Your engineering process, run by coding agents.

Agents take work from your tracker, CI and alerts and do it the way your team works. People step in only where it matters. Every step is measured, so the process keeps getting better.

The factory dashboard: work moving through intake, agents, checks, the merge gate and the merge queue, what is in flight, what merged, and the outcomes of the last 24 hours.
  • Linear
  • Jira
  • GitHub
  • Bitbucket
  • GitHub Actions
  • Claude Code
  • Codex
  • Slack

Works with the tools your team already uses

Writing the code is the easy part.

The hard part is everything around it:

  • which work to take
  • how to check it
  • who decides
  • when to stop
  • what it may cost

That is your process. Today it lives in people’s heads. The factory writes it down and runs it.

Fig 0.1 V13 V12 V14

Your process, not ours

Encode how your team already plans, builds, reviews and ships. Change it whenever you like, one version at a time.

Fig 0.2 MAIN CHECKS PASS YOU DECIDE

People where it matters

Agents stop and ask, with the evidence and a recommendation. Everywhere else the work moves on its own.

Fig 0.3 V12 V13 V14 MERGED PER WEEK IF NOTHING CHANGED

Better every week

Every change to the process is recorded next to the numbers. Keep what helps, roll back what doesn’t.

● Questions

Questions engineering leaders ask

What the people who answer for delivery ask first, answered by what the product does today. Open a question for the detail.

  1. Every agent run records what it cost, and the dashboard adds it up per task, per project and per merged change.

  2. Each task has a budget and each project a ceiling; at the cap the next agent turn does not start, and a person decides what happens next.

  3. Cheap checks run often and expensive ones once, a merge batch is verified together, review and repair rounds are capped, and a person is asked only where your process needs one.

  4. Each kind of work takes the same steps, checks and caps every time, and the dashboard shows cycle time at p50 and p90, so you see how predictable it is instead of being promised it.

  5. Every event and everything a run produced is stored and cannot be changed once published; roles and project access decide who sees it, on the web, the API and MCP alike.

  6. The dashboard shows where work is and where it waits, and any task opens down to the transcript of each agent session.

  7. Each team gets its own process, budgets and access, while the merge queue, required checks and caps on load hold for all of them.

● The methodology in practice

How we ship our own screens with agents

This is our own UI design workflow, as the factory runs it today. Agents draft, check and fix. People review twice: a draft review of the idea, a final review of the finished screen.

See the workflows →

Who works at each step

  • Agent works
  • Check passes
  • Sent back
  • You decide
Step

The brief names the screen, its states, the components to reuse and what “done” looks like. A check refuses an incomplete brief before any agent starts.

Small interface fixes ship in batches: each merges on its own, and you review the whole area once.

1.0 Intake

Issues, pull requests and alerts start the work

Issues from your tracker, pull requests waiting for review, a broken build on main, an alert, a schedule, any webhook. Each source has its own rules for what gets picked up and which process it goes to.

Learn more →
SOURCES ROUTING WORKFLOWS OUTCOMES TRACKER ISSUES LINEAR · JIRA PULL REQUESTS FROM PEOPLE OR TOOLS BROKEN BUILD MAIN CI FAILS ALERTS ANY MONITORING SCHEDULES CALENDAR RULES WEBHOOKS ANY SYSTEM FEATURE DELIVERY MERGED TO MAIN PULL REQUEST REVIEW REVIEW ON THE PR REPAIR & INVESTIGATION FIX OR REPORT ROUTING RULES
Features

2.0 Process

Agents follow your process. Ask one to change it.

Everything that makes the process yours is set per team, and an agent can make the change for you. Ask in chat, or press Change with agent on the workflow: the change starts as a draft version that you check before it goes live, and can roll back.

