For clients · legal

AI hallucinations in legal briefs

The client needed to keep a human as the final decision-maker (a lawyer certifies every filing under Rule 11 and state bar rules, so citations can’t be automated away) while still speeding the review. I built a stoplight process that lets a paralegal or attorney focus on the passages that carry the most risk instead of re-reading everything. I delivered the proof-of-concept; the client’s development team is building the production version.

Citation validator summary: 51 citations triaged by risk with deep-investigation tiers
The validator’s summary view. 51 citations scored low / moderate / high risk, with the riskiest escalated to a deeper multi-model review tier.
Architecture
  • Human as final decision-maker
  • Multi-LLM architecture
  • Panel design to drive an accuracy number
  • AI escalation: uses low-cost models to assess and spends expensive model calls only where necessary
  • AI triage of technical and regulatory content