DEMO / RECORDING
Overview & Result
Raph Guilhem demonstrates a marketing pipeline combining Opus 5.5, Jev and Pletor. The author reports scoring 120 ads from 12 competitors on seven criteria, then having code select 10 to adapt. Opus builds the pipeline, Jev makes ad judgments, and Pletor MCP creates variants. These counts and results are author-reported.
How Jev fits in the loop
- The author reports using Opus to find competitors and build the pipeline with Pletor’s Meta ads workflow.
- Jev judges hook, clarity, message, concept fit, tone, angle and health-claim risk.
- Code combines the scores and selects candidates; Pletor MCP creates adapted versions.
How to reproduce
- Watch the original video and read the seven scoring criteria.
- No matching public source repository is linked. The post names Pletor as a component, not as the source code for this case.
- For a similar workflow, manually review the chosen ads and claims before using its recommendations.
Why this build matters
Separates ad selection from content generation so a marketer can inspect the criteria behind a shortlist.
Limitations
- The 120-ad, 12-competitor and 10-shortlist figures have not been independently verified.
- Model judgments do not establish advertising effectiveness or validate health claims.