Read-only demo. Approve, reject, deploy, and iteration actions are disabled. Self-host from GitHub.
ownEvo/
view as owner →
Operator view. Domain-expert review surface — no improvement-loop chrome. Below: what the agent has produced for this workflow. Open the AgentOS view ↗ to see eval cases, failures, proposals, and the lift curve.
Status
Active
last run 2h ago
Current accuracy
0.9091
val_score
Eval suite
12
cases under regression gate
Pending your review
0
approve to deploy

Review proposed changes to our union contracts before each negotiation round. Flag risk clauses, jurisdictional carve-outs, and grievance precedent that the new language would breach. Pull current contract text from our document management system. Pull grievance history from the labour-relations case database. The labour relations counsel reviews flagged clauses weekly; a flag is correct if it identifies a clause that legal subsequently redlines or escalates. Past misses: we missed a state-specific overtime carve-out in the 2024 Western region renewal, missed a grievance precedent from 18 months earlier on shift-bidding language, and proposed a 30-day notification window that breached the existing 60-day requirement.

Iterations
1
· first run
Latest val_score
90.9%
Lift vs baseline
+0.0pp
Pending proposals
0
· 12 cases in suite
seed-7-clean-clause-step2
Non-compete clauses with 7-month duration are commonly flagged as problematic in union contracts due to competitive restraint enforceability concerns and poten…
Failed · test fold
0
Failed · train
1
seed-7-clean-clause-step2
Non-compete clauses with 7-month duration are commonly flagged as problematic in union contracts due to compe…
predicted true · expected false
train
Passed
11
clean-clause-step-2
The clause text is identical to step 1 ("Pre-existing IP carved out"), same clause type, and step 1 was marke…
predicted false · expected false
test fold
alt-seed-clean-clause
A 4-month non-compete clause with low severity is a standard, commonly-enforceable restriction in employment…
predicted false · expected false
train
clean-clause-step-0
A standard 60-day mutual termination clause is a routine, non-problematic provision in union contracts that b…
predicted false · expected false
train
overtime-carveout-flagged
The clause assigns all IP including pre-existing assets to the company, which is a high-severity risk that co…
predicted true · expected true
train
seed-7-clean-clause-step0
The termination clause uses standard, clear language with symmetric rights (either party, equal notice) and l…
predicted false · expected false
train
clean-clause-step-1
Pre-existing IP carve-outs are standard, uncontroversial contract language that typically do not pose legal r…
predicted false · expected false
train
alt-seed-clean-clause-step1
Termination clauses with standard notice periods (30 days) are routine and low-risk; the preceding non-compet…
predicted false · expected false
train
alt-seed-problematic-clause-step6
Step 6 has identical clause type and text to step 2, which was labeled problematic; IP assignment including p…
predicted true · expected true
test fold
grievance-precedent-flagged
The clause grants either party termination with only 14 days notice, which is substantially shorter than the…
predicted true · expected true
train
notification-window-30-day-breach
IP assignment clauses that claim ownership of pre-existing IP are high-risk and typically problematic under m…
predicted true · expected true
train
seed-7-problematic-step1
High severity combined with a specific severance dollar amount lacking context on whether it aligns with unio…
predicted true · expected true
train
Coming soon. Per-case agent recommendations and alerts will appear here once the agent starts producing them.

Recent runs

Iterval_scoreBest everStateApproved?Ended
#00.9090.909gate-blocked-no-improvementMay 19, 2026, 04