How we work.

A two-week audit finds where the work is held up. Then we build, test and deploy in two-week cycles until the first job meets the standard, and we stay to keep it running.

FIRST TWO WEEKSTHEN, EVERY TWO WEEKSAuditMap the work.Set the direction.Cycle 01Build, testand deploy.Cycle 02Build, testand deploy.Cycle 03Build, testand deploy.The platform and world model carry forward.We operate and improve what is in use.
First two weeks
Audit
Map the work. Set the direction.
Every two weeks
Cycle 01
Build, test and deploy.
Every two weeks
Cycle 02
Build, test and deploy.
Every two weeks
Cycle 03
Build, test and deploy.
The platform and world model carry forward. We operate and improve what is in use.

01 · Audit · Two weeks

Find where the work is held up.

We spend time on site with your team. People can’t fully describe their own work, so we watch it: the inputs, decisions, handoffs and exceptions. Then we find the constraint and redesign the process around what AI can now do.

02 · Build · Every two weeks

Put agents to work, two weeks at a time.

Each cycle has a clear scope. We build with your team, test on real examples and deploy what meets the standard, in the tools your team already uses. Every two weeks we review the results together and decide what comes next. The first job goes live when it passes the evaluations we agreed.

ScopeAgree the resultand the checks.BuildConnect, designand implement.EvaluateTest on realexamples.DeployPut the changesinto use.REVIEW THE RESULTS. SET THE NEXT SCOPE.
Scope
Agree the result and the checks.
Build
Connect, design and implement.
Evaluate
Test on real examples.
Deploy
Put the changes into use.
Review the results. Set the next scope and repeat.

03 · Run · Ongoing

We stay to keep it running.

We host and operate the platform, monitor the work and rerun the evaluations when anything changes. The connections, evaluations and world model carry into the next piece of work, and over time your team shapes more of the workflows itself.

Quality

We agree the standard before we build.

Real examples of your work, including the messy ones, become evaluations. We track four things.

  • Quality

    Does the work meet the standard on real examples?

  • Cost

    What does each piece of work cost, compared with before?

  • Time

    How long before the result is ready?

  • Human effort

    What review, correction or intervention is still needed?

Before we start

What we need from you.

  • An owner

    An internal owner with the authority to make decisions and drive implementation, ideally a founder or someone on the leadership team.

  • Time with the team

    Time with the people who do the work, so we can watch it and test what we build with them.

  • Access

    Agreed access to the systems and data the work depends on.

We work with companies in Europe and the US.

Pricing

Two parts, agreed before we start.

Deployment services

The audit is a fixed fee, based on the people and departments involved, and is credited against the first build if you go ahead. Each build is a fixed fee, agreed at the end of the audit.

The ongoing platform

A monthly fee, sized at the end of the audit to how much your agents will do. Unlimited users and no annual commitment. We review the size with you every quarter.

We agree the scope, expected usage, support and fees with you before work begins.


Let’s plan the audit.

Tell us where the work gets stuck. We’ll work through the audit scope, who should be involved and how to get started.