Any corpus
“Works for any documents” is only credible if onboarding a new vertical is a configuration pack rather than a fork of the product. That constraint is enforced in the code, not asserted in a diagram.
The core knows nothing about any industry. Ingest, chunking with byte offsets, hybrid RAG retrieval, the grounding contract, verification, the LangGraph review gate — none of it contains a word about security, finance, or medicine.
A pack supplies exactly four things and nothing else:
The formats this vertical actually arrives as. Scanned PDFs, Confluence exports, spreadsheets, contract sets.
The deliverable. A compliance audit reads nothing like a technical RFC.
Vocabulary and context. It cannot relax the grounding contract — the core enforces that regardless of what a pack says.
An evaluation set for that vertical, including questions the corpus deliberately cannot answer.
If adding a vertical ever requires editing the core, the pack interface is wrong and gets widened. It does not get worked around. That is what makes “any corpus” checkable rather than a claim.
| Pack | Documents | Deliverable | Status |
|---|---|---|---|
cyber |
Security policies, SOC 2 reports, pen-test findings, CIS & NIST controls | Security questionnaire responses · control-gap assessment | First |
fintech |
SEC filings, AML/KYC policy, card-network dispute rules | Regulatory compliance audit | Designed |
saas |
Confluence wikis, pull requests, incident post-mortems | Technical RFC · architecture guide | Designed |
health |
Clinical trial documents, FDA guidance, insurance policy | Medical policy brief | Designed |
legal |
Vendor MSAs, IP filings, contract clause libraries | Due-diligence brief | Designed |
Built means running against real documents with measured behaviour. Designed means the interface exists and the pack does not yet. We would rather tell you which is which.
Not because it is the largest market. Because it has the sharpest version of the problem: a customer security questionnaire is answered in writing, signed by a named person, and read later by someone deciding whether to trust you. Inventing a control you do not have is not an embarrassment — it is a misrepresentation.
It is also a domain where the right answer is frequently “our documents don’t say”, which most systems are structurally incapable of producing.
Each pack carries its own gold set. Four numbers, reported separately and never averaged into one score — each fails in a different direction, and a combined figure hides which.
| Metric | Question it answers |
|---|---|
| Grounding rate | Of the claims made, how many carry a quote that resolves? |
| Retrieval hit@5 | Of answerable questions, how often was a supporting document in the top five? |
| Correct refusal rate | Of unanswerable questions, how often did it decline? |
| Fabrication rate | Of unanswerable questions, how often did it answer anyway? Must be zero. |
A fabricated answer can score 100% on grounding: the invented claim is perfectly “sourced” to an irrelevant passage. Averaged into one number, that failure disappears entirely. The unanswerable half of a gold set is the valuable half.
No number appears in our materials until the harness prints it on a real corpus. Where we have not measured, we say so rather than estimate.