Turn "we govern our AI" from a claim into auditor-grade evidence.

Keel is the operating layer that makes agentic AI safe, observable, and auditable. Every change your people or your agents make carries a record of who did it, who approved it, and which controls fired. When an agent does something unexpected, you answer what happened instead of guessing; when someone asks for proof, you are not assembling it after the fact.

Deploys onto Azure · Microsoft Fabric · Databricks

One ledger, every actor.

This is Keel's own estate: two code repositories, a Databricks workspace, and the GitHub organization itself. Every change, deployment, and control run lands in the same table, whether a person, a pipeline, or an agent did it.

WhenWhoActor typeWhereWhatRun outcome
2026-08-12 01:27Claude CodeagentGitHub: keelport/keelrepo:keelrunning
2026-08-28 18:05steventchirhumanGitHub: keelport/keelkeelport/keel#195succeeded
2026-08-28 17:48steventchirhumanGitHub: keelport/websiteThe feed and figures learn the three-way actor taxonomysucceeded
2026-08-28 17:45steventchirhumanGitHub: keelport/websitekeelport/website#8succeeded
2026-08-28 17:38keel-opsserviceDatabricks: keelportchecked the evidence dashboard against its governed sourcesucceeded
2026-08-28 17:38keel-opsserviceGitHub: keelport orgchecked branch protection against the manifestsucceeded
2026-08-28 17:32keel-opsserviceGitHub: keelport/keellinked architecture decisions to their implementing commitssucceeded

Work still in flight first, then newest first, as of 2026-08-28.

A keel is the part of a ship nobody sees. It sits below the waterline and keeps the boat upright, so the crew can sail hard without thinking about it. Keel does the same job for a company adopting AI agents: the structure underneath that lets you move fast without tipping over.

Every organization adopting AI agents faces the same two questions.

One

Can I let agents in without losing control?

You cannot safely put an agent on an ungoverned estate. Keel installs the golden path first: gated deploys, protected branches, drift detection, rollback. The foundation agents can safely operate on, and the one your team needed anyway.

Two

Can I prove what they did?

Every actor, human and agent, writes to one ledger held in your own estate. Who acted, under which identity, who approved, what the controls found. You read the same ledger your agents write to, row by row.

How it works

An opinionated way to ship, and a record of everything that shipped.

One manifest, whole estate

A single reviewed file parameterizes a client: platform, environments, identity, approvers, evidence store. Repos generate from templates and onboard in dependency order with one command.

Stood up on a new client in a day.

Deploys that can't skip the gate

One merged commit flows dev to stage to prod; prod always pauses for a named human, who sees exactly what approving applies. No auto-approve path to prod exists. Not policy: structure.

A rollback is a governed deploy, not a bypass.

The estate can't quietly change

Daily controls compare live branch protection, approval gates, and infrastructure against what the manifest declares. Hand-edits and out-of-band changes become recorded findings the next morning.

Drift is bounded by time, not by luck.

One evidence base

Every control writes to one ledger: runs, events, alerts, rollbacks, tamper-evident and checkable after the fact. "Show me all unauthorized prod changes this quarter" is a query, not an archaeology project.

A control that isn't logged is a claim, not evidence.

Agents with accountable humans

AI agents get their own identity, cryptographically separate from any person's, and every agent carries the name of the person accountable for it. Supervision becomes gates and queryable evidence instead of watching.

Your agents' compute bill grows with the work; your payroll doesn't.

Governed to the exit

Create, govern, sync, roll back, retire. Offboarding is where orphaned access comes from, so leaving the fleet is as governed as joining it: one reviewed change retires a repo, and the record survives.

History is evidence: archived, never deleted.
Proof, not promises

We run our own controls on ourselves.

Keel's own estate is governed by Keel. Every change on record so far was merged by the founder without an independent approver, and the system flagged every one.

542
runs on record
3
by AI agents
385
by automated controls
41 of 41
changes merged without an independent approver
31
architecture decisions on record
Walk through the evidence

Live figures from the ledger, as of 2026-08-28. They move.

For regulated teams

Most vendors sell controls. Keel sells evidence that the controls fired.

OSFI B-13 / E-23attributable records of automated and model-driven actions, with accountable-human mapping NI 52-109change authorization and separation of duties, evidenced per change at merge time Law 25 / SOC 2operating effectiveness demonstrated by daily recorded controls, not sampled screenshots ISO 42001AI actions governed under named human accountability, in one auditable graph

See it on your stack.

A thirty-minute walkthrough of the live evidence, then what standing this up on your estate looks like. Write to hello@keelport.ca.