidence, not tricks](/en/cto-scorecard-guide/knowledge-sharing/)

Questions 13 and 22–25 (tooling ownership and budget, cost, secrets, what agents may not touch, which tools to standardise on) sit with the organization. Their pages are listed in the [answer key](/en/lead-scorecard-guide/); most sit in [Engineering organization](/en/org/), with tooling policy and MCP security under the CTO scorecard guide.

## How do you know the team system works without reading every diff?

Ask for artifacts, not reassurance. Every merged agent pull request carries an evidence bundle: the acceptance criteria, the tests that prove them, and the required checks that passed. Branch protection enforces the same gates on every pull request, whoever or whatever wrote it. [Reading evidence instead of code](/en/ladder/evidence-not-diffs/) explains why that replaces line-by-line review.

Then watch three numbers each month: time in review, change failure rate (the share of deployments that cause a failure in production), and the share of sampled pull requests where a human found something the gates missed. The tech lead owns the gates; a named engineer owns the evidence for each [loop](/en/ladder/one-map/) (a repeatable class of change with its own trigger, oracle and stop condition). Treat these as a team contract and commit it next to `AGENTS.md`:

**Adopt as-is: team agent agreement**

```text
TEAM AGENT AGREEMENT (reviewed quarterly, changed by pull request)
1. Harness: one shared rules core per repository (AGENTS.md) with thin
   per-tool adapters; skills, hooks and MCP config are checked in, and
   each has a named owner.
2. Gates: lint, types, tests and coverage are required on every pull
   request. An agent PR also attaches its evidence bundle.
3. Flow: at most N open non-draft pull requests awaiting review,
   team-wide (the WIP cap); agent dispatch pauses at the cap. Size
   budget: one reviewable change per PR. High-risk paths always get
   a human.
4. Trust: each loop sits at one stage (shadow, sampled or evidence-only)
   and moves back one stage after a production escape or a material
   miss in a sampled read.
5. Measures: time in review, change failure rate, sampled-review findings.
   Reviewed on the first Monday of each month.
6. People: seniors own the gates; juniors practise specified tasks by
   hand; one person watches releases each week.
```

Replace `N` with the team-wide WIP cap your review capacity supports; the review queue page shows how to size it.

## What goes wrong when a team rolls out agents?

- **Agents amplify weak gates.** DORA's 2025 report (Google Cloud, 23 September 2025) puts it plainly: "AI doesn't fix a team; it amplifies what's already there." Recovery: freeze new parallelism, fix questions 5–8, then raise the cap.
- **The harness forked.** Each developer tuned a private setup, and agents now disagree on conventions. Recovery: merge the private rules into the shared file through one reviewed pull request, and route later changes the same way.
- **Trust moved faster than evidence.** The team skipped review on a loop that had weak tests, and a defect escaped. Recovery: move that loop back one stage, as the trust transfer page describes, and strengthen its tests before moving forward again.
- **Seniors were routed around.** Adoption numbers look good while senior engineers re-review everything. Recovery: hand them ownership of the gates and the rules.

## Where to go next as a tech lead

- [The tech lead track](/en/start/tech-lead/) — The ordered reading path, from the autonomy ladder to trust transfer.
- [Tech Lead Scorecard answer key](/en/lead-scorecard-guide/) — Each of the 25 questions, its page, and the evidence for 3 points.
- [Place the team on the ladder](/en/ladder/one-map/) — One map of autonomy levels, judged by what actually reaches production.
- [Engineering organization](/en/org/) — The operating model, controls and budget your team works within.
