Glossary

Every concept in this sheet, plus the smaller terms it uses. Select a concept to open its card.

Agent loop: A loop in your code: send the conversation and tool list to the model, run any tool calls it returns, append the results, and call the model again until it answers without a tool call or a limit is hit.
Augmented LLM: A language model given three extras by your code: tools it can call, retrieval that brings in relevant documents, and memory that carries facts between calls.

Ground truth from the environment: Real results from the world, such as test output, an API response or a database row, that the agent reads after each action to judge whether it is on track.

Keeping tool results small: Return only what the model needs to decide the next step: a few relevant fields, a page of results with a way to get more, and readable ids instead of raw internal dumps.

Parallel tool calls: One model turn can contain several tool calls.
Provider differences in tool calling: Every major provider has the same loop with different field names.

ReAct pattern: The idea, from a 2022 research paper, that a model alternates between reasoning about what to do, taking an action with a tool and observing the result before reasoning again.

Tool call and tool result: The model replies with a tool call carrying an id, a tool name and JSON arguments.
Tool choice: A request setting that lets the model decide freely (auto), forces a tool call (any or required, or one named tool), or blocks tools (none).
Tool definition: A name, a description and a JSON Schema for the arguments, sent with every request.
Tool errors the model can act on: When a tool fails, return a result marked as an error with a short message saying what went wrong and what to try instead, rather than throwing and crashing the loop.

When not to use an agent: A quick test before building: is the task multi-step and hard to specify in advance, is the outcome worth extra cost and latency, can a model do it, and can mistakes be caught and undone?
Workflow vs agent: In a workflow your code decides the steps and the model fills in parts of a fixed path.
Writing tool descriptions: Describe each tool as you would for a new teammate: what it does, when to use it, when not to, what it returns and any limits.