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.
"Review Level" is LexCore's implementation of the Lawyer Analysis Metric (LAM): how much human review counts as *sufficient* supervision of AI for a given task. At one end you review everything, which is safe but saves no time. At the other you review nothing, which is sanctionable. The right point depends on the task and the risk.
| Review Level | Typical task | Effect |
|---|---|---|
| Low | Routine extraction, defined-term pulls | High auto-pass; few escalations |
| Moderate | Standard contract review | Balanced; the default |
| High | Unusual clauses, liability, novel risk | Low auto-pass; more findings escalate |
| Highest | Deal-critical, strategy | Almost everything reaches a lawyer |
The level sets the confidence bar a finding must clear to auto-pass. The higher the level, the more findings escalate to a Human Gate. Every review records the level it used, so a judgment call becomes a record you can defend.
What LAM is not
Review Level is a supervision policy and a record. It is not a guarantee of correctness. A finding that auto-passes is only as trustworthy as its CitationGate-verified grounding. The settings are policy, and they can be calibrated against measured accuracy over time.
Related documentation
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.
CitationGate: grounding every finding
A finding with no verifiable quote is rejected, and a quote that doesn't match the source is dropped. This is what makes LexCore's output traceable.
Data sovereignty and model routing
How the model router keeps a sovereign tenant's documents away from third-party model providers, and why where your analytics go is a separate question with its own control.