The full post is published on Substack. Continue reading →
LLM API spend is the new shadow cloud bill. Every tool call your agent makes is metered tokens — context in, completion out — and most of that context is repeated file reads and shell output the mode…
CodeGraph and AgentGateway show how AST-backed knowledge graphs replace grep-and-guess workflows for agentic coding.
Two open-source tools show how separated executor and verifier agents catch what self-review misses.
Two open-source projects turning repos and agent memory into searchable, self-hosted knowledge graphs.
One email a week. Field notes on AWS cost, tagging, and commitment strategy — straight from the people building the control plane.
