Skip to main content

Ask Agent With Structured Output (Automation Action)

Structure the output of agents' replies in your automations.

Updated over a month ago

Overview

Use the Structured Output type when you want extract specific information and use them as variables in you next actions in your automation. This is common used with the Insert Row action or Add Task action to fill up columns in a table.

How to Use It

  • Click ➕Add Step and choose the Ask Agent with Structured Output action.
    ​

  • Select the agent you want to use.

  • Enter the input you want the agent to process.
    ​

  • Click ➕ Add Output to choose the format.
    ​

    • Text
      ​

    • Number
      ​

    • JSON Array
      ​

    • JSON Object
      ​

    • Boolean
      ​

    • Date
      ​

    • Time
      ​

    • Date and Time
      ​

    • URL
      ​

    • Email
      ​

    • Single Select
      ​

  • Add additional output fields to structure your agent's response.

  • Finish the automation or add more steps for further processing.

Action Settings


Connector options give you full control over the Create Project automation:

🏷️ Field

🔤 Description

Agent

The agent that will be used.

Input

The query you want the agent to process.

Output

The structure of the agent's reply.

Use Cases

Not sure how to make the most of this action? Start with these ready-made kits:

You can also build data-driver automation flows yourself:

🪄 Use Case

⏩ Action Flow

AI cost difference calculation

  • ✅ Trigger: Task Added (Est Cost and Act Cost fields)

  • ➡️ Action: Ask Agent With Structured Output

    • Input: “The estimated cost is $500, the actual cost is $650. What is the difference?”

    • Output: Diff Cost (Number)

  • ➡️ Action: Update Custom Field Diff Cost with result

Approval routing based on score

  • ✅ Trigger: Task Added (e.g., budget approval request)

  • ➡️ Action: Ask Agent With Structured Output

    • Input: “Rate feasibility from 0–100."

    • Output: Approval Score (Number)

  • ➡️ If Approval Score > 80 → Mark Task as Completed

  • ➡️ Else → Assign Task to reviewer

Lead qualification

  • ✅ Trigger: Form Trigger (new lead)

  • ➡️ Action: Ask Agent With Structured Output

    • Input: “Is this lead qualified for outreach?”

    • Output: Is Qualified (Boolean)

  • ➡️ If Is Qualified = true → Create Contact in HubSpot

Auto-update project KPIs
​(Dynamic Project Updates)

  • ✅ Trigger: Schedule (daily)

  • ➡️ Action: Find Task(s) tagged metrics

  • ➡️ Action: Transform Array to String

  • ➡️ Action: Ask Agent With Structured Output

    • Input: “Calculate completion rate of tasks."

    • Output: Completion % (Number)

  • ➡️ Action: Update Custom Field → Progress Score

Scorecard automation with spreadsheet logic

  • ✅ Trigger: Task Completed

  • ➡️ Action: Ask Agent With Structured Output

    • Input: “Evaluate task and add performance rating.”

    • Output: Score (Number), Status (Single Select)

  • ➡️ Action: Update custom fields → Score and Status

Sync qualified data to external tools

  • ✅ Trigger: Task Added

  • ➡️ Action: Ask Agent With Structured Output

    • Input: “Extract name, email, lead score (0–100)."

    • Output: Name (Text), Email (Email), Score (Number)

  • ➡️ Action: Insert Row in Google Sheets

😊 Helpful Links

🤖 Taskade AI Essentials

  1. Generate projