Use case · Engineering

Know which pull requests are ready before standup

To check release readiness with AI agents, install the Ship Software Safely team in Brainwrite and connect GitHub. Every weeknight at 21:00, Rigel reviews pull requests opened or updated against your default branch, records check status, review status, size, and age, and flags what looks ready, what is stalled, and what has failing checks. It never merges or approves.

Download for MacSee the ready-made team
Release readiness

Turn on the nightly release readiness sweep for our web app repository. In the morning, tell me which pull requests can go in Thursday's release and which are blocking it.

Your Chief of Staff put a team on it

  • Atlas· Rigel, QA and Release Engineer
  • Sage· Ada, Tech Lead
  • Dash· Lin and Pixel, Backend and Frontend Engineers
  • 11 pull requests opened or updated since last night's sweep
  • Looks ready: 4 (checks green, approved, under 300 lines)
  • Stalled: #482 open 9 days with no reviewer assigned
  • Failing checks: #491 integration tests, #493 lint

DoneSaved as a routine: Weeknights at 21:00. It starts paused until you turn it on.

An illustrated example. Your team works on your own files and apps.
Split scene: at 11:04 pm a developer rubs his eyes alone at his desk; at 7:04 am he drinks coffee while AI agents Atlas and Dash show finished work.
11:04 pmYou hand the bug to your team.
7:04 amTwo fixes ready for review.
AtlasResearchRoot cause found
DashOpsTests passing
NovaChief of Staff
7:40 am

Release readiness: done. Nothing sent.

  1. 111 pull requests opened or updated since last night's sweep
  2. 2Looks ready: 4 (checks green, approved, under 300 lines)
  3. 3Stalled: #482 open 9 days with no reviewer assigned
3 bots on this job
Every merge and approvalWaiting for your yes

The job

Doing it yourself, and handing it off.

Doing it yourself

Before a release, someone opens the pull request list and clicks through each one. Are the checks green? Has anyone reviewed it? Why has this one been open for nine days? Is it safe to ship with the rest? The answers live across CI, review threads, and people's memory, and the list changes daily. By release day the picture is stale, and decisions get made on a hunch.

What the team does

  • Review pull requests opened or updated since the last sweep
  • Record check status, review status, size, and age for each
  • Flag ready, stalled, and failing pull requests
  • Draft a release checklist with rollback options when asked

What waits for you

  • Every merge and approval
  • Whether the release goes out
  • Any comment posted on a pull request

See it in the app

What it looks like in Brainwrite.

A real screenshot from a demo workspace.

Editing the Daily briefing routine: bot picker, Post results to a dedicated results thread, the task prompt and where the run executes.

The team

Who's on it.

Your Chief of Staff picks the specialists the job needs. Each has its own role, instructions, model, and app access.

  • AtlasIllustrated example

    Rigel, QA and Release Engineer

    Runs the nightly sweep, turns acceptance criteria into a risk-based test plan, and reports what passed, what is uncertain, and the rollback options.

  • SageIllustrated example

    Ada, Tech Lead

    Owns scope and tradeoffs, inspects the existing system before proposing changes, and coordinates the release decision.

  • DashIllustrated example

    Lin and Pixel, Backend and Frontend Engineers

    Own the service and interface boundaries, compatibility, and the focused tests that show a change works.

How it runs

A run, step by step.

  1. 01

    Install and connect

    Add the team from the team library and connect GitHub. The nightly routine arrives paused.

  2. 02

    Point it at a repository

    Tell Rigel which repository to watch. It asks for one if none is configured.

  3. 03

    Nightly sweep

    Weeknights at 21:00, Rigel records the check status, review status, size, and age of each pull request opened or updated since the last sweep.

  4. 04

    Decide in the morning

    Read the flagged list: ready to merge, stalled without a clear reason, failing or missing checks. You merge.

Start faster

Ready-made teams for this job.

Add a team from the library in one click. You see a preview first; routines arrive paused and connected apps stay off until you approve them.

What you'll connect

Apps this job uses.

FAQ

Questions about Release readiness

Can the AI merge pull requests?

The sweep routine is written to report only: it does not merge, approve, or comment on anything. Outside that routine, a bot with GitHub tools can request actions, and in Ask mode each one becomes an approval card you accept or deny. Denying hands control back to the bot so it can choose a safer path.

Does it run my tests?

The nightly sweep reads check status from GitHub; it does not run your test suite. For hands-on verification, give a bot a computer, such as an isolated Local VM through Docker or Podman, or your own Linux VPS over SSH. Rigel can then reproduce defects and verify fixes there.

Do I need the whole team?

No. The team has four roles, but the readiness sweep is Rigel's routine alone. You can install the team, turn on only that routine, and use the other bots when you plan or review a change. Each bot can run its own model, so you can match model cost to the job.

Built on

Features this job relies on.

Keep going

Put a team on something else.

Give your first job to Brainwrite.

Download the app, connect the AI you already pay for, and tell your Chief of Staff what needs doing.

Download for MacSee how it works

macOS today. Windows and Linux are coming soon.