Learn more →
Set per team
  • Sources and routes
  • Steps and states
  • The agent and instructions per step
  • Checks
  • Review rounds
  • Budgets and limits
  • Where a person decides
  • The merge policy
Every change
  1. DraftAsk an agent, or edit the workflow yourself.
  2. PreviewA change to the rules is tried on last week’s work first.
  3. PublishNew work starts on it; running work keeps its version.
  4. Roll backActivate the previous version.
A workflow drawn as a graph: planning, implementing, syncing, visual review, review and the fix loops, next to its changes against the previous version. At the top right, a Change with agent button asks an agent to make the next change.
Features

3.0 Reviews & decisions

Every change is checked before anyone is asked

Every change passes the checks your team defines: automated pre-checks, an agent’s review, a visual review for interface work, and a person where you require one. When the work needs a call, the factory stops and asks, with the evidence and its recommendation.

Learn more →
A design task stopped after the agent’s visual review: the review summary and three answers, each saying what it will do: approve the review, request changes or cancel.
Features

4.0 Control

Agents stop at the limits you set

Budgets per task and per project, caps on retries and on how many agents run at once. Roles and project access for every person and every agent. Agent sandboxes can run on your own machines. Nothing goes past a limit without a person saying yes.

Learn more →
AGENT TURNS BUDGET REACHED YOU ANSWER CHECKS SPENT $0 $5.00 BUDGET $5.40 RAISED TO $8.00 STOPS AND ASKS YOU RAISE BUDGET · REPLAN · CANCEL WORK IS KEPT PASS MAIN ALSO CAPPED: RETRIES · REVIEW ROUNDS · AGENTS RUNNING AT ONCE · TIME PER STEP
Features

5.0 Insights

Find where work waits, and fix that first

Measure the line, find where it slows, change the process and see what the change did. Each change to the process is marked on the charts, and with our weekly review you decide whether to keep it or roll it back. What agents find along the way, and review remarks that do not block, become follow-up work.

Learn more →
THE NEXT ROUND STARTS FROM THE NEW NUMBERS 01 MEASURE THE DASHBOARD 02 SPOT SIGNALS AND BOTTLENECKS 03 CHANGE A NEW VERSION, PREVIEWED 04 SEE THE CHANGE MARKED ON THE CHARTS 05 KEEP OR ROLL BACK A PERSON DECIDES
The performance dashboard: changes merged per week, arrivals against finished work, cycle time at p50 and p90, and the outcome of finished work per day, with the process changes marked along each chart.
Features

6.0 Agents & MCP

Use any coding agent. Steer the work from chat.

Claude Code, Codex, OpenCode or Pi: your process works with the agent you choose. Ask the built-in agent why something stopped, or connect your own agent over MCP and run the factory with your permissions.

Learn more →
The built-in agent chat: asked why a task stopped, the agent diagnoses it and raises the budget with the operator’s approval.
Features

● Proof

The factory builds itself. These are its numbers.

We build this product on itself, by the same methodology we bring to your team.

1,753
changes merged in six weeks
87%
merged with no person stepping in
1.0M
lines of TypeScript, about 40% of them tests
10,116
files in the repository

Our own numbers on our own products: 1,726 of the changes are on the factory’s own code. “No person stepping in” means no human decision, review verdict, recovery or hold on that change. This is not a forecast for your team.

● Changelog

Shipping every week

The factory ships the factory. A few of the latest releases.

  1. Every source in one queue

    Trackers, pull requests, broken builds on main, schedules and webhooks feed one queue, with priorities between them.

  2. Calendar schedules

    Run a workflow on a calendar rule. Missed slots are recorded, not lost.

  3. Review any pull request

    The factory reviews pull requests from people and other tools and posts the review on the PR.

  4. Decisions that explain themselves

    A stopped task says why it stopped and what each answer will do with the work.

● How we work

We bring the methodology. You keep your process.

We set the factory up with your team, on your tools, starting small. Autonomy grows only as fast as the numbers allow.

How we work →
01

Map

We map how your team works today and pick the first workflow: usually the chores that cost time and carry little risk.

02

Pilot

The factory runs it on one repository with your tools and your checks. You see every change, its review and its cost.

03

Expand

More workflows, more repositories and more autonomy, as the numbers earn it.

Keep your process.
Add the agents.