Chapter 8 - Layer 3: Dialog Interface (What the AI Implements)
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. This page collects the AI-side dialog interface material and links the worked transcript. On the human side, CSAR (clarify, summarize, act, reflect) is the matching discipline.
The question this chapter takes up
What does the conversation layer owe the human: clarification, surfaced assumptions, and repair when the two diverge?
Put it to work
Use the dialog worked example to repair one request where the literal ask and the underlying need diverge.
Key sources
Chapter 8 cites in the print book: D11, D35, D37. Entries below are the sources this page draws on; some are related literature cited elsewhere in the book rather than in this chapter.
- D3 - Correa, F. (2024). Dialog Engineering: AI as Your Research Assistant. medium.com/@fabioc/dialog-engineering-ai-as-your-research-assistant-616a625e9853 - the dialog-discipline essay that anchors the human-side counterpart.
- D11 - Willison, S. (2025). Designing agentic loops. simonwillison.net/2025/Sep/30/designing-agentic-loops
- D35 - Tversky, A., and Kahneman, D. (1974). Judgment under uncertainty: Heuristics and biases. doi.org/10.1126/science.185.4157.1124
- D37 - Fleming, S. M., and Lau, H. C. (2014). How to measure metacognition. doi.org/10.3389/fnhum.2014.00443
Primary-source links
- Correa, "Dialog Engineering: AI as Your Research Assistant" (October 2024) - the article that named the discipline and introduced the human-side CSAR protocol.
- Willison, "Designing agentic loops" (2025) - the chapter's epigraph source: "My preferred definition of an LLM agent is something that runs tools in a loop to achieve a goal."
Related resources
A dialog worked example shows a full intent-clarification dialog start to finish, with the repair moves annotated.