AI Concepts category
Agents & Tool Use
Agent Memory
Agent memory is information an agent system retains or retrieves for use across model invocations.
Agent Planning
Agent planning is the decomposition of a goal into intermediate steps or actions before or during execution.
Agent Planning Failure
A flawed plan can lead an agent to the wrong outcome even when its tools work correctly.
Agent Reflection
Agent reflection uses a model to explicitly evaluate earlier outputs, actions, observations, or outcomes before an agent continues or revises its approach.
AI Agent
An AI agent is a system in which a model helps choose actions within an orchestrated execution loop.
Side-Effecting Tool Call
A tool request whose intended behavior can change external state, such as issuing a refund or sending a message.
Tool Calling
Tool calling lets a model request a named operation with structured arguments for an application or runtime to evaluate and execute.
Tool Execution Failure
A selected tool can reject a request, stop partway through, or leave the outcome uncertain.
Tool Selection
An AI system can choose the tool that fits the next step, or continue without one.