Most tokens burned by an AI coding agent are spent on I/O and boilerplate, not reasoning. Here’s how to slash your bill by routing grunt work to a cheaper model while keeping your frontier model for the problems that actually need it.
How to combine Bazel’s hermetic execution model with Buildbuddy’s remote build cache and execution to ship faster, more reliable CI pipelines.
A practical guide to delivering push notifications that the server cannot read, covering Signal’s Double Ratchet, MLS group state, APNs/FCM payload constraints, and the tradeoffs you’ll hit in production.
Most ‘AI engineering’ tutorials stop at a notebook. This post walks through the full production stack — data pipelines, training loops, evaluation harnesses, serving, and observability — so you can build a system that actually ships.
Coding agents spend most of their budget on file and symbol discovery, not on actual reasoning. Here is how precomputed context graphs change that, and why it matters for every team shipping agentic dev tools.