Research & Evals

Build With Dramatica

Dramatica gives writing what coding already has: a verifier. We do not optimize for a single scalar notion of “good writing.” We define narrative intent as a Storyform specification and measure whether drafts align with that intended meaning.

Use this section to review the technical framing and benchmark-style evaluations.

Who this section is for

• Developers integrating Dramatica or evaluating verifier behavior
• Researchers inspecting structural correctness, alignment, and diversity
• Advanced users who want the technical framing behind narrative validation

Start here

• Technical Note
• Evals Hub
• Verifier Scoring

Three-layer eval model

1. Constraints (compiler errors): does the candidate violate the intended Storyform?
2. Alignment (unit tests): does the candidate express the intended Throughline pressures and Dynamics?
3. Quality and diversity (search): within valid candidates, can we select among distinct strong options?

NOTE

The verifier narrows outputs to meaning-correct candidates. Human creators, editors, or separate style graders choose voice and taste.

Related paths

• Go to Build With Dramatica for the connector and integration route
• Go to Connect Dramatica to ChatGPT (MCP) when you are setting up access rather than reading the research framing