liveBook · Manning

Planning

Planning is the process of determining and organizing intended actions or steps toward a goal, often accounting for conditions or constraints.

How 11 Manning books explain it

AI Agents in Action

Sequential planning is the organization of dependent actions into an ordered plan in which later actions follow earlier ones.

How it is used
Coordinates agent actions and tool use to achieve multistep goals, including dependent sequential tasks.
How deep it goes
Walks through prompt construction, JSON plan generation, local execution, evaluation, and feedback, with exercises for comparing sequential and parallel actions.
Examples
Uses a Wikipedia research-and-save assistant and a time-travel reasoning problem to illustrate planning and the need for feedback.
What you can do after
Build it from scratch using a planning prompt and sequential executor, then test and extend it with feedback.

Read how AI Agents in Action explains planning →

Build an AI Agent (From Scratch)

Planning is the construction of an ordered strategy or set of steps for completing a complex task.

How it is used
Directs agents through complex, multistep tasks instead of relying only on reactive tool calls.
How deep it goes
Works through task decomposition, status tracking, whole-plan updates, tool guidance, and replanning decisions.
Examples
Traces a marathon-pace journey to the Moon through research, calculation, task updates, and tool failure recovery.
What you can do after
Build a task-list planning tool from scratch and integrate it into an agent workflow.

Read how Build an AI Agent (From Scratch) explains planning →

AI Agents in Action, Second Edition

Planning is the process of constructing and organizing steps needed to achieve a goal.

How it is used
Coordinates multistep agent work toward higher-level goals through explicit plans and execution loops.
How deep it goes
Distinguishes decomposition from planning and develops a plan-execute-review loop with storage, iteration limits, and replanning.
Examples
Uses a revised San Francisco itinerary and a Python planner-executor with a sequential thinking server.
What you can do after
Apply planning with an MCP sequential thinking server, a checklist, observation review, and bounded execution.

Read how AI Agents in Action, Second Edition explains planning →

The Art of AI Product Development

Online planning is the dynamic generation and revision of an action plan while an agent is executing a task.

How it is used
Uses language-model agents to coordinate multi-step tasks involving tools, decisions, feedback, and changing execution conditions.
How deep it goes
Explains decomposition, reflection, and explicit flows, but stops short of detailed implementation or reliable long-horizon replanning.
Examples
Demonstrates roadmap updates through retrieval, web research, user-feedback analysis, strategic alignment, and subtask reflection.
What you can do after
Evaluate and design agent workflows by balancing adaptive planning against explicit controls for errors, latency, and user disruption.

Read how The Art of AI Product Development explains planning →

Robotics for Programmers

The computation of actions or action sequences that move a robot toward an objective based on state and environmental information.

How it is used
Derives the next action or action sequence from objectives and robot/environment state.
How deep it goes
Defines planning and gives system-level robot examples without detailing specific planning algorithms.
Examples
Uses manipulator motion, quadcopter exploration and landing, fleet task assignment, and a sense-plan-act loop.
What you can do after
Apply planning within a sensing–planning–acting loop for motion, exploration, landing, or fleet coordination.

Read how Robotics for Programmers explains planning →

Investing for Programmers

A planning pattern is an agent architecture in which an agent dynamically constructs and executes a sequence of actions toward a complex goal.

How it is used
Structures AI agents that pursue complex goals through dynamically assembled action sequences.
How deep it goes
Defines planning within a pattern taxonomy but does not detail planning algorithms, representations, or execution mechanics.
Examples
Uses a reference workflow for an AI agent as the main visual artifact.
What you can do after
Evaluate/understand planning as a way to organize agent behavior around ordered actions and complex goals.

Read how Investing for Programmers explains planning →

AI Governance

Planning is the process by which an agent selects and orders actions, tools, constraints, success criteria, and stop conditions to pursue a goal.

How it is used
Maps a goal to ordered actions and tools under constraints, enabling agents to pursue multi-step tasks rather than respond to single prompts.
How deep it goes
Defines steps, constraints, success criteria, stop conditions, replanning triggers, and governance for intermediate artifacts.
Examples
Uses travel rebooking and multi-vehicle insurance claims to illustrate task decomposition and autonomous tool selection.
What you can do after
Apply planning by decomposing a goal, selecting and ordering tools, setting constraints and stop conditions, and responding to failed checks.

Read how AI Governance explains planning →

Build a Multi-Agent System (from Scratch)

Planning is the capability of formulating and revising a sequence of actions or steps toward completing a task.

How it is used
Uses planning to choose actions and tool calls throughout an LLM agent’s task execution.
How deep it goes
Explains initial planning and revision from action results, without detailing planning algorithms.
Examples
Uses a New York City croissant search requiring bakery, price, and rating comparisons.
What you can do after
Evaluate when an agent should revise its plan or end execution based on action results.

Read how Build a Multi-Agent System (from Scratch) explains planning →

Spring AI in Action

Agent planning is the capability of selecting a path through available actions to achieve a desired goal.

How it is used
Uses dynamic action selection to achieve goals without a predetermined workflow.
How deep it goes
Demonstrates planning through execution traces rather than formal planning algorithms.
Examples
Uses Azul questions about player count and game mechanics to show different action paths.
What you can do after
Evaluate an agent’s autonomy by observing which actions it selects for a goal.

Read how Spring AI in Action explains planning →

Retrieval Augmented Generation, The Foundational Ideas

Planning is an agentic workflow pattern in which a system constructs an action sequence before or during task execution.

How it is used
Decomposes multi-hop questions before retrieval when one pass cannot gather the complete evidence.
How deep it goes
Explains decomposition, independent retrieval, synthesis, and contrast with fixed query expansion, but not implementation internals.
Examples
Uses claims-processing documentation, external auto-insurance benchmarks, and independently retrieved sub-queries as the central example.
What you can do after
Apply planning to split complex questions, retrieve evidence per sub-query, and synthesize a multi-source answer.

Read how Retrieval Augmented Generation, The Foundational Ideas explains planning →

Designing AI Agents

An agent capability for decomposing goals and selecting an intended sequence of steps toward achieving them.

How it is used
Distinguishes dependent planning from structural checks and semantic review when selecting mechanisms for an architecture.
How deep it goes
Names planning as a distinct mechanism need but does not detail its procedure or implementation.

Read how Designing AI Agents explains planning →

Also covered in

What to know first

Related concepts

Questions about planning

What is planning?

Planning is the process of determining and organizing intended actions or steps toward a goal, often accounting for conditions or constraints.

Which Manning books explain planning?

AI Agents in Action, Build an AI Agent (From Scratch), AI Agents in Action, Second Edition, The Art of AI Product Development, Robotics for Programmers, Investing for Programmers, AI Governance, Build a Multi-Agent System (from Scratch) and 3 more.

What should I know before learning planning?

Manning books that teach planning usually introduce language model, AI agent, similarity search and contract first.

What kinds of planning are there?

Kinds of planning include financial planning, long-term planning and production planning.

What is planning a kind of?

Planning is a kind of AI agent. An AI agent is a computational system that uses artificial intelligence to interpret information and select or perform actions toward goals while interacting with an environment.

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.