Python

Model Routing: Stop Using One Model for Everything

Model Routing: Stop Using One Model for Everything

4 min read

A 70B model summarizing an email burns money; a 3B model reviewing production code courts disaster. Routing matches task complexity to model capability across four strategies — capability, cost, latency, hybrid — each optimizing what hurts most. Production systems converge on hybrid; start there only after one model genuinely fails.

LLM Guardrails in Practice: Control the Risk, Not the Model

LLM Guardrails in Practice: Control the Risk, Not the Model

3 min read

Models hallucinate, leak data, emit harmful content, and refuse legitimate requests. Guardrails constrain behavior without removing capability — but only the guardrails that match real risk earn their latency. The discipline is knowing which ones matter and which are noise.

Multi-Model System Design: The Right Model for the Right Task

Multi-Model System Design: The Right Model for the Right Task

3 min read

Running a 70B model to summarize an email wastes money; running a 3B model to review production code courts disaster. Multi-model design isn’t about collecting models — it’s about architecture that puts the right model on the right task at the right time, with the simplest pattern that survives the constraints.