All runs
Failedrun_1019Orion Media

Ad-copy moderation — iteration #20

Score ad copy for policy + brand voice violations.

Loop
Ad-copy moderation
Trigger
manual
Rounds
1 / 3
Critic
gemini-2.5-pro
Started
20652d ago

Round 1

Failed26.4s
Claude Code
50
3/6 tests12.9smajor
  • majorbug: Verifier reported failing test case #3.
OpenAI Codex
50
3/6 tests15.6smajor
  • majorbug: Verifier reported failing test case #3.
Local OSS
50
3/6 tests21.4smajor
  • majorbug: Verifier reported failing test case #3.