Human Gates and the triage worklist
Keeping a lawyer in the loop without burying them: what escalates, and how the rest is ranked by risk and materiality.
Human Gates are checkpoints where a finding needs a lawyer's sign-off before it counts as accepted. The Review Level and governance escalations decide which findings hit a gate. Low-confidence, high-risk, contested and absence findings all go to a human.
A thorough review can still produce 20 or more cards. Instead of listing them in backend order, triage ranks the verified findings by risk × materiality (not raw confidence), removes near-identical findings raised by different agents, and puts a short "what needs your judgment" list at the top. Every ranking decision is explained, so the worklist can be audited too.
Note
This is the fix for "the AI made me review everything anyway". Your review time goes to the findings that matter.
Related documentation
Review Level (LAM): sufficient supervision, made auditable
How much human review is enough for a task? LexCore turns that judgment into an explicit setting, recorded for audit, that decides how many findings escalate to you.
Deliberative governance and anti-sycophancy
Reputation-weighted, commit-reveal aggregation that stops the AI agreeing with itself, and records dissent instead of hiding it.
Contract review and risk analysis
The core workflow: verified, prioritised findings with citations, a clause heatmap, and visual risk maps.