FireClaw

How we build

Agents build. People decide.

Brad runs about 50 AI agent sessions at once, across FireClaw’s two client systems and his own projects. This is the method that keeps it safe and fast, worked out across all of them, and it is what FireClaw brings to a client’s team. Each pattern below says where it runs.

How a change ships

Seven steps. Three of them only a person can do.

  1. A person

    A person writes the spec

    Drafted with Claude inside the app, then reviewed section by section.

  2. A person

    Only a person can accept it

    Agents can file work in the queue, but only a person can accept it.

  3. An agent

    An agent builds it

    Claude Code or Codex picks up the item and works in its own copy of the code and database.

  4. An agent

    A preview link that opens on a phone

    Every change runs at its own private link with its own copy of the database. Email and payments are switched off outside production.

  5. An agent

    The checks run

    Automated tests and checks run on every change, 209 steps on Brain alone. Past incidents have checks of their own.

  6. A person

    A person merges

    Agents can’t merge their own work. A person reads each change and decides.

  7. An agent

    Merging is deploying

    The new version goes live on its own, linked back to the spec and the session that built it.

The rules

Agents draft, people send

Anything that moves money, emails a customer, deletes data or widens access waits for a person. Everything else an agent can do on its own.

Keep agents busy, not waiting

Whatever needs a decision comes to the top of one queue. Everything else keeps working in the meantime.

No lock-in to one AI company

Claude Code, Codex and ChatGPT work from the same queue, and any AI feature can change model without a release.

Every incident leaves a check behind

When something breaks, the fix ships with an automated check that stops it happening again.

Works from a phone

Every system has a Claude connector and every change has its own preview link, so all of it can be reviewed from anywhere.

Patterns running in production

The build fails if Claude can’t use a feature

Every screen and API needs an MCP tool, or a written reason why not, before it can ship. That is why the tool counts are so high, and why an agent can do almost anything a signed-in person can.

1,081 MCP tools across 5Seasons, Bedplate and Brain

Runs in: 5Seasons (FireClaw), Bedplate (FireClaw), Brain (Brad’s own)

Errors file themselves as work for agents

When something breaks in production it becomes one written-up ticket, ready to hand to an agent. An hourly sweep sorts the new ones, and no agent starts a fix until a person accepts it.

Runs in: 5Seasons (FireClaw), Brain (Brad’s own)

Any AI feature can change model without a release

Each AI feature has its own model and prompt, and changing either is a setting that applies on the next call. Every call is logged with its cost and speed. At Acquirelytics a new model is tested against people’s own decisions before it takes over.

$1.36 for 4,178 AI calls in Bedplate in 30 days

Runs in: 5Seasons (FireClaw), Bedplate (FireClaw), Acquirelytics (Brad’s own), Brain (Brad’s own)

Many agents in one codebase without collisions

Each agent works in its own copy of the code, with its own database and preview link, and can’t commit into another agent’s copy. The house rules are thirteen practices, each written after the incident that taught it.

~15 ms to give a new agent its own copy of the database

Runs in: Brain (Brad’s own), 5Seasons (FireClaw)

The agents have their own GitHub account

Agents commit as their own GitHub user and go through the same steps as everyone else: the automated checks, then a person reading and merging the change.

500 pull requests opened by the agents’ account, each merged by a person

Runs in: 5Seasons (FireClaw), Bedplate (FireClaw), Brain (Brad’s own)

Starting an agent takes a hardware key

Starting or steering an agent session needs a tap on a security key or passkey, so a compromised server can’t set an agent going on its own.

Runs in: Brain (Brad’s own)

Tell us what you need.

A few lines is plenty. We’ll reply with a clear quote, usually within two business days.

Or email [email protected]