Assistant

As explained in Prompt Engineering in Practice

An assistant message is a conversational message representing content generated by the model.

An assistant message contains the model’s generated response, shaped by system instructions, user input, and conversation history. It becomes context for subsequent turns. section 6.1.1

Distinguish assistant messages from the messages you design:

• System messages configure behavior; user messages carry queries, requests, or changing context. section 6.1.1
• Assistant messages are normally generated, but can be manually written as example exchanges for few-shot prompting. section 6.1.2

API troubleshooting

Given a user reporting failing API calls, the assistant asks for the exact error, endpoint, request details, and environment before suggesting likely causes. section 6.1.1

Figure 6.1 Prompt types in a chat conversation: system and user prompts are designed; assistant messages are generated.

The diagram contrasts designed system and user prompts with generated assistant messages. section 6.1.1

How Prompt Engineering in Practice covers it

How deep it goes

Defines the message’s role and demonstrates it in troubleshooting; leaves few-shot prompting for later treatment.

Examples

Uses an API troubleshooting exchange in which the assistant requests diagnostic details before offering likely causes.

What you can do after

Evaluate message placement by distinguishing generated assistant responses from designed system instructions and user inputs.

How it connects

Connects assistant messages with system messages, user messages, conversation history, and few-shot prompting.

liveBookmanning.com

Read Prompt Engineering in Practice on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Spring AI in ActionAn assistant message is a message containing a response generated by a language model.
• 

  liveBookmanning.com
  AI for Everyday ITAn assistant role is a conversational API message role containing the model-generated response to user input.

Compare how 3 books explain assistant →

Related concepts

• few-shot prompt contextused by · Few-shot prompt context is input to a model that includes a small number of examples to guide its response or behavior.
• dialoguepart of · Dialogue is an ordered exchange of related messages across successive turns between participants or an interactive system and its users.
• contextuses · Context is the surrounding information, state, or circumstances that condition how an entity, event, or task is interpreted or how a system behaves.
• system promptconfigured by · A system prompt is a high-priority instruction or context supplied to an AI model to establish its role, task, behavioral guidance, or constraints.

This explainer was generated by Manning's knowledge graph from the text of Prompt Engineering in Practice. The section links point to the parts of the book it draws on.