§ Field notes · File 03
Notes from inside the work.
Short dispatches on AI systems, automation, and FPV. Written while the systems are still running, not after the fact.
Short dispatches on AI systems, automation, and FPV. Written while the systems are still running, not after the fact.
Four checks in two days that were structurally incapable of reporting a problem. One habit behind all of them, and the question I now ask before calling anything verified.
Anthropic dropped a new model today. I threw a full site review at it and told it to use as many agents as it needed. 62 agents, adversarial verification, 52 confirmed findings, one session.
A field note on what changed after moving more daily work through Hermes: control surfaces, verification, memory, and the parts that still feel too manual.
What I kept from ClawSweeper was the product shape: local evidence, explicit proposals, stable hashes, and a human apply boundary.
A Windrose server went live on a Windows 11 VM the same hour a friend asked, then stabilized through practical AI-assisted operations.
Why the useful AI stack is the surface around delegation, verification, memory, and deployment, not just the model choice.
Frontend generation is useful when it produces artifacts, evidence, and reviewable winner bundles, not silent production patches.
Persistent memory helps only when it reduces repeated steering without becoming a second, fuzzier source of truth.
Status, crawlability, deployment freshness, screenshots, and the regressions users actually feel.
A layered multi-agent system with 8 agents, local LLMs on Ollama, and Claude as orchestrator. Research, review, and QA, 24/7.