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.
Related technical documentation
Review Level (LAM): sufficient supervision, made auditable
How much human review is enough for a task? LexCore turns that judgment into an explicit, auditable dial that drives how many findings escalate to you.
Deliberative governance & anti-sycophancy
Reputation-weighted, commit-reveal aggregation that stops the AI from agreeing with itself — and records dissent instead of hiding it.
Contract review & risk analysis
The core workflow: verified, prioritised findings with citations, a clause heatmap, and visual risk maps.