The setting
is an AI platform for legal work, used by law firms and the legal teams of companies. is its software that uses AI agents to draft, negotiate, review, and manage contracts.
The original review histories disappear before every converted finding can be checked.
Keeping negotiations interactive protects lawyer continuity, while withholding uncertain histories protects the meaning of a verified review.
Who you’d be doing this for
“I clicked the evidence beside an edit I'd checked yesterday, and it opened the draft we rejected.”
Kerem Aksoy · Senior Commercial Counsel · a character in this brief
Negotiates supplier agreements and must explain which proposed edits received legal review.
What is at stake
Lawyers could lose usable histories for 1,200 active contract reviews in 48 hours. You must weigh continuity in live negotiations against carrying uncertain verification claims past an irreversible cutover.
Why it isn’t already fixed
Every obvious fix costs something else. That’s the part you’d have to decide.
- negotiation continuity vs reliable verification states
- security deadline vs confidence from further testing
- interactive histories vs bounded read-only evidence
- broad availability vs repeated lawyer inspection
Why Harvey
Harvey for Word puts agent-generated edits and their supporting evidence inside the document lawyers are preparing to send.
Written with these in mind
Not your kind of problem? 52 more at Harvey, or browse every organization.
Where the organization context comes fromThe postings this brief was written from, and the reporting read before it.
The organization context comes from public information. The situation and characters are written for the brief.
Job postings it was written from
Public descriptions of the work at Harvey. They are listed as sources, not as openings. The lines under a posting are its own words, where it meets this brief.
- Senior Product Manager, Embedded Experiences (opens in a new tab)
- You'll take a product customers already love and rely on to many more lawyers, make Harvey's agents useful for complex drafting and review work, and help bring Harvey to new surfaces.
- Own key embedded experiences in Harvey: Define the vision, strategy, and roadmap for Harvey for Word and the other drafting tools lawyers work in, taking problems from discovery through launch and iteration.
- Staff Product Manager, Agents (opens in a new tab)
- Build experiences that help users edit, refine, and verify AI-generated work, making it easy to inspect supporting evidence and identify what needs closer review.
- Staff Product Manager (opens in a new tab)
- API Product Lead (opens in a new tab)
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.
Where similar work appears
Other live briefs connected to this one, and what connects them.
Similar problems at other organizations
Like this one, each of these is about an irreversible change forced by a fixed date.
Conflicting injury entities are appearing across matters headed into a permanent migration.
You must weigh a firm’s implementation deadline against source-level trust in facts attorneys will use.
Rehearsal found mismatches in 0.18% of converted files, and automated checks turned up anomalies that reviewers can't yet classify.
You have to weigh the committed date against defects that get costly after teams build on them.
37% of policy families still have no approved owner or retention mapping, and the old contract ends on a fixed date.
You have to weigh audit-proof structure against a system frontline teams will actually use.
The same setting, from another role
Each is set around Harvey’s Contracts, written for a different role. They’re separate briefs, not the same scenario.
Discovery details from Gong and Salesforce conflict on active enterprise opportunities.
You have to decide where the system's drafted fields and next steps hand over to the seller, so the record that reaches a proposal matches what legal, procurement and finance discussed.
Legal sponsors want to evaluate contract review, but procurement cannot see a bounded path to a budget decision.
You have to weigh a simpler commercial entry point against enough evidence to earn conversion.
A procurement committee will decide whether a 250-review monthly commitment is credible after counsel questioned proposed redlines.
You must weigh a controlled rollout against the contract volume Finance needs to approve spend.
Other problems with a similar purpose
In each of these, as in this one, the aim is to build machine-learning systems that earn trust by staying explainable where their errors carry real consequences.
An audit found sensitive fields in 7% of shared artifacts that manual review missed, and the classifiers disagree on the edge cases.
You have to build evidence for a production commitment you cannot easily reverse.
One threshold sends very different numbers of drivers into coaching in each region, and reviewers there agree less often.
You have to balance fair treatment of drivers against enough coverage to improve coaching.
Confirmed takeover messages are reaching guests, while legitimate pre-check-in threads are also being blocked.
You must weigh fraud prevention against a guest losing the instructions needed to enter a booked stay.
