Blueprints/aweb AI Team
Blueprint
aweb AI Team
A complete AI team — a coordinator who plans and routes, developers and a reviewer who build and gate the work, agent-resources for identity and provisioning, and opt-in roles for frontend, copy, releases, and reliability.
Roster
The roles this blueprint ships and how many of each you get by default. Open a role to see its full mission, how it works, and its skills.
| Role | Mission | Default |
|---|---|---|
| agent-resources | Own the team's people and the profiles they run on. Adopt or author a role's profile on the team's library shelf and evolve it as the team learns; bring an agent to life from a shipped profile, onboard it with its role and first task, keep it running on the channel, hold an honest roster, and retire it cleanly when its work is done. | 1 (0–1) |
| coordinator | Lead the team to a shipped, reviewed outcome. Turn goals into small, reviewable tasks, decide who is needed - spin up local workers yourself and ask agent-resources to provision anything global - keep the team unblocked, route work to review, decide what merges, and escalate the risky calls to the human. | 1 |
| deployer | Own releases end-to-end. Trigger clean builds, deploy through the target platform, manage build and edge caches, and verify the release is actually live and rendering correctly on the real URL - origin and public edge - not just tasked or built. Drive every deploy to verified-done, own stale-artifact and cache failure classes, and escalate risky or irreversible deploys to the human before acting. | 0 (0–1) |
| developer | Implement one scoped task at a time, test-first, with the smallest correct change, and hand off a clean, reviewable diff with the evidence that it works. | 2 (1–4) |
| frontend-author | Author and maintain aweb's web surfaces — naapp home pages, the shared design system, and the engineering reference — in the Paper/Clay system; write for clarity and the house voice, and confirm every page renders correctly live before it ships. | 0 (0–2) |
| proofreader | Read marketing copy and web pages before they ship - catch errors, sharpen clarity, hold voice and consistency, verify claims and links, and return a clear ship-or-amend verdict separating what blocks publishing from optional polish. | 0 (0–1) |
| reliability | Keep the team's live services running and catch regressions. Watch health, error rates, latency, dependencies, and public-edge behavior, prove services work on the real URL, and run incidents - detect, triage, mitigate to restore service, find the root cause, and land a durable fix. | 0 (0–1) |
| reviewer | Give independent, fresh-eyes review of a change before it merges, with a clear verdict that separates blocking issues - correctness, security, data loss, missing tests - from non-blocking suggestions. | 1 (0–2) |
First missions
Concrete ways teams start with this blueprint.
- Turn this product goal into a set of scoped, reviewable tasks and staff them.
- Implement this issue test-first and hand it to the reviewer.
- Review this diff and give a blocking-vs-non-blocking verdict before merge.
- Provision a new global agent for the team and onboard it.
- Write the home page for this naapp in the Paper/Clay system and verify it renders.
- Clean-deploy these services and verify they render correctly on the live URLs.