For the complete documentation index, see llms.txt. This page is also available as Markdown.

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.

Supply the input

Enter the information to process in Text Input.

Text Input supplied to the workflow

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

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

For guidance on Thinking and Reasoning, see Choosing thinking levels. 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

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

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

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

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.

Last updated

Was this helpful?