Data Hatch
An agentic system that reads, validates, and adjudicates healthcare claims. Routine claims settle in minutes; complex ones reach handlers with the evidence already assembled.
Dashed figures are placeholders pending confirmed engagement data.
Claims arrived as PDFs, emails, and scanned post. Each one was read, cross-checked across several systems, and decided by hand: days per claim, inconsistent outcomes, and a backlog that tied up senior handlers on routine work.
The trust needed routine claims to move without human touches, and complex ones to reach the right person with context attached.
An LLM extraction layer parses every incoming document into a structured claim record.
Cross-checked against membership, coverage, and tariff schedules. Missing information is requested automatically.
Each claim is scored for anomalies, tariff variance, and complexity. Every score is explainable.
Claims within thresholds set by the trust settle automatically: decision, rationale, and payment instruction drafted by the agent.
Flagged claims reach the right handler with evidence, risk profile, and a draft assessment attached. No claim arrives cold.
Every step is logged as it happens, to IG standards. Handler overrides feed back into the models.
Handlers only see claims that need judgement.
Routine claims settle with zero handler touches.
Down from days per claim.
Handler time shifts to complex cases.
Cleared during rollout.
Written at decision time, not reconstructed after.
Every score and settlement carries a rationale.
Dashed figures are placeholders pending confirmed engagement data.