Skip to main content
Runchat can generate output parameters from object keys automatically, so you can define parametric relationships between nodes without parsing objects yourself.

How spread output works

When spread output is on for an Agent or Code node, Runchat reads the node’s output array, finds object items, and creates one output parameter for each key it finds. Each parameter gets the matching value from the object.

Agent node

This is the most common use: get a single LLM call to return several distinct fields, and wire each field into a different downstream node. Open the Agent node’s More (…) menu, set Output format to Custom schema, and define the schema you want the model to return in Output schema. Then choose Spread output from the same menu. The next time the node runs, every key in the structured output becomes its own output parameter. For example, an Agent set up to return:
…will show three output parameters: title, material and area. You can pipe each one into a separate node without parsing the object yourself.

Code node

Press E or click Edit code to open the code editor, then turn on One output per key in the side panel. The next time the node runs, Runchat creates output parameters for each key in the object items returned from your code. This is useful when a Code node fetches structured data from an API or builds a result object from multiple inputs.

Publishing generated outputs

On a Code node, turn on Publish all in the code editor’s side panel to automatically publish every generated output. This is useful when you want every key exposed to downstream workflows or app users without managing each one.

Next steps