Key facts
- Use before
- Writing specs, prompts, or review criteria.
- Most confused pair
- State vs memory.
- Highest-risk term
- Tool, because it carries permission.
- Spec rule
- Define terms before granting autonomy.
Terms
An application that can plan, call tools, keep task state, and complete multi-step work with some autonomy.
The repeat cycle where a model selects an action, the application executes it, the result returns, and the model decides what to do next.
A typed capability exposed to the model, such as search, database lookup, file write, code execution, payment, or browser control.
A controlled sequence of steps. A workflow can use LLM calls without giving the model broad autonomy.
State carried across turns or runs. Short-term memory keeps a thread coherent; long-term memory stores durable facts or preferences.
A saved execution state that lets an agent resume after an interruption, review, crash, or long pause.
A policy or validation layer that checks user input, tool calls, retrieved context, or final output.
Human in the loop. A deliberate approval, review, or escalation point before the agent takes a sensitive step.
A controlled delegation from one agent or specialist to another.
Model Context Protocol, a standard for connecting AI applications to external resources, prompts, and tools.
A structured record of model calls, tool calls, decisions, guardrails, cost, latency, and outputs during an agent run.
A test suite that measures whether the agent completes tasks correctly, safely, cheaply, and consistently.
A security failure mode where a model is allowed to perform damaging actions because its permissions or tools are too broad.
The argument contract a model must satisfy before your application runs a tool.
A step implemented in normal code because the desired behavior is known and should not be left to model judgment.
How to use this glossary in a spec
Pick the vocabulary before implementation starts. If the team says "memory," clarify whether that means current conversation state, a saved user preference, a vector store, a database record, or a resumable checkpoint. If the team says "tool," clarify whether it is read-only, writes internal state, contacts a customer, spends money, or calls another agent.
The purpose is not academic precision. The purpose is to remove ambiguity before a model receives permissions. In agent work, unclear words become unclear boundaries.
Sources used
- Agents SDK OpenAI Developer Docs. Accessed 2026-07-06.
Defines agents as applications that plan, call tools, collaborate, and keep state.
- Model Context Protocol Specification Model Context Protocol. Accessed 2026-07-06.
Official specification for resources, prompts, and tools exposed by MCP servers.
- Agents CrewAI. Accessed 2026-07-06.
Defines CrewAI agents as autonomous units with roles, goals, tools, memory, and collaboration.
- Persistence LangChain Docs. Accessed 2026-07-06.
Explains short-term memory through checkpointers and long-term memory through stores.