Bakeoff

Set 4 production pipeline

2 profiles · Jul 17, 2026, 3:53 PM UTC

Profile

set4-prod-1

ready · QA pass
arm baselineexemplar art card emergency-redsource creativeregen 0
set4-prod-1 ↗$0.0694
16,742 in11,256 out$0.0694 cost189.4s workflow wall131.4s LLM call time
StepProvider:modelEffortPrompt variantTokensCostStep wall time
plananthropic:claude-opus-4-8default0 / 0$0.0000226ms
art_directionopenrouter:z-ai/glm-5.2default
theme_emitopenrouter:z-ai/glm-5.2landing5,102 / 9,416$0.0486121.0s
hero_continuationopenrouter:z-ai/glm-5.2default
page_generateanthropic:claude-opus-4-8default
honesty_repairanthropic:claude-opus-4-8default
honesty_judgeopenrouter:anthropic/claude-haiku-4.5default11,640 / 1,840$0.020810.2s
visual_qaopenrouter:anthropic/claude-haiku-4.5default
visual_repairopenrouter:z-ai/glm-5.2default
restyleanthropic:claude-opus-4-8default
Submitted profile JSON
{
  "name": "set4-prod-1",
  "artDirectionCardId": "emergency-red",
  "steps": {
    "theme_emit": {
      "provider": "openrouter",
      "model": "z-ai/glm-5.2",
      "promptVariant": "landing"
    }
  }
}
Resolved run profile
[
  {
    "step": "plan",
    "role": "plan",
    "provider": "anthropic",
    "model": "claude-opus-4-8",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 8192,
    "temperature": 0.2,
    "timeoutMs": 120000
  },
  {
    "step": "art_direction",
    "role": "generation",
    "provider": "openrouter",
    "model": "z-ai/glm-5.2",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 1600,
    "temperature": 0.4,
    "timeoutMs": 90000
  },
  {
    "step": "theme_emit",
    "role": "generation",
    "provider": "openrouter",
    "model": "z-ai/glm-5.2",
    "effort": null,
    "promptVariant": "landing",
    "maxTokens": 20000,
    "temperature": 0.85,
    "timeoutMs": 300000
  },
  {
    "step": "hero_continuation",
    "role": "generation",
    "provider": "openrouter",
    "model": "z-ai/glm-5.2",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 16000,
    "temperature": 0.85,
    "timeoutMs": 300000
  },
  {
    "step": "page_generate",
    "role": "generation",
    "provider": "anthropic",
    "model": "claude-opus-4-8",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 20000,
    "temperature": 0.85,
    "timeoutMs": 300000
  },
  {
    "step": "honesty_repair",
    "role": "generation",
    "provider": "anthropic",
    "model": "claude-opus-4-8",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 20000,
    "temperature": 0.85,
    "timeoutMs": 300000
  },
  {
    "step": "honesty_judge",
    "role": "claims_judge",
    "provider": "openrouter",
    "model": "anthropic/claude-haiku-4.5",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 4096,
    "temperature": 0,
    "timeoutMs": 60000
  },
  {
    "step": "visual_qa",
    "role": "claims_judge",
    "provider": "openrouter",
    "model": "anthropic/claude-haiku-4.5",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 1200,
    "temperature": 0,
    "timeoutMs": 20000
  },
  {
    "step": "visual_repair",
    "role": "generation",
    "provider": "openrouter",
    "model": "z-ai/glm-5.2",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 20000,
    "temperature": 0,
    "timeoutMs": 300000
  },
  {
    "step": "restyle",
    "role": "plan",
    "provider": "anthropic",
    "model": "claude-opus-4-8",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 8192,
    "temperature": 0.2,
    "timeoutMs": 120000
  }
]

result 80fd0d1a-9460-404b-9792-5bbb1c9e8487 job f90be5df-b40e-4105-821f-9b0efbabfde3 site bo-site-80fd0d1a-9460-404b-9792-5bbb1c9e8487

Profile

set4-prod-2

ready · QA pass
arm baselineexemplar art card emergency-redsource creativeregen 0
set4-prod-2 ↗$0.3898
34,824 in21,992 out$0.3898 cost454.5s workflow wall439.3s LLM call time
StepProvider:modelEffortPrompt variantTokensCostStep wall time
plananthropic:claude-opus-4-8default0 / 0$0.0000578ms
art_directionopenrouter:z-ai/glm-5.2default
theme_emitopenrouter:anthropic/claude-opus-4.8, openrouter:z-ai/glm-5.2landing12,927 / 17,793$0.3469415.3s
hero_continuationopenrouter:z-ai/glm-5.2default
page_generateanthropic:claude-opus-4-8default
honesty_repairanthropic:claude-opus-4-8default
honesty_judgeopenrouter:anthropic/claude-haiku-4.5default21,897 / 4,199$0.042923.4s
visual_qaopenrouter:anthropic/claude-haiku-4.5default
visual_repairopenrouter:z-ai/glm-5.2default
restyleanthropic:claude-opus-4-8default
Submitted profile JSON
{
  "name": "set4-prod-2",
  "artDirectionCardId": "emergency-red",
  "steps": {
    "theme_emit": {
      "provider": "openrouter",
      "model": "z-ai/glm-5.2",
      "promptVariant": "landing"
    }
  }
}
Resolved run profile
[
  {
    "step": "plan",
    "role": "plan",
    "provider": "anthropic",
    "model": "claude-opus-4-8",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 8192,
    "temperature": 0.2,
    "timeoutMs": 120000
  },
  {
    "step": "art_direction",
    "role": "generation",
    "provider": "openrouter",
    "model": "z-ai/glm-5.2",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 1600,
    "temperature": 0.4,
    "timeoutMs": 90000
  },
  {
    "step": "theme_emit",
    "role": "generation",
    "provider": "openrouter",
    "model": "z-ai/glm-5.2",
    "effort": null,
    "promptVariant": "landing",
    "maxTokens": 20000,
    "temperature": 0.85,
    "timeoutMs": 300000
  },
  {
    "step": "hero_continuation",
    "role": "generation",
    "provider": "openrouter",
    "model": "z-ai/glm-5.2",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 16000,
    "temperature": 0.85,
    "timeoutMs": 300000
  },
  {
    "step": "page_generate",
    "role": "generation",
    "provider": "anthropic",
    "model": "claude-opus-4-8",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 20000,
    "temperature": 0.85,
    "timeoutMs": 300000
  },
  {
    "step": "honesty_repair",
    "role": "generation",
    "provider": "anthropic",
    "model": "claude-opus-4-8",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 20000,
    "temperature": 0.85,
    "timeoutMs": 300000
  },
  {
    "step": "honesty_judge",
    "role": "claims_judge",
    "provider": "openrouter",
    "model": "anthropic/claude-haiku-4.5",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 4096,
    "temperature": 0,
    "timeoutMs": 60000
  },
  {
    "step": "visual_qa",
    "role": "claims_judge",
    "provider": "openrouter",
    "model": "anthropic/claude-haiku-4.5",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 1200,
    "temperature": 0,
    "timeoutMs": 20000
  },
  {
    "step": "visual_repair",
    "role": "generation",
    "provider": "openrouter",
    "model": "z-ai/glm-5.2",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 20000,
    "temperature": 0,
    "timeoutMs": 300000
  },
  {
    "step": "restyle",
    "role": "plan",
    "provider": "anthropic",
    "model": "claude-opus-4-8",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 8192,
    "temperature": 0.2,
    "timeoutMs": 120000
  }
]

result 188cdc42-f92a-4319-bce4-a3f2ef4d0f4e job e5907549-87cd-40d2-a034-36f4ad153e4a site bo-site-188cdc42-f92a-4319-bce4-a3f2ef4d0f4e

Workflow provenance

Git SHA
unknown-local-build
Captured
Jul 17, 2026, 3:53 PM UTC
  1. startValidate business data; mark the job and bakeoff result running.
  2. pipeline / planBuild the full SEO page plan through the selected plan profile.
  3. pipeline / generateGenerate the homepage theme and scoped pages, repairing or falling back safely.
  4. pipeline / visual QAWhen enabled, render desktop/mobile, run the vision critic, and verify up to two surgical homepage repairs.
  5. pipeline / assembleAssemble raw HTML/CSS/JS with shared SEO, navigation, business facts, and legal pages.
  6. pipeline / auditRun deterministic QA plus the independent honesty judge.
  7. pipeline / writeWrite the validated mutable draft and its source/provenance artifacts to tenant R2.
  8. finishFinalize generation job, site metadata, and page rows in D1.
  9. domainsBest-effort domain candidate discovery used by the real claim path.
  10. bakeoff-finalizeBakeoff-only: publish an immutable preview snapshot and roll up LLM usage.