← Harvey
Something new at Harvey

Rank an opponent's citations so attorneys check the weakest first

You’re the ai / ml engineer. Your team is in the room. Printed Oct 20, 2026.

The fastest citation review path can miss the authority that changes the argument.

Opposing briefs require broad coverage, while filing lawyers need a short queue they can defend reviewing.

Who you’d be doing this for

“The partner asked which citations I’d actually checked, and I had 46 tabs open.”

Yaw Sackey · Litigation Associate

Prepares research and draft responses to opposing briefs for an enterprise law firm.

What is at stake

A lawyer must manually reopen authorities across an opponent’s brief to find citations that do not support the claim. You have to weigh recall of meaningful risks against a queue that attorneys can realistically review.

Why it isn’t already fixed

Every obvious fix costs something else. That’s the part you’d have to decide.

  • recall of risky citations vs. attorney review capacity
  • long-brief coverage vs. usable latency
  • shared platform reuse vs. litigation-specific learning
  • ranked evidence vs. attorney legal judgment

Why Harvey

Citation-grounded research and drafting must support reviewable legal work when attorneys are responsible for checking both their own filings and opposing citations.

Written with these in mind

evaluation-driven ML builderagent systems engineerhigh-stakes AI product engineer

Not your kind of problem? 43 more at Harvey, or browse every organization.

This is the setup. The work is inside.

Running it puts you in the room: the full situation and its constraints, stakeholders who push back in their own words, and the decisions that are yours to make. What you produce becomes a Day One Plan — work you can show someone instead of describing.