Agents & tools · Glossary term
What is Agent?
A software system that lets a model select actions toward a goal, observe tool or environment results, and continue under an orchestration policy. An agent may use a loop, a state machine, a workflow engine, or human approvals. The model is one component, not the entire system.
“An autonomous model that thinks and acts alone.”
Why does Agent matter?
Reliability comes from the harness, tool contracts, state, permissions, and verification around the model.
Agent in practice
A coding agent reads repository context, proposes a patch, runs tests in a sandbox, and stops for approval before deployment.
What is the common confusion about Agent?
Autonomy is a degree of delegated authority, not a required property of every agent.
Learn Agent in the course
Start with
- The Agent Loop: Observe, Think, Act
Every agent in 2026 is a variant of the ReAct loop from 2022 — Claude Code, Cursor, Devin, Operator included. Reasoning tokens interleave with tool calls and observations until a stop condition fires.
Lessons that name Agent in a title or section
- Chatbots — Rule-Based to Neural to LLM Agents
ELIZA replied with pattern matches. DialogFlow mapped intents. GPT answered from weights. Claude runs tools and verifies. Each era solved the previous one's worst failure.
- 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.
- Agent Framework Tradeoffs — Graph, Role, and Actor Orchestration
Every framework sells the same demo (research agent builds a report) and hides the same bug (state schema fights with the orchestration layer).
- Multimodal Agents and Computer-Use (Capstone)
The 2026 frontier product is a multimodal agent that reads screenshots, clicks buttons, navigates web UIs, fills forms, and completes workflows end-to-end.
- The Tool Interface — Why Agents Need Structured I/O
A language model produces tokens. A program takes actions. The gap between those two is the tool interface: a contract that lets the model request an action and the host execute it.
- Agent Skills: Portable Contract and Runtime Boundary
A skill is not a long prompt with a better filename. It is a discoverable package of instructions, resources, and executable helpers that enters an agent's context through a runtime contract.
- Agent Memory — Virtual Context and Memory Paging
Context windows are finite. Conversations, documents, and tool traces are not. The fix is OS virtual memory restated — main context is RAM, external store is disk, the agent pages between them.
- The Actor Model for Agents — Async Messages and Typed Runtimes
Agents as actors: async message exchange, event-driven handlers, fault isolation, natural concurrency. AutoGen v0.4 (Microsoft Research, Jan 2025) redesigned agent orchestration around this model;…
Taught in Phase 14: Agent Engineering.
Also covered in Phase 04: Computer Vision, Phase 05: NLP: Foundations to Advanced, Phase 11: LLM Engineering, Phase 12: Multimodal AI, Phase 13: Tools & Protocols, Phase 15: Autonomous Systems, Phase 16: Multi-Agent & Swarms, Phase 18: Ethics, Safety & Alignment and Phase 19: Capstone Projects.
Related terms
- Agent HarnessThe runtime around a model that assembles context, exposes tools, manages state, enforces limits, records traces, and decides when the…
- Agent StateThe explicit data an agent carries across steps, such as the current objective, completed actions, tool results, open questions, budgets,…
- Tool ContractThe complete agreement for a tool boundary: purpose, typed inputs, outputs, validation, permissions, side effects, errors, timeouts,…
- Human-in-the-Loop (HITL)A workflow design in which a person supplies judgment, correction, approval, or escalation at defined points in an AI-driven process.
- Function CallingA provider or application interface through which a model emits a structured request naming a tool and its arguments.
- ReActAn agent pattern that interleaves task reasoning, a concrete action, and an observation returned by the environment before deciding the…
- SwarmA loosely coordinated multi-agent pattern in which local agent decisions and message exchange produce system-level behavior.
More terms in Agents & tools
- Agent Harness
- Agent Memory
- Agent State
- Agent Skill
- Approval Gate
- Checkpoint
- Compensating Action
- Delegation
- Durable Execution
- Function Calling
- Human-in-the-Loop (HITL)
- MCP (Model Context Protocol)
- Multi Round-Trip Request (MRTR)
- Orchestration
- Planning
- ReAct
- Sandbox
- Skill Bundle
- Skill Catalog
- Skill Discovery
- Skill Invocation
- Stateless MCP
- Structured Output
- Swarm
- Termination Condition
- Tool Contract
This entry comes from glossary/terms.md on GitHub. Browse all 250 glossary terms.