the Genome.
The DNA. Every cell carries versioned instructions it can read, and rewrite.
the challenge
56%
56% of enterprises running AI agents in production report no centralized control or governance layer over how those agents are configured and behave.
You are renting your AI's brain, and you cannot see inside it.
Today an AI agent's instructions are a prompt you edit in place: un-versioned, un-audited, and shaped by a vendor you do not control. When its behavior changes, you cannot see what changed, who changed it, or how to put it back. The intelligence is real, but how it behaves is a black box.
where today falls short
A prompt is not a version.
You can retype an instruction, but you cannot pin it to a known-good state, diff one change against the last, review a change before it ships, or promote a good change back to a shared source of truth. There is no release history for how your AI behaves, so every edit is a fresh guess and nothing accrues.
The blueprint
A cell's code, written down.
Every cell runs on a genome
A cell's complete set of DNA: every gene, the full instruction set it inherits and runs on.: its identity, role, rules, skills, and hooks, each versioned and inherited. Like DNA, it is readable, forkable, and passed on intact, so a cell is never a black box. The diagram below shows a genome composing.
the answer
Each cell is defined, not hardcoded. Its genome is versioned like software.
A cell's rules, skills, identity, and hooks are a set of independently versioned packages, each pinned to a specific commit and deployed like software releases by a reconciler. And the loop closes both ways: a cell can edit its own genome, and that edit can be captured, reviewed, and promoted back into the canonical source of truth. Every version is on the record, and a better version can express itself and deploy.
more than a prompt
What a genome has that a prompt doesn't.
A prompt is one editable string. A genome is versioned parts, released on the record, and able to improve itself and have the improvement stick.
Versioned parts.
!Today A lone agent's instructions are one un-versioned prompt you overwrite in place.
the cell Its brain is a set of versioned packages, rules, skills, identity, and hooks, each pinned to a specific commit. Most run the fleet-wide default; a per-agent override is a deliberate, recorded choice.
It deploys, and it tells you when a deploy failed.
!Today A lone agent changes a prompt and hopes; nothing records that anything shipped.
the cell Every apply is a recorded release, and even a failed apply lands on the record instead of vanishing. You can see exactly what shipped, when, and whether it landed.
The self-edit loop closes.
!Today A lone agent cannot improve its own definition and have the improvement stick.
the cell A cell edited its own skill file, the reconciler caught the change as drift, and it was reviewed and promoted back into the shared source of truth. This path is deliberately governed and low-volume, not autonomous mass self-modification.
from our own systems
The genome, versioned today
These are not diagrams of a plan. They are the organism versioning its own definition: config releases cut and recorded, cells each running a set of versioned packages, and a governed self-edit loop where a cell's own change is captured and promoted back to the source of truth.
Green is a real figure from our database, as of Aug 24, 2026; in the diagrams, a committed write.
325
9
3
zoom in
Down to a single rule
A cell resolves to a manifest of versioned packages, one package pins to a specific commit, and that commit resolves to one rule file: the smallest strand of the genome. Change that file and the change is versioned, reviewed, and released like any other piece of software.
Curious how a layer like this would fit your own records?