
Route LLM calls by cost, not just quality
How intelligent model routing cuts inference spend without sacrificing output accuracy for your workloads.
Read on Substack ↗Cloud economics, tagging, commitment strategy, and self-hosted governance — written by the engineers and operators who actually sign the AWS bill. No vendor fluff, no growth-hack listicles. Just the work.

How intelligent model routing cuts inference spend without sacrificing output accuracy for your workloads.
Read on Substack ↗Every post lives on Substack. Filter by topic above, or read the full archive on the publication.

ASM centralizes skills across Claude, Cursor, Windsurf, and 10+ agents — no more scattered directories.

Pre-indexed knowledge graphs cut tool calls by 70% and keep context local—no model changes required.

Labor, capital, data — and energy. How grid simulation thinking reframes capacity planning and infrastructure cost models.


Join 6,200+ engineers, SREs, and FP&A operators who get our field notes on AWS cost, tagging, and commitment strategy — straight from the people building the control plane.