← Back to Bulkhead Forge

Bulkhead Forge — product / Agent Delivery

Agents write the code. Your team keeps the decisions.

Agent Delivery is a control plane for agent-driven development. Humans file tasks and review the artifacts — specs, then pull requests. Code agents draft, build and test in isolated VMs, behind review gates, a drift guard and budgets your team sets. The job shifts from writing to approving.

Working prototype · Google Cloud · EU region

The Agent Delivery control plane: counters for tasks in flight, items waiting on humans, active agents and spend today; a scope-drift alert offering re-scope, split or review; a "waiting on you" review queue; and a delivery pipeline board with columns for intake, spec review, building, code review and verify.
Agent Delivery control plane — prototype UI, sample data

Every screenshot on this page is the working prototype with sample data. The names, task IDs, token counts and dollar figures are fixtures used to build the interface — they are not client work, and not measured results.

The problem

Code generation isn't the bottleneck anymore. Trust is.

Agents can already write most of the code. What teams lack is the machinery around them: gates that decide what merges, guards that catch an agent drifting off-spec, and a bill that's visible before month end. That machinery is the product.

What changes when the control plane sits between the agent and your main branch.
Concern Agents today With Agent Delivery
Control Output merged on vibes and a skim of the diff Spec gate, then code gate — every requirement traced from R1 to the line that implements it
Scope An agent quietly rewrites half the service Drift gate: past the threshold the agent pauses itself and posts options — re-scope, split, or roll back
Spend Token bills discovered at month end Per-task budgets, weekly team caps, and agents that sleep at $0/hr while waiting on CI or reviews

How it works

The delivery loop: two gates, one human

  • Phase 01

    Intake

    A task arrives from Slack or the console. The agent reads the knowledge-graph slice around it and asks its questions up front.

    Slack · console

  • Phase 02 · gate

    Spec

    The agent drafts a spec as Markdown in your repo — goals, requirements, test plan. A human approves it, and approval auto-starts the build.

    docs/specs/*.md

  • Phase 03

    Build

    An isolated VM per task. Checkpoints after each step, sleep during CI, and a drift gate that stops work that grows past the approved scope.

    VM · checkpoints · drift gate

  • Phase 04 · gate

    Code review

    A pull request with requirement traceability and the agent's notes on why the code took this shape. Your feedback wakes the agent; it revises and re-requests.

    PR per task · min 1 human

  • Phase 05

    Verify

    Canary and end-to-end tests after merge, a delivery report, and the knowledge graph updated — so the next task starts smarter than this one did.

    Canary · e2e · report

Inside the console

Your home isn't a kanban. It's the review queue.

Eight screens, one idea: everything that needs a human is in front of you; everything that doesn't is an agent's job. Review is the work now — generation isn't.

Spec review screen: an agent-drafted specification with goals, non-goals and numbered requirements R1 to R5, changed sections marked against the previous version, alongside a review gate offering approve or request changes, the required reviewers, the version history and an impact preview.

Spec review

Agent-drafted, versioned in GitHub. Changed sections marked; one open question blocks approval. Approve — and the build starts itself.

Code review screen: a pull request with each spec requirement mapped to the diff hunks that implement it, plus the agent's notes explaining why the code took this shape.

Code review

Every requirement mapped to the diff that implements it. Agent notes explain why the code took this shape — challenge them, and it revises.

Agent fleet screen: counters for running, sleeping and gated agents and the week's spend against the team budget, over a table listing each agent's task, state, harness version, phase, uptime, tokens and cost.

Agent fleet

Every agent's state, harness version, tokens and cost — live. Idle agents auto-sleep; the week's spend tracks against the team budget.

Knowledge graph screen: services, entities and specs drawn as a connected graph with the blast radius of a selected task highlighted.

Knowledge graph

Services, entities and specs as a living graph. See a task's blast radius before the build starts — the same slice each agent loads as context.

Guardrails

Autonomy you can sign off on

  • Two human gates

    Nothing builds without an approved spec; nothing merges without a human review. Trivial diffs can take a no-spec lane — by policy, not by exception.

  • Drift gate

    When the implementation grows past your threshold, the agent pauses itself and posts options with estimates. A human decides; work resumes.

  • Spec traceability

    R1–R5 aren't prose — they're anchors. The pull-request view shows which requirement each hunk covers and which are still pending.

  • Sleep/wake economics

    Waiting on CI, a review or an answer? The agent sleeps at $0/hr and wakes on the event. Idle time costs nothing by design.

  • Versioned harnesses

    The agent runtime is versioned like software — stable, LTS, canary. Override per task; the change applies on next wake with session context preserved.

  • Your tools, both ways

    Specs live in your repo as Markdown; pull requests are real GitHub pull requests; reviews sync both ways. Slack carries intake, questions and escalations.

Google Cloud

Built on Google Cloud from day one

Running today

  • Console, BFF and domain services on Cloud Run — europe-west1
  • Isolated agent VMs provisioned per task
  • Cloud SQL (PostgreSQL) + Cloud Workflows pipelines
  • Google OAuth sign-in · GitHub & Slack integrations
  • Secret Manager · Artifact Registry · keyless WIF deploys
  • Cloud Monitoring — every model call metered (ai.model.*)

Where Gemini fits next

  • Spec drafting and intake Q&A on long context — a whole service slice in one pass
  • Coding-harness roles on Vertex AI, versioned and overridable per task
  • Drift detection as fast, cheap classification against the approved spec
  • Per-task token metering is already wired — model cost shows up on the task card, not the invoice

Roadmap

Where this goes

Now

  • Working prototype — 8 screens, full loop
  • Drift gate · harness override · sleep/wake
  • Spec & code gates with traceability

Next

  • Implementation on the Forge console stack
  • Live GitHub & Slack two-way sync
  • Real fleet telemetry & budgets

Later

  • Multi-team rollout & policy packs
  • Delivery analytics & reports
  • Findings from Discovery, tasks from Actions

Early access

Review is the job now. Generation is the agent's.

We're looking for teams to shape the first release with. Bring one service and one backlog — we'll run the loop on it together. One email is the whole first step.

contact@bulkheadlogic.com