LLM INFRASTRUCTURE
2 items
2 posts
Blog
13.5 Million Copilot Sessions: What Production Coding Agent Traffic Actually Looks LikeA Microsoft Research analysis of 3.2M users and 761M LLM calls shows coding agent traffic is 87% agent-initiated, burns KV cache at turn boundaries, and punishes every tool failure with up to 4x compute.
Blog
Envoy AI Gateway 1.0 Makes LLM Routing an Infrastructure DecisionEnvoy AI Gateway 1.0 is production-ready. The useful question for builders is when an Envoy-based LLM gateway beats direct SDK calls, LiteLLM, OpenRouter, or a hosted AI gateway.
Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever