Chain-of-thought prompting

As explained in Coding with AI

Chain-of-thought prompting is a prompting technique that guides an AI model through a problem using a sequence of intermediate reasoning steps.

Chain-of-thought prompting guides an AI through a complex task as a sequence of smaller, logical steps instead of requesting a single final answer. A useful prompt supplies the problem context, asks what to check first, and continues through decisions or evidence needed for the next step. This approach aims for clearer, more accurate responses while leaving the developer in control of the result. section 9.5.1 section 9.0

Build a chain-of-thought prompt around three working parts:

• Sequential reasoning: divide the problem into manageable steps that can be addressed in order. section 9.5.1
• Contextual awareness: provide enough task-specific information for the model to interpret each step and its constraints. section 9.5.1
• Iterative refinement: evaluate an answer, add new information or corrections, and ask for the next revision. section 9.5.1 section 9.7

Diagnose a Python application in Docker

Rather than asking why an application crashes, lead the investigation: ask whether the container is running with `docker ps -a`; if stopped, ask how to inspect errors with `docker logs`; if running, ask how to enter it and inspect application logs; then verify the Python version, dependencies, and Dockerfile configuration. Each answer determines the next check, turning a vague failure into a testable debugging path. section 9.5.1

Stage an implementation decision

For a caching system, request the cache interface first, an in-memory implementation next, and eviction policies last. For an authentication design, ask for reasoning about JWT versus session-based authentication before requesting code. Staging work this way makes it easier to inspect and revise individual decisions. section 9.6.1 section 9.6.1

Figure 9.6 A chain-of-thought prompt gets the model to reason out a problem like a human would. You break down the problem and experiment with answers until you get the results you desire.

The diagram reinforces the workflow: break down the problem, experiment with answers, and refine until the result is useful. section 9.5.1

How Coding with AI covers it

How deep it goes

Defines sequential reasoning, contextual awareness, and iterative refinement, then demonstrates them with practical prompt sequences.

Examples

Uses Docker failure diagnosis, staged cache construction, and JWT-versus-session authentication decisions.

What it assumes

Assumes engineering fundamentals and familiarity with prompt types while using stepwise prompts to structure complex work.

What you can do after

Apply it to break complex technical tasks into testable steps and refine AI responses iteratively.

How it connects

Connects prompt engineering with recursive prompting, context manipulation, instruction refinement, and output control.

liveBookmanning.com

Read Coding with AI on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Introduction to Generative AI, Second EditionChain-of-thought prompting is a technique that elicits intermediate reasoning steps before a model produces its final answer.
• 

  liveBookmanning.com
  AI Agents in Action, Second Edition
• 

  liveBookmanning.com
  The Art of AI Product DevelopmentChain-of-thought is a prompting technique that elicits an intermediate sequence of reasoning steps before a model produces a final answer.
• 

  liveBookmanning.com
  LLMs in ProductionChain-of-thought prompting encourages a language model to produce or use intermediate reasoning steps before giving a final answer.
• 

  liveBookmanning.com
  WordPress Power Toolkit: Harness AI to build next-level websitesChain-of-thought reasoning is a problem-solving technique in which an AI model generates intermediate reasoning steps before producing a final answer.
• 

  liveBookmanning.com
  Build AI-Enhanced Web AppsA prompting technique that guides a language model through a single sequential reasoning path.
• 

  liveBookmanning.com
  Prompt Engineering in PracticeA reasoning or prompting technique in which a model generates intermediate steps toward an answer.
• 

  liveBookmanning.com
  Grokking AI ApplicationsA prompting technique that asks a language model to express intermediate reasoning steps before presenting a conclusion.
• 

  liveBookmanning.com
  AI Agents and Applications
• 

  liveBookmanning.com
  Generative AI in ActionChain of thought is a prompting technique that decomposes a problem into intermediate reasoning steps before producing an answer.
• 

  liveBookmanning.com
  Sutskever's ListChain-of-thought prompting is a prompting technique that elicits explicit intermediate reasoning steps before a model produces its final answer.
• 

  liveBookmanning.com
  Building Reliable AI SystemsChain-of-thought prompting is a prompting method that elicits explicit intermediate reasoning steps from a model.
• 

  liveBookmanning.com
  Time Series Forecasting Using Foundation ModelsChain-of-thought prompting is a prompting technique that elicits intermediate reasoning steps before a model produces an answer.
• 

  liveBookmanning.com
  Transformers in ActionChain-of-thought prompting guides a language model by providing or eliciting a sequence of intermediate reasoning steps before the final answer.
• 

  liveBookmanning.com
  How Large Language Models WorkA prompting technique that encourages a language model to produce an intermediate sequence of reasoning steps before an answer.
• 

  liveBookmanning.com
  Reinforcement Learning from Human FeedbackA reasoning trace is a sequence of generated textual intermediate steps used while solving a problem before reaching an answer.
• 

  liveBookmanning.com
  Deep Learning with Python, Third EditionA search-based inference approach that explores reasoning in natural language by generating intermediate thought steps before an answer.

Compare how 18 books explain chain-of-thought prompting →

Related concepts

• prompt engineeringkind of · Prompt engineering is the deliberate design and refinement of instructions, context, examples, or other inputs to guide an AI model’s behavior or outputs.
• language modeluses · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.
• multi-step reasoninguses · Multi-step reasoning derives a conclusion, solution, or decision through multiple connected intermediate inferential or problem-solving steps.
• Tree-of-thoughtcontrasts with · Tree-of-thought is a reasoning technique that explores and evaluates multiple branching paths of intermediate reasoning to develop a solution.
• self-consistencyused by · Self-consistency is a technique that generates multiple reasoning paths or responses for the same input and selects or combines results based on their agreement.

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