On LLM Control

A 3-part series on making LLMs produce reliable structured output without fine-tuning.

1. Part 1 of 3

   Schema Design
   10 Nov 2025

   Making LLMs produce reliable JSON - Part 1 of 3. Simple schemas, detailed descriptions, constrained decoding, and why enums beat strings.

2. Part 2 of 3

   When One LLM Isn't Enough
   17 Nov 2025

   Making LLMs produce reliable JSON - Part 2 of 3. Multi-model architectures, writer-critic loops, best-of-N sampling, and the freeform thinker + JSON formatter pattern.

3. Part 3 of 3

   Shipping in Production
   24 Nov 2025

   Making LLMs produce reliable JSON - Part 3 of 3. Temperature tuning, graceful degradation, observability, token caching, jailbreak detection.