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.
What the Document Substrate is
Document Substrate is a platform for firms that produce signed work from client documents and prioritize privacy by design, traceability, and a complete record of every decision.
Unstructured documents are still the dominant interface businesses use to store and share the information they run on. Statements, invoices, receipts and agreements: layout, language and context mixed together, in a form no downstream system reads directly.
The substrate is the foundation every Orbital system is built on. It 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:
- Reads the shoebox. 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.
- Every figure is traced to its page. A figure that cannot be found on the page is flagged, never passed.
- 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.
- 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.
How the Document Substrate works · Explained simply · Project detail
Principles
- Garbage in, garbage out. Validation checks that a file is complete and consistent before any money is spent on it.
- Doer to reviewer. Verification checks that each figure is true to its source, so people review the machine's work instead of doing it.
- Keep the model out of the parts that have to be defensible. The model reads and suggests. Code checks and decides. A person signs.
- Personal details never leave the building. Leaking customer data is the one thing a business cannot get wrong. Details are removed before the model sees anything, and restored only for the person allowed to see them.
- Ledger, not spreadsheet. Records with provenance. Excel only at export.
- One install per customer. Your documents in your own accounts, not a shared database.
- Small firms first. Practices, property managers, professional services, councils and co-ops.
- Expertise is captured, not generated. Models and prompts are commodities. Your definition of "complete" and your correction record are not.
Questions to Ask
Three questions that 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 the expertise an AI system needs. 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 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.