Product

Your AI gets your company's rules.

The approved ones — not the ones somebody improvised in a chat window. One source: people and AI working hand in hand in the same direction, because both work from the same released state.

The problem appearing everywhere right now

In most companies several people now use AI tools, and each of them explains to their own assistant how the place works. What comes out is as consistent as any one person's memory: one knows the current procedure, another a version from two years ago, a third invented something plausible. The more employees, the wider the drift.

Keeping that aligned by hand does not work in practice. Pasting rules into a chat window creates a copy the moment it is made — and a stale one as soon as the original changes.

One release process, for people and machines

easo did not have to build anything new for this. The ceremony that makes a QMS audit-proof — review, four-eyes release, versioning, signature — is the same one that makes an answer trustworthy. What your team reads in the handbook is what your people's AI is told: the released version, not the draft and not the recollection.

One source, two consumers Drafts are not connected. Both your team and your team's AI tools read from the released, signed state; on the path to the AI sits a switch that the company turns on. Drafts Released state AI access Your team AI tools
One source, two consumers: your team reads what the AI is told — released, signed, with provenance on every answer. Drafts stay outside, and the path to the AI is opened by the company; it is off by default.

What we explicitly do not claim

easo transmits nothing — your AI tool does. The channel reads locally, and that is where our responsibility ends. Where your assistant sends what it read afterwards is decided by that tool and its provider. We tell you what the assistant gets to see, not what it does with it.

The switch governs easo's channel, not file access. Your QMS deliberately consists of open text files in your own git — which is exactly why you can never be locked out. Anyone with access to those files can point any tool at them. What we govern is the official, verified path with provenance attached, and that is a different thing from copy protection.

And we monitor nobody. This is about what the tools are told, never about what employees type.

Why not simply use one of the large platforms

That an AI should answer only from reviewed content is becoming self-evident — there are several providers for it by now, and that is a good thing. The open question is a different one: where does the approved version live, and who can verify it without the vendor?

Platforms that must first collect your company knowledge in order to show it to your AI answer that question with "here, with us". Tools that govern which server an assistant may call do not answer it at all — access control says nothing about whether the content is approved. With easo the source lives in your own git, the release is a cryptographic signature rather than a tick in a workflow, and both can be checked without us. Leaving easo costs you nothing.

Honestly placed

The channel today is read-only. It can answer from your QMS but change nothing in it, release nothing and withdraw nothing. Advisory functions — which clauses a text addresses, what is still missing — are the next step and are not shipped yet; we will write them here once they are. On a single device, read access is part of the free tier; the company-wide policy with automatic rollout across the team belongs to the Team plan.

Common questions about AI access

What does AI access actually do?

easo ships its own local server through which AI tools can read your QMS. Only the released, signature-verified state is served; every answer names the version, the release and the verification result. Drafts and unreleased edits are never served.

Do my documents leave the building?

Not through easo. The channel opens no network connection and reads your local working copy. What your AI tool then does with what it read, and where it sends it, is decided by that tool and its provider — not by easo. If you need to rule that out, choose an AI tool that runs locally.

Can the AI change or release anything?

No. The channel reads. Releasing, signing, withdrawing and everything touching control stay with people and stay bound to the existing release ceremony.

Who switches it on?

An administrator, in the company settings. The setting is recorded as a signed change like any other rule. The channel is off by default; while it is off, easo serves nothing this way.

Which AI tools does this work with?

Any that speaks the open MCP standard. easo sets up Claude Desktop and Claude Code itself; other tools are connected with a command easo copies out for you. Browser-based assistants are deliberately out — they would require your content to travel through someone else's servers.

So easo controls what our AI does?

No, and that would be the wrong promise. easo decides what the assistant is told from your QMS. What the model does with it belongs to the model. The switch also governs easo's own channel, not file access on your machine.

Stay in the loop

easo is available for macOS and Windows. The newsletter tells you what comes next — new versions and new content, nothing else.

Notify me