AGENT ENVIRONMENT •
Fleet running
A method, running in production

The thinking lives in the environment, not the chat.

The environment carries the work forward: decisions in ledgers, progress in status files, context in handovers and checks in review protocols. The next session starts with a record of what happened and what remains to do.

The reasoning layer

The method is externalised cognition: putting decisions, evidence and operating rules into an environment that sessions can read, question and update. The models do the work. The environment gives that work continuity.

01

Persistent state

LEDGER.md · STATUS.md · HANDOVER.md

Keep decisions, progress and handovers in files that survive a session ending. Dated records give the next session a starting point and a trail it can check.

02

Forced metacognition

bookends · in writing · before start, before done

Ask “how would this claim be wrong?” before starting and again before declaring done — in writing. Make the assumptions, evidence and unresolved limits visible to the next reviewer.

03

Independent review

counters · frozen candidates · duplicate protection

Freeze the work being reviewed, give another session the evidence, and record its findings. Keep review counters and receipts so the next session can see which checks have already run.

04

Different models

one authors · a second reviews · a third reviews independently

Have one model author the work, a second review it and a third review it independently. Record disagreements and resolve them against the evidence before release.

A good firm is smarter than any employee in it. Sessions are the employees. The filesystem is the institution.

Not a pitch deck

Jesse runs his companies with a fleet of AI agents he directs — this page describes the method those companies actually run on. Built by an operator with no coding background and no formal research.

12 months

of daily use inside live companies.

The environments built Grace — customer-facing AI deployed in legal and finance.

1,000s

of enquiries handled by deployed agents.

From Jesse · October 2026

It had to earn its keep.

I was deploying agents inside my own business. I had no option but to make that investment pay. This method grew out of the operating pressure to make it work, day after day.

For the last several months, I’ve been bullish: agents need an environment that carries the state, the standards and the work forward. It’s the only way I would deploy agents into my business.

Over the last few weeks, it’s felt like the world is catching up to that view. For me, this was an operating result before it was a thesis.

— Jesse

See it running

The frontier is coordination between AI-augmented parties — not capability inside any one of them.

Request a walkthrough

One email. No list, no funnel.