liveBook · Manning

Working memory

As explained in Designing AI Agents

The limited information temporarily available to an agent or model while it performs a task.

Working memory is the information available in an agent’s context window during a model call: fast, small, and volatile. It can include current instructions, evidence, and tool results; finite token capacity makes context placement an architectural choice. section 4.1.1 section 1.1

Keep frequently needed state near the model; leave durable history and source material outside the context until retrieval justifies their token cost. Moving information closer changes its availability, not its authority: provenance, version, ownership, and invalidation still matter. section 4.1.1

Table 4.1 Dimensions of agent memory
Memory category
Example content
 
Scope
 
Function
 
Lifetime and access
 
Owner or authority
 
Active context
 
Current instructions, evidence, tool results
 
Turn or session
 
Working state
 
Immediate and volatile
 
Runtime plus source owners
 
Task or session state
 
Goal, artifacts, receipts, pending decisions
 
Task or session
 
Resumption
 
Durable until task closure
 
Orchestrator or task owner
 
Project or user context
 
Conventions, preferences, profiles
 
Project, user, or team
 
Continuity
 
Durable, versioned, retrieved on demand
 
Human or system owner
 
Admitted lessons
Scoped guidance with admission evidence
Workload, team, or organization
Governed reuse
Versioned, expiring, supersedable
Admission owner
Archival evidence
Raw traces, prior versions, audit records
Task through organization
Audit and later review
Archived under retention policy
Evidence or records owner

Compare active context with task state, project or user context, admitted lessons, and archival evidence by scope, function, lifetime, and authority. section 4.1.1

How Designing AI Agents covers it

How deep it goes
Distinguishes volatile active context from durable task state and external memory, relating placement to access cost and validity checks.
Examples
Uses current instructions, evidence, and tool results as active context, contrasted with goals, artifacts, and pending decisions in task state.
What you can do after
Apply context-window management by keeping frequently needed state close and retrieving durable history when its token cost is justified.
How it connects
Connects working memory to context windows, token budgets, episodic memory, and semantic memory.

Also explained in

Compare how 11 books explain working memory →

Related concepts

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