desktop

Navigate

Overview DesktopBench Leaderboard RL Envs Evaluation
Main site Evals Blog Dashboard
expansion candidate

LegalOps-200

Legal desktop workflows across contract upload, clause tagging, signature requests, matter updates, risk flags, obligations, and renewal tracking.

Task families

20 families x 10 variants

ContractUploadClauseTagNDAReviewMatterCreateMatterUpdateSignatureRequestDeadlineAddCounterpartyUpdateRiskFlagPlaybookCheckRedlineCompareObligationExtractRenewalTrackLegalIntakeTriageDocumentRenameFolderOrganizeApprovalRouteTemplateGenerateComplianceChecklistExportMatterReport
Target UIs

Mock apps for resettable rollouts

Contract management mock

DocuSign-like signing flow

Legal intake portal

Matter management mock

Examples

Representative task contracts

Example 1

LegalOps.SignatureRequest.001

Instruction
Send Vendor Agreement - Mirae Foods for signature to legal@mirae.example.
Grader
signature request exists for target document and recipient == legal@mirae.example
Example 2

LegalOps.RiskFlag.001

Instruction
Open Cloud Services Agreement and flag it as High Risk because liability is uncapped.
Grader
contract.risk == High and risk_reason contains uncapped liability
Example 3

LegalOps.RenewalTrack.001

Instruction
Add a renewal reminder 30 days before the expiration date of Office Lease 2026.
Grader
reminder.date == contract.expiration_date - 30 days
Verifier

Suite-level verifier shape

Matter DB checks, document metadata, clause tags, deadline records, signature routing, and risk flag state.

On this page

  • Summary
  • Task families
  • Examples
  • Verifier

Help improve UseDesktop

Optional analytics help us learn which pages are useful. They stay off unless you accept.

Privacy