AI That Thinks Like Your Best People

Every business runs on expertise that took years to build — the instincts, the judgment calls, the "we just know" that separates good from great. Most AI has no access to any of it, so it gives textbook answers when your clients expect yours. Orbital builds AI systems grounded in how your business actually works.

Intelligence is bought. Expertise is built.

The model supplies intelligence: reasoning from whatever context it is given. Anyone can buy it, and next year's model will be better.

Expertise is knowing how this firm does the job: which document to reach for, which figure does not add up, when a finding is accepted with a note and when it is chased. It lives in people and in the checklists, letters and corrections they produce. No model has it. It has to be captured, written down, and tested against real work.

A substrate captures your expertise

We call this captured expertise a substrate. It has three layers and three wrappers.

The three layers are what the firm already knows.

• Quantitative. The metrics, frameworks and calculations the field uses: materiality in accounting, bracing tables in construction, training load in cycling coaching. This is textbook material, plus the firm's own calibrations of it.
• Subjective. What the metrics miss. Pattern recognition built up over years, such as knowing something is wrong before the figures show it. It is rarely written down, but it affects decisions.
• Procedural. How an expert responds: the structure of a good answer, the order of the steps, the decisions nobody has written down.

Three wrappers are defined from the layers.

• Question archetypes. The kinds of question that come up in the work, grouped by how they are answered.
• Constraints and safety. What the expert refuses to do, what is escalated, and what is out of scope. These matter as much as what the AI can do.
• Grounding constraint. What every output is tied to, so that it is correct for this firm and this client, not just plausible.

Every answer the AI gives is tied back to both the layers and the wrappers.

A written substrate needs software to apply it to real work. That software is the Document Substrate.

Why "substrate"?

How the Document Substrate works

Document Substrate is a platform for firms that produce signed work from client documents and prioritise privacy by design, traceability, and a complete record of every decision.

Businesses still store and share most of their information in unstructured documents. Statements, invoices, receipts and agreements mix layout, language and context, and no other system can read them directly.

The Document Substrate reads those documents whatever form they arrive in, keeps personal details away from the AI model, and checks every figure against the page it came from. What comes out is a record a reviewer can check and sign.

The Document Substrate flow:

• The shoebox is read in any state. PDF, Word, Excel, scans and photos, arriving by upload, email or API. Document type is detected from the contents. Confident detections are applied; the rest wait for a person.
• Personal details never reach the model. Names, addresses, bank account, IRD and company numbers are replaced with placeholders before any model call and restored only for an authorised person. Every restore is logged.
• Checks run in code. Twenty-two document types have field definitions and eighteen have arithmetic checks. Same files, same verdict.
• The model never does arithmetic. Code adds the totals. The workpaper and draft letter are generated from checked records only.
• Every figure is traced to its page. A figure that cannot be found on the page is flagged, never passed.
• A person reviews and signs. Uncertain items come first, each with a reason.

For each firm:

• Quality is tested against the firm's own work. Rated answers and corrected figures become permanent test cases that gate every change. For redaction, zero leaks is the pass mark.
• The firm's judgement is written down. A practice manual in the firm's words, with a test that fails the build if the manual and the checks disagree.

The Document Substrate in detail · Explained simply · Principles

Where to start

You can start on your own substrate today. Three questions show where your firm's expertise is, and where AI will save time.

• What does a good answer depend on? Pick a question your senior people are asked often and answer well. List what the answer has to be based on to be defensible: the figures, the standards, the earlier cases, the firm's written position. That list is most of your quantitative layer, and it is what every answer has to be tied back to. Write it down.
• What do new staff get wrong? Pick a mistake a junior makes in their first six months, and ask what the senior person knows that the junior does not yet. It is usually in the procedural or subjective layer: a procedure or a judgement call that nobody has written down. It is the most valuable thing to capture, because at present only a few people have it.
• How much of that hour needs that person? Do not start with what can be automated. Start with an hour of work someone repeats every week, and ask how much of it needs them.

Worked examples across six professions · Map, Architect, Build in practice