Originally published on bluearch.substack.com ↗
The full post is published on Substack. Continue reading →
Agent systems don't just call an LLM. They call one, chain the output into a tool, call another model, retry on failure, and sometimes loop until a stopping condition fires — or doesn't. Every hop is…
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.
BlueArch