Skip to content

The Human-Agent Operating Layer

One layer underneath every AI tool your teams already use.

Your people are already working with AI. What they lack is anything underneath it: a shared understanding of your systems, one governed way to act inside them, and a record of what worked.

Bring your own tools Claude Code, Codex, Cursor, chat, Slack, or agents you wrote yourself. All of them reach the same brain and the same governed tools.
Engineering sets it once Connectors, scopes, tools, roles and limits are infrastructure decisions, made once and reviewed, rather than re-argued per request.
It runs where you run Your VPC, your Kubernetes, or air gapped. Self hosted is the default rather than the enterprise tier.

See it working

What it looks like when it is running.

Six surfaces your team would use in the first week. Open any capture at full size.

The Company Brain: an entity resolved graph across accounts, people, services, documents and SOPs

A living company brain

Your accounts, people, services, documents and procedures, entity resolved and cross linked, re-curated from every connected source rather than loaded once and left.

A grounded, cited answer about an account at risk

Answers cited to your systems

Why is this account at risk, and who owns the renewal. Answered from the brain with the owner, the lost champion and the usage drop, each traceable to the row it came from.

Versioned skills registry with publish and deploy actions

Skills compound across the team

A versioned registry your people publish to, fork from and deploy. The tenth teammate starts from the ninth's best work rather than from an empty prompt.

A review queue gating learnings proposed by agents

It learns from corrections

Agents propose learnings from real runs and a person approves or rejects before anything enters the company brain. Compounding that someone signed off on.

An internal app built from a plain English brief, running on live data

Describe an app, and it ships

A plain English brief becomes an internal app on live data, here a view of deals at risk with drafted nudges and a person approving before anything sends.

Run observability: trace detail with phases, cost and tool calls

Every run traced and costed

Runs from every harness in one place, opened down to phases, tool calls and spend, so who ran what and what it cost are answerable questions.

Demo data throughout. The product is real; the company in it is invented, so nothing here needs anyone's permission to show.

What installs

One substrate, with your tools above it and your systems below it.

Everything above the middle band is replaceable by you, and everything below it stays where it is.

Fig. 10 · your tools above, your systems below, the layer between

The six capabilities

Most teams ship one of these. They only work as one system.

You may already have two of them. What makes an agent safe enough to leave running is the wiring between them, which is why they are built and governed together.

Company Braincontext, profiled

Every source into one graph that re-profiles itself and escalates what it is unsure about.

live

Skills libraryknow-how, versioned

How your company does a thing, written in plain English, versioned and shared.

live

Agent builderplain English

Describe an agent, assembled from skills the team already published, running against the same brain and the same governed tools.

live

App buildersandboxed

Internal apps and live views on real data, scanned at build and deployed to a sandboxed URL behind the egress proxy rather than to somebody's personal account.

live

Governed accessone door

Separately revocable credential surfaces, roles across every transport with denials audited, tool allowlists, parameter contracts, egress control and a kill switch, applied the same way to a person, a tool and a scheduled agent.

live

Learning loopcorrections, promoted

Every run traced. Every correction reviewed and promoted so it reaches every agent, rather than dying in a chat window.

live

The test that matters

Take one vendor away and see what survives.

Every layer in an AI stack claims to be neutral, so the word is worth nothing. Remove each piece in turn and ask what your company still has on Monday, including us.

Fig. 07 · the same test applied four times
How this compares to the four obvious alternatives →

Where the work actually is

Connecting data and calling a model is the easy half.

These five are what stand between an agent that demos well and one you would let near a real customer.

01

Keeping context current

Schemas drift, definitions change, documents go stale.

common outcome: a one time setup, then decay

Company Brain →

02

Who authors the rules

The knowledge that makes an agent correct sits with your ops leads and analysts.

common outcome: engineers relay it, imperfectly

Rails and authoring →

03

Agents that actually act

Reading is safe. Writing to a CRM, a ledger or a live campaign is where the blast radius starts, and it needs one door with a log on both sides of it.

common outcome: keys in a chat window, no audit

Governance →

04

Earning autonomy

Nobody turns an agent loose on day one. What is the gate, who sets the threshold, and what is the rollback when a change makes it worse.

common outcome: no gate, and a judgement call

The ladder →

05

Learning from what ran

Every run and every correction is signal. Stored and never read, it is a log. Reviewed and promoted, it is the reason the same agent is better next quarter.

common outcome: traces kept, never used

Learning loop →

What it connects to

Your existing stack, connected rather than replaced.

Connectors are read scoped before anything becomes callable, and a system with no connector is reachable through its own API as a declared tool.

BigQuery Snowflake Postgres Salesforce HubSpot Zendesk Jira Notion Google Drive Sheets S3 Slack Email WhatsApp Ads and analytics internal APIs
What teams build on it →

See it against your own systems.

A walkthrough on a schema and a workflow you already know well, so you can tell within minutes where this fits what your team is trying to build and where it does not.