Placeholder chapter page. Sections are produced by the book-skills pipeline.
Sections
- 22.1 From single-shot inference to agentic sensing loops
- 22.2 Anomaly explanation and root-cause reasoning with LLMs
- 22.3 Log/telemetry reasoning and industrial copilots (Argos, AgentFM, CALM)
- 22.4 Tool use: agents that call detectors, filters, and forecasters
- 22.5 Multi-agent recursion-of-thought for RCA
- 22.6 Guardrails, calibrated confidence, and human-in-the-loop
- 22.7 Cost, latency, and reliability of agentic pipelines
Lab 22
build an agent that monitors a sensor stream, invokes a detector tool, and produces an explained, uncertainty-tagged alert.