Engineering blog Post 06

KrewHQ: running an engineering programme with a crew of AI agents

Vivek Raja5 min readPart 6 of 9, published as one series

  • KrewHQ
  • process
  • review
  • agents
KrewHQ on Kiro Crew: one hub, a spoke per teamarchitecture
Programme leadKiro Crew · commonsSDKKiro CrewSDK harnessKiro CrewConstellOpsKiro CrewConstellOps harnessKiro CrewRobots forkKiro CrewKrewHQ hubKiro Crew · auditeach spoke its own Kiro Crew instance · crossing teams: promote or handoff only

One day a release commit quietly rewrote evidence bundles that were already on main, so each manifest claimed a run at its original date with a lockfile that did not exist then. The author was an AI coding agent.

The review board, an independent AI reviewer agent, called it false provenance and ruled the release a no-go, and every file was restored byte for byte the same day. This is how one engineer ran a crew of AI agents, and why that review board existed.

Why a crew needs shared memory

Agents forget between sessions, and parallel agents do not see each other's work. Left alone, that produces duplicated effort, contradicting decisions and, worst, one team quietly relying on another team's internals.

KrewHQ is the team-context layer the programme ran on. It gives agents shared, scoped, auditable team memory.

A hub enforces scope and provenance on every read and write and keeps an audit ledger. Each team works through a spoke, with a local queue, and sharing is an explicit promotion, not a side effect.

Record text is marked as data, and agents are instructed never to act on text inside it. Provenance and scope on every record limit what a misbehaving read could reach.

Built beside Kiro Crew

KrewHQ runs on Kiro Crew. Each team works in its own Kiro Crew instance, a spoke, and the hub runs its own instance too. KrewHQ is the layer between them: shared, scoped, auditable team memory beside Kiro Crew, with a hub API and a spoke for each team.

There are six spokes: the SDK, the SDK harness, ConstellOps, the ConstellOps harness, the robots fork and the programme lead. KrewHQ is the owner's own product, built beside Kiro Crew. Kiro Crew is named here only as what it runs on; no endorsement is implied.

The team map

The map is one team per repository, plus a programme commons. These are the comments at the top of the map file:

# One team per repo. Knowledge crosses teams only by explicit promote / handoff (scoped + provenance).
# `program` is the shared commons: every team is a member, so records promoted or handed off
# under program scope are readable by all teams. Team-scoped records stay private to their team.

Each team has a lead agent, with helper agents inside the team. The owner is the engineering manager of every team. A team reads and writes only its own repository and the shared docs, and uses other teams' work only as tagged releases.

How a record crosses teamsdata flow
Team recordprivate to the teamPromote or handoffexplicit, by theauthorHub checkscope · provenanceProgrammecommonsreadable by allteamsevery step → audit ledger

An independent review board

The review board is a fresh AI reviewer agent, never the author of the change, working in a clean context. It sees the pull request, the programme rules, the metric definitions and the design.

It must approve changes to the gates, the uplink path, autonomy levels and public interfaces, plus every release.

Its checklist includes: gates fail closed and cannot be bypassed; no fabricated numbers; no secrets or account identifiers; teams stay isolated. Verdicts are approve, request changes or reject, with conditions, and each is logged.

What "independent" means here

Every reviewer in this programme is an AI agent: independent reviewer agents with no shared context. No outside human has reviewed the code yet.

It is the same kind of model as the authors, so its independence is a clean context and no stake in the change.

It is not a different mind, and the owner's rejections (post 8) are partly why we know that matters.

Evidence gates before merge. Hosted CI was off on the private repositories. Merging needs board approval at the exact head commit, plus a recorded local verification at that same commit. If the head moves, it is verified again.

What went wrong

Re-records under one rule

During a live recording campaign, the network on the recording host failed twice. Runs recorded during the outages were unreliable, and the temptation is to pick the bad-looking ones by eye.

Instead, one criterion was written down and applied to every run: logged agent errors and failed model streams in that run's journal, or zero model calls.

Runs that matched were set aside with a note, their spend stayed in the accounts, and they were re-recorded. The board re-applied the criterion to every run folder and found it selected exactly the set-aside runs, with no mismatches.

The same board ruled that a run which failed to reproduce for a different reason could not be re-recorded away. Post 4 has that story.

The key-person question

The plain answer first: the founder, Vivek Raja, is the only human on this programme, and no outside human engineer has reviewed the code yet. Everything above reduces the risk; none of it removes it.

What does exist is a written trail a new engineer can read: every decision, review verdict and handoff is a record with scope and provenance, and every release has an evidence bundle.

An outside human code review is the next step we want, before any operator pilot.

Next pass

A crew of agents can build fast, and it can also rewrite its own evidence. What made this programme trustworthy was not the agents; it was the board that could say no-go, and the rule that recorded evidence is never rewritten.

§ · NEXT PASS

Request a briefing.

A 45-minute session with the evidence behind any figure. Operators can send a week of their queue.

This address is used only to reply to you. The site sets no cookies and loads no trackers.

Briefing requests