liveBook · Manning

Sequential planner

As explained in AI Agents in Action

A sequential planner is a planner that organizes and executes actions in an ordered sequence to achieve a goal.

A sequential planner turns a goal into an ordered list of subtasks, executes them one by one, and returns the resulting answer. section 11.3

A typical sequential-planning workflow:

  • Build a planning prompt containing the goal and available functions, usually without conversation history. section 11.3
  • Submit results for LLM evaluation and summarization before returning the final output. section 11.3

How AI Agents in Action covers it

How deep it goes
Explains prompt construction, structured plans, local execution, iteration, and result summarization without detailing every executor implementation.
Examples
Uses a JSON planner, a create_plan function, an execute_plan function, and a for-each special function.
What it assumes
Assumes basic reasoning and plan derivation while introducing planner implementation through prompt engineering.
What you can do after
Build it from scratch with prompt templates, available functions, structured plans, and a local executor.
How it connects
Connects planning with reasoning, prompt engineering, function execution, JSON, LangChain, and Semantic Kernel.
Cover of AI Agents in Action
liveBookmanning.com
Read AI Agents in Action on liveBook Get the book at manning.com

Related concepts

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