BramForgeLabs / Products / Insurance AI Radar / Preview
Free sample · Use Case 1.4 · Domain 01
The canonical insurance worked example. Same orchestration as the IT playbook’s knowledge-base pattern, applied to a life-underwriting file. The agent does not issue, decline, or rate. It produces a cited clinical packet a human underwriter can use.
Attending Physician Statements arrive as PDFs, faxes, and portal dumps. An underwriter spends 20–45 minutes per APS extracting diagnoses, dates, medications, unresolved investigations, and contradictions against the application. Backlogs sit in evidence-procurement, not in judgment. The waste is reading, not deciding.
A summarization agent that cites page and source, flags contradictions, and refuses to invent labs is a legitimate production candidate. A summarization agent that writes a rating class is not — that is Use Case 1.5, and it stays human-gated.
| Metric | POC target | Why it matters |
|---|---|---|
| Time-to-first-clinical-packet | < 5 min | The operational win |
| Citation coverage | 100% of findings have page/source | Without this, it is theatre |
| Hallucinated finding rate | 0 on the gold set | An invented finding is a model-risk incident |
| Underwriter accept / minor-edit | ≥ 70% | If they rewrite it, you built a chatbot |
| Escalation rate | 15–30% | Too low means the verifier is asleep |
Four agents, one orchestrator, no write-back to the policy admin system in v1.
APS PDF → Retrieval (page-map, source hashes) → Synthesis (JSON packet + narrative) → Verification (grounding, purpose-limit, prohibited fields) → high confidence: UW workbench (read-only) / else: Escalation (reason codes + immutable trace)
| Agent | Responsibility | Success criteria |
|---|---|---|
| Retrieval | Find the passages that matter | Gold-set recall ≥ 0.9 on diagnosis/med/date entities |
| Synthesis | Packet from retrieved context only | Zero claims without a span; schema-valid |
| Verification | Grounding, safety, purpose-limitation | 100% of findings re-found in chunks |
| Escalation | Human UW queue + trace | Reconstructable six months later |
Prohibited fields on this packet: rating_class, table_rating, decline_reason, issue_decision. If ops asks “can we just auto-issue clean files?”, that is a different system with a different E-23 inventory line — not a new column here.
If the packet would be the sole basis of an automated disposition, Verification must escalate under Law 25 s.12.1. This use case is designed so that never happens: the underwriter still decides.
In: APS with page map, e-App coded impairments, UW-manual excerpts as a retrieval set. Optional labs/Rx/MIB as separately cited channels. Out of the context window: neighbour cases, marketing features, unrelated advisor notes. Purpose: new-business underwriting only. Using the same APS later for persistency is a purpose change — blocked.
One product, one language, PDF APS only, 30-file gold set, read-only packet view. Demo: side-by-side original page highlight, packet finding, verifier pass. If a stakeholder cannot see the span, the POC has failed even if the prose is fluent.
Concrete path: 42-year-old applicant, e-App discloses elevated cholesterol. APS page 3: lipid panel. APS page 9: “follow-up with oncology 2024, records requested.” Synthesis emits hyperlipidemia (page 3) and unresolved oncology (page 9) plus contradiction vs e-App. Escalation routes to UW with reason contradiction — not to a decline engine. That single path is the product. Fluency is not.
This is one of 39 cells. The Radar’s job is to tell you which 13 should not be built as autonomous agents yet — and to hand you this spec for the ones that should.