liveBook · Manning

Context management

Context management is the deliberate control of information or resources available and maintained within an execution or interaction.

How 3 Manning books explain it

Context Engineering

Context management is the shaping of context through selecting, writing, compressing, and isolating information before model consumption.

How it is used
Shapes the working context for individual LLM calls within a broader context engineering pipeline.
How deep it goes
Defines four complementary operations and their resource constraints, then illustrates implementations in coding agents.
Examples
Illustrates context editing and memory in Claude, project instructions and compaction in OpenCode, and repository maps in Aider.
What you can do after
Operate and configure OpenCode context inputs using instruction sources and targeted file inclusion.

Read how Context Engineering explains context management →

Coding with AI

Context management is the deliberate organization of codebase information and prompts so an AI system receives relevant context for producing useful outputs.

How it is used
Improves AI-assisted coding by supplying focused project information for generation, debugging, and multi-file workflows.
How deep it goes
Explains context sources, selection rationale, and prompt specificity, then demonstrates them through a SQLite implementation.
Examples
Uses Cursor context sources and a Blackbox AI Python example that connects to data/questions.db.
What you can do after
Apply it via Cursor or Blackbox AI to formulate focused prompts and integrate generated code after review.

Read how Coding with AI explains context management →

Effective Conversational AI

The ongoing process of tracking, retaining, updating, and applying conversational context as an interaction progresses.

How it is used
Keeps virtual-assistant responses coherent, relevant, and personalized as conversations and user needs change.
How deep it goes
Explains state updates, contextual cues, changing preferences, feedback loops, and RAG integration without implementation-level detail.
Examples
Uses a travel recommendation exchange in which a preference shifts from budget options to luxury accommodations.
What you can do after
Apply dynamic context management to adapt assistant responses, recommendations, and retrieved information as interactions evolve.

Read how Effective Conversational AI explains context management →

Also covered in

What to know first

Related concepts

Questions about context management

What is context management?

Context management is the deliberate control of information or resources available and maintained within an execution or interaction.

Which Manning books explain context management?

Context Engineering, Coding with AI and Effective Conversational AI.

What should I know before learning context management?

Manning books that teach context management usually introduce conversational ai, language model, workflow and dependency graph first.

What is context management part of?

Context management is part of context engineering stack. A context engineering stack is a conceptual organization of the core and harness components involved in building context-aware AI systems.

What are the parts of context management?

Context management includes memory management model and compaction.

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.