The Trust Model4 min read

Human Gates & the triage worklist

Keeping a lawyer in the loop without drowning them: what escalates, and how the survivors are ranked by risk and materiality.

Human Gates are the checkpoints where a finding requires a lawyer's sign-off before it counts as accepted. Which findings hit a gate is driven by the Review Level and by governance escalations — low-confidence, high-risk, contested, and absence findings all route to a human.

A thorough review can still hand you 20+ cards. Rather than dumping them in backend order, triage ranks the verified findings by risk × materiality (not raw confidence), de-duplicates near-identical findings raised by different agents, and surfaces a short "what needs your judgment" lead list. Every ranking decision is explained, so the worklist is itself auditable.

Note

This is the antidote to the "the AI made me review everything anyway" failure — supervision is targeted at what actually matters.

Verification Guarantee: LexCore rejects any AI assertion it cannot mathematically trace to character offsets within the source agreement. It serves as a mechanical review assistant and does not constitute formal legal advice. For technical architecture details, see the Security & Trust Center.