Agents & tools · Glossary term

What is Agent State?

The explicit data an agent carries across steps, such as the current objective, completed actions, tool results, open questions, budgets, approvals, and artifact references.

Why does Agent State matter?

Explicit state makes long tasks resumable, inspectable, and less dependent on the model reconstructing progress from a transcript.

Agent State in practice

Store the selected issue, changed files, latest test result, and remaining checks in a typed object that is updated after each action.

What is the common confusion about Agent State?

State is not the same as conversation history. A transcript is evidence; state is the compact operational record used to decide what happens next.

Learn Agent State in the course

Start with

  • Repo Memory and Durable State

    Chat history is volatile. The repo is durable. The workbench stores agent state in versioned files so the next session, the next agent, and the next reviewer all read from the same source of truth.

    Phase 14: Agent Engineering

Lessons that name Agent State in a title or section

  • Agent State Machines — Graphs, Nodes, Checkpoints

    A ReAct loop written by hand is a while True. The same loop written as an explicit graph is something you can checkpoint, interrupt, branch, and time-travel through. The agent hasn't changed.

    Phase 11: LLM Engineering

Taught in Phase 14: Agent Engineering.

Also covered in Phase 11: LLM Engineering.

  • CheckpointA durable snapshot used to resume from a known boundary. In a workflow, it stores operational state and artifact references.
  • Durable ExecutionRunning a workflow so its state and completed steps survive process crashes, restarts, or long waits without redoing confirmed side effects.
  • Context EngineeringDesigning the full information environment supplied to a model at each step, including instructions, selected files, retrieved evidence,…
  • HandoffA structured transfer of a task between people or agents that preserves the objective, current state, evidence, decisions, constraints,…
  • AgentA software system that lets a model select actions toward a goal, observe tool or environment results, and continue under an orchestration…
  • Agent HarnessThe runtime around a model that assembles context, exposes tools, manages state, enforces limits, records traces, and decides when the…
  • Agent MemoryInformation stored outside the model and selected for use in later agent steps, such as prior decisions, user preferences, task episodes,…
  • Context WindowThe maximum token capacity available to one model inference under a specific model and API contract.
  • ObservabilityThe ability to understand an AI system's behavior from recorded inputs, outputs, state transitions, tool calls, timings, costs, errors,…
  • PlanningConstructing, selecting, or revising a sequence of actions and dependencies intended to move from the current state to a goal.
  • SwarmA loosely coordinated multi-agent pattern in which local agent decisions and message exchange produce system-level behavior.
  • TraceA correlated record of one request or task across model calls, retrieval, tools, state transitions, retries, approvals, and evaluations.

More terms in Agents & tools

Open the Agents & tools list in the glossary

This entry comes from glossary/terms.md on GitHub. Browse all 250 glossary terms.