Chapter 11 - The Full Sensorimotor Loop
Loop Engineering by Fabio Correa, the Applied AI foundation volume on working with AI through framing, feedback, verification, memory, and human judgment.
Last updated 2026-10-25. Chapter 11 runs every layer at once on one composite task. This page collects the chapter's single cited source, the dated Alex ACT artifacts its handoff discipline builds on, and a pointer to the end-to-end worked examples, which live in the harness assessment section.
The question this chapter takes up
What happens when every layer runs at once, and where does the whole loop break first?
Put it to work
Trace one task end to end through the full loop, naming the handoff at each transition and the check that would catch a failure there.
Key sources
Chapter 11 cites in the print book: D23. Entries below are the sources this page draws on; some are related literature cited elsewhere in the book rather than in this chapter.
- D23 - Runkle, S. (2026, June 16). The Art of Loop Engineering. LangChain. langchain.com/blog/the-art-of-loop-engineering
- D10 - Anthropic. (2024). Building effective AI agents (originally published as Building effective agents). anthropic.com/engineering/building-effective-agents
- D11 - Willison, S. (2025). Designing agentic loops. simonwillison.net/2025/Sep/30/designing-agentic-loops
Primary-source links
- Runkle, "The Art of Loop Engineering" (LangChain, June 16, 2026) - the chapter's cited source [D23]: "an agent is just a model calling tools in a loop until a task is complete."
- Alex ACT commit, April 27, 2026 - the Tenet IX visible-marker conventions, an earlier form of the visible-marker discipline the chapter articulates. (Project home, D1; the book's references give no per-commit URL.)
- Alex ACT HANDOFF.md record, September 3, 2026 - an evidence-carrying handoff instance, with verified counts, timestamps, and rerun warnings. (Project home, D1; the book's references give no direct URL for the record.)
- Anthropic, "Building effective AI agents" - related reading on the multi-step agent pattern behind the sequence diagram.
- Willison, "Designing agentic loops" - related reading on handoff discipline in agentic loops.
- The chapter's sequence diagram is Figure 11.1 in the print book; end-to-end traces of the same handoffs live in the harness assessment worked examples.
Related resources
Use the worked examples to inspect end-to-end traces, including full dialog transcripts, multi-step agent action logs, and the per-layer state captured at each handoff.