User Message
The User Message block sends a text message to an AI model and returns the model's response as a string.
Send a message to an AI model and return a response
The User Message block sends a text message to an AI model and returns the model's response as a string. It accepts a message input along with optional configuration for the source, output format, and model settings. When the source is set to "user", the message is forwarded to the configured AI model and the response is captured. When the source is set to "system", the block echoes the message content directly without making an AI call.
What you can build
Real-world workflows powered by the User Message block.
Customer Support Reply Generation
Pass an incoming customer inquiry as the message input to generate a draft response from an AI model, saving the output to a variable for review or delivery.
Structured JSON Data Extraction
Send a prompt with structuredOutputType set to "json" and provide a structuredOutputExample to extract structured data from unstructured text in a consistent format.
Dynamic Content Summarization
Feed article or document text as the message to an AI model and store the summarized response in a destination variable for use in downstream workflow blocks.
System Message Injection
Use the "system" source mode to echo a static or dynamically constructed message into the workflow without triggering an AI model call.
CSV Report Generation
Set structuredOutputType to "csv" and supply a structuredOutputExample to prompt the AI model to return tabular data in a consistent, parseable format.
Model Override Testing
Use the modelOverride parameter to swap in a different model configuration for a specific step, allowing comparison of outputs across models within the same workflow.
Ready to add User Message to your workflow?
Get Started FreeCommon questions about User Message
What are the required parameters for the User Message block?
The only required parameter is "message", which is the text string sent to the AI model or echoed as a system message. All other fields — source, destinationVar, structuredOutputType, structuredOutputExample, and modelOverride — are optional.
What does the block return?
The block returns a single output field called "content", which is a string containing either the AI model's response (when source is "user") or the echoed message text (when source is "system").
What is the difference between the "user" and "system" source options?
Setting source to "user" sends the message to the configured AI model and returns the model's generated response. Setting source to "system" bypasses the AI model entirely and echoes the message content directly as the output.
Can the block return structured output like JSON or CSV?
Yes. The structuredOutputType field accepts "text", "json", or "csv" to constrain the output format. You can also provide a structuredOutputExample string to show the AI model the desired shape of the output.
What kinds of workflows commonly use this block?
This block fits into any workflow that requires generating text from an AI model, including content generation, data extraction, summarization, classification, and dynamic message routing. It can also be used to inject static or computed text into a workflow via the system source mode.
Related capabilities
Generate Image
Generate an image from a text prompt using an AI model.
Generate Video
Generate a video from a text prompt using an AI model.
Generate Chart
Create a chart image using QuickChart (Chart.js) and return the URL.
Text to Speech
Generate an audio file from provided text using a speech model.
Generate Music
Generate an audio file from provided instructions (text) using a music model.
Generate LipSync
Generate a lip sync video from provided audio and image.
Add User Message to your workflow
Build powerful AI workflows with drag-and-drop blocks. No coding required.