Tag

Strcutured Outputs

25 May 2026

Pydantic as an AI Architecture Boundary

LLM output is not application state until it passes a typed boundary. Schemas, validation errors, evidence fields, and versioned contracts make AI workflows easier to inspect and change.

25 May 2026

The Death of the 1,000-Line Prompt

Giant prompts feel productive at demo stage. In production, workflow logic needs to move into code, schemas, routing, validation, evidence, review, and evaluation.