AI Builder: Smarter Data Linking Across AI Actions & Create Task

/in

We have made significant improvements to how AI Builder links data into AI actions and the Create Task action, enhancing the accuracy and reliability of generated workflows.

Smarter Data Linking Across AI Actions

AI Builder now correctly passes the actual variable or data into action fields, rather than inserting redundant prompts or instructions. Previously, AI Builder would inject a full prompt into an action’s input field (e.g., “Summarise the following text into bullet points…”) instead of simply passing the variable containing the value. As these actions already understand what to do, the additional instructions were unnecessary and sometimes led to unexpected output.

Now, AI Builder cleanly passes just the relevant variable (e.g., {{message.body}}) into each action’s input field, allowing the action to function as intended.

  • AI Summarise — Passes the target variable directly into the input field instead of enclosing it in summarisation instructions.
  • AI Translate — Passes the source text variable seamlessly, without adding translation prompts.
  • AI Intent Detection — Correctly links the content variable for sentiment or intent analysis.
  • AI Decision Maker — Passes the standard value for the content on which the decision needs to be made, resolving an issue where branch names were left empty by AI Builder.

Create Task Action Improvement

The task description field now contains a clear, human-readable task description for the assignee, rather than a prompt instructing the system to create a task.

Before: The description would read something like, “Create a follow-up call task for the new lead.”

After: The description reads, “Follow up with {{contact.name}} to discuss their enquiry and schedule a discovery call.”

This makes the generated task immediately actionable for the person assigned to it.

These enhancements render AI Builder-generated workflows production-ready out of the box, requiring less manual cleanup, resulting in fewer broken automations, and providing a significantly smoother experience from prompt to live workflow.