Articles

1 published · newest first

all Machine Learning Deep Learning Models GPUs Prompt Engineering Context Engineering Harness Engineering Loop Engineering Semantic Layer Chatbots & Agents Model Switching MCP Servers Workflows Observability

Model Switching

Model Switching and Routing: Use the Smallest Model That Works

One model for everything is the expensive default. Routing tasks to different models by difficulty, cost, and latency is how real systems stay affordable.

Pooja Thirupuranthakam · May 25, 2026 2 min 10