ModelRefs / Assistant Message — AI Glossary
Assistant Message — AI Glossary
A message in the chat completion format carrying the model's response, which may include text, tool calls, or structured output.
Overview
Assistant messages represent the model's output. When doing few-shot prompting in the chat format, callers can pre-populate assistant messages to prime specific output styles. The assistant message may contain tool_calls (JSON array of function invocations) which the caller must execute and return as tool messages.
Reference details
| Topic | prompting |
|---|---|
| Also known as | model response, model turn |
| Last reviewed | 2026-06-24 |
Related terms
Commonly confused with
The model's turn in the transcript — but nothing stops you writing one yourself. Placing text in an assistant message makes the model continue from it as though it had said it, which is a steering technique rather than a record of what happened. So an assistant message in a request is a claim about the conversation, not evidence of it, and traces should distinguish the two.
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Assistant Message — AI Glossary.
Frequently asked questions
What is Assistant Message?
A message in the chat completion format carrying the model's response, which may include text, tool calls, or structured output.
Is Assistant Message the same as model response?
Yes — model response, model turn are common aliases for Assistant Message.
What concepts are related to Assistant Message?
Closely related concepts include user message, system message, tool definition.