liveBook · Manning

Chain-of-thought prompting

As explained in The Architecture of Reasoning

A prompting technique that asks a model to produce intermediate reasoning steps before its final answer.

Chain-of-thought prompting asks a model to work through intermediate steps before giving a final answer. Making that pathway visible can expose inconsistencies and assumptions that a compressed answer would leave hidden, especially on complex tasks. section 1.2.1

From symptom to root cause

During an engineering incident, the team first blamed a database after moving directly from symptom to conclusion. Making the reasoning chain explicit showed the database was a downstream victim: a retry configuration change had interacted with a reconciliation job that was not stress-tested under peak conditions. section 3.1

Figure 1.3 This example sequence of reasoning architectures separates expansion from validation. Chain-of-Thought makes assumptions visible, Tree-of-Thought widens the available paths, and Chair-of-Thought examines those paths from different positions. ReAct then introduces disciplined friction by testing the reasoning against evidence. The sequence is illustrative rather than mandatory: the architectures can be selected and combined according to the shape of the problem.

Compare how Chain-of-Thought makes assumptions visible, while other architectures widen, examine, or test reasoning paths. The sequence is illustrative, not mandatory. section 1.2.1

How The Architecture of Reasoning covers it

How deep it goes
Defines the prompting pattern and explains its effects, without giving a prompt template or implementation procedure.
Examples
Uses an engineering incident where retry configuration and peak-load reconciliation—not the database symptom—revealed the root cause.
What you can do after
Understand how exposing intermediate reasoning can surface assumptions and weak links before a conclusion is accepted.
How it connects
Contrasts Chain-of-Thought with Direct Q&A and places it alongside Tree-of-Thought, Chair-of-Thought, and ReAct.

Also explained in

Compare how 29 books explain chain-of-thought prompting →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of The Architecture of Reasoning. The section links point to the parts of the book it draws on.