> For the complete documentation index, see [llms.txt](https://docs.stackai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stackai.com/guides-and-quickstarts/workflow-builder/configure-models-and-prompts.md).

# Configure models and prompts

An agent node uses a model to process information and produce a response. Choose the model, explain the task in Instructions, and supply the information in Prompt.

{% embed url="<https://files.gitbook.com/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FSQ1Sgy933krTyK0S4JpP%2Fuploads%2FDLMkgYfEMdfmxiK9iO49%2FG021.mp4?alt=media&token=b559253e-0093-4098-915b-4559a9f2541c>" %}

## Supply the input

Enter the information to process in Text Input.

![Text Input supplied to the workflow](https://content.gitbook.com/content/SQ1Sgy933krTyK0S4JpP/blobs/09TVU5ss9tZp9srM0xjK/assets/g021-g021-01-input.png)

This input will be available to the model when you insert its reference in Prompt.

## Choose a model and give it instructions

Open the model selector and choose an available model.

![Available model selection](https://content.gitbook.com/content/SQ1Sgy933krTyK0S4JpP/blobs/019hky0e3qfGD3C92Kbt/assets/g021-g021-02-model.png)

Model availability and supported settings can differ by provider and workspace.

For guidance on Thinking and Reasoning, see [Choosing thinking levels](/guides-and-quickstarts/workflow-builder/configure-models-and-prompts/choosing-thinking-levels.md). Choose a setting for the work inside each agent node, then compare quality, response time, and cost on representative inputs.

In Instructions, describe the task and required response format. Insert the Text Input reference in Prompt.

![Instructions and Text Input prompt reference](https://content.gitbook.com/content/SQ1Sgy933krTyK0S4JpP/blobs/DB3yIs5naPenqwXYGlzV/assets/g021-g021-03-bullets.png)

The reference supplies the current input each time you run the workflow.

## Configure response settings

Open Settings to review Conversation Memory and Answer Format.

![Conversation Memory and Answer Format settings](https://content.gitbook.com/content/SQ1Sgy933krTyK0S4JpP/blobs/N7J3YwqM5DAudVxI2hSu/assets/g021-g021-04-settings.png)

These affect the context available to the model and the structure of its response.

Update the instructions when you need a different response.

![Updated model instructions with the input reference retained](https://content.gitbook.com/content/SQ1Sgy933krTyK0S4JpP/blobs/y49wk5lcUqxrSmSBCT4W/assets/g021-g021-05-sentence.png)

Keep the input reference in Prompt so the model continues to receive the current input.

## Review the output

Inspect Output for both accuracy and format.

![Model output checked for facts and format](https://content.gitbook.com/content/SQ1Sgy933krTyK0S4JpP/blobs/XOuSDvvPQAVpnwh8gPLM/assets/g021-g021-06-result.png)

A response can follow the requested layout while still omitting or changing a source fact.

## Important behavior

Use Instructions for the task and response requirements. Use Prompt for the information to process.

References supply values from the current run. Text typed directly into the prompt stays fixed.

## Related steps

* [First input to output workflow](/guides-and-quickstarts/workflow-builder/first-input-to-output-workflow.md)
* [Structured outputs and templates](/guides-and-quickstarts/workflow-builder/structured-outputs-and-templates.md)
* [Conversation memory](/guides-and-quickstarts/workflow-builder/conversation-memory.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.stackai.com/guides-and-quickstarts/workflow-builder/configure-models-and-prompts.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.