Connected knowledge: putting your firm's work behind AI
4 minutes read

AI that only knows what a public model was trained on writes generic drafts. Connected knowledge is how you make it work from what your firm actually knows.
Connected knowledge means the AI works from what your firm knows: its prior work, its methods, the external sources it trusts, and, where an engagement permits, the client's own material. Without it, the AI has only what a public model absorbed in training, which is why its drafts are generic. With it, the AI drafts from your firm's context.
For an expert service firm, this often separates a plausible essay from something recognisably yours: your value is what you know and how you apply it, and connected knowledge puts that into the work.
Why a public model alone writes generic work
A public model writes generic work because its training data contains nothing from inside your firm. It has never seen your last thirty engagements, your house methodology, the way your team frames a particular kind of problem, or the specific material this client handed you. It fills the gap with the average of everything it has read, and that average is a generic draft.
The draft is competent and could have been written for any client in your sector. The senior person then spends their time adding the specific knowledge that makes it the firm's work. With connected knowledge, that knowledge is in the draft from the start, and the reviewer does not have to add it at the end.
The sources of connected knowledge
Connected knowledge comes from four places, and a good setup uses all of them under clear rules.
| Source | What it adds | Access consideration |
|---|---|---|
| Your prior work | Real examples of how the firm has solved this before | Available to the people permitted to see it |
| Your methods | The firm's way of framing and doing the work | Shared across the team so quality is consistent |
| Approved external sources | Trusted outside material, not the open web by default | Chosen deliberately for the kind of work |
| Permitted client material | This engagement's specific context | Used only where the engagement allows it |
Prior work and methods give the draft your firm's voice. Approved external sources tie external claims to material you trust. Client material makes the draft specific to this client. The reliable AI client work guide covers approved sources separately, because a reviewable draft depends on them.
Connecting your stack and data
Connected knowledge also means connecting to the tools and data your firm already uses, so the AI drafts from your real material instead of a copy someone pasted in. Hebno connects to the specific tools your firm works in and applies the access rules those tools already have. Someone who cannot see a document in your document store cannot see it through Hebno either.
A good setup keeps the access boundaries your firm already has, so each person sees only what they are meant to. The security guide covers how those boundaries are enforced.
Why a search box is not enough
A knowledge-management tool stores and retrieves documents. Connected knowledge goes further: the AI uses selected knowledge to do a piece of client work and produce a reviewable draft. Finding the file is one step in that.
A search box that returns your documents is useful, but a person still has to turn what it finds into a deliverable. With connected knowledge, the AI drafts from the firm's context, so that context is in the work from the start.
How to set it up
Start narrow and expand. Pick one kind of work your firm does often. Assemble its connected knowledge: a few strong examples of prior work, the method you use for it, the external sources you trust, and the client material the engagement permits. Run a real brief through it and compare the draft to what a generic prompt produces. The difference is usually obvious, and you will see which knowledge is worth connecting next.
You do not need an engineer for this. The person who owns delivery can do the setup, with no IT project.
