Quality Gates

The pipeline runs three quality checks in parallel after each draft is produced. If any gate fails, the synthesis agent compiles feedback and the writer rewrites the article — up to 3 iterations.

Gate Overview

Gate	Agent	Model	What It Checks
Factuality	Factuality Checker	Haiku	Medical claim accuracy against research dossier
SEO	SEO Optimizer	Haiku	Keyword density, heading structure, meta descriptions
Readability	Style Checker	Haiku	Reading level, tone, clarity

Each gate returns a score and a pass/fail decision. The synthesis agent reconciles all three results and produces rewrite instructions if needed.

Coming soon

Detailed documentation on scoring thresholds, synthesis logic, and the rewrite loop will be added here.