How it works

How an agent gets generated

There is no platform to learn and no prompt to write. You describe the job once. Everything after that is the product: the spec, the build, the connections, and keeping it working as things change.

  1. You10 minutes

    Describe the job

    Ten minutes on the brief form. Name the agent, describe its one job, tick the tools it needs, and say where a human should stay in the loop. Plain English throughout.

  2. Us1 business day

    It becomes a spec

    Your description comes back as a spec: what the agent will do, what it will not, and a fixed price. Then a short call on the edge cases, because the exceptions are what make an agent useful or useless.

  3. Us2 to 4 weeks

    It gets built and connected

    The agent is built and wired into your accounts. Nothing gets copied out of your systems that does not need to be. First runs happen in draft mode so you can read its work before it touches anything real.

  4. BothFirst 2 weeks

    It goes live, watched

    You watch the first cycles and tell us where it is wrong. Agents earn autonomy the same way people do: one correct week at a time. You decide when to widen what it does on its own.

  5. UsOngoing

    It stays working

    Payers change rules. Tools change APIs. Your process changes because you got better at it. Keeping the agent correct is part of the product, not a surprise invoice.

  6. YouWhen you are ready

    You generate the next one

    Most teams start with one job and add a second once they trust the first. Each new agent is another description, and the second is faster because your stack is already connected.

Writing the description

What to include

Write it the way you would brief someone on their first Monday: here is what lands on your desk, here is what you do with it, here is who to ask, here is what you never do without checking.

  • One job, not five. Agents that do one thing stay reliable.
  • The exceptions. The three weird cases are the actual work.
  • The line. What it does alone, and what waits for a person.
  • The measure. One number that tells you it is working.
The spec you get back
Scope
The job as the spec reads it, in one paragraph you can correct.
Not doing
What it deliberately leaves out, and why.
Connect
Which systems, what access each needs, and what stays untouched.
Human
The approval steps, fixed before anything is built.
Timeline
First working version, and when you see it.
Price
Build, plus what it costs to keep running.
One business dayNothing starts until you agree
Questions

Before you start

How long does an agent take?

A narrow first version is usually two to four weeks. Anything that touches a system without a clean integration takes longer, and we say so during scoping rather than discovering it later.

What does it cost?

Price depends on the systems involved, so it is set on a call once the spec is agreed. You get a fixed number in writing before anything is built.

Where does our data go?

The agent works against your accounts with the narrowest access that does the job. We do not build a shadow copy of your database, and we do not train anything on your data.

What if the tool we use has no API?

That is common in dental, construction, and insurance software. There is usually a path, whether that is a file drop, a portal session, or a workaround the vendor did not advertise. Tell us the system and we will tell you honestly whether it is workable.

Do we need someone technical on our side?

No. You need someone who knows the job well enough to say when the agent got it wrong. That is usually the person doing the work today.

What if we want to stop?

You keep your accounts, your data, and the output. We disconnect and hand over documentation for what was built.

Which job should be first?

The repetitive one that gets skipped when the week gets busy. That is almost always the right first agent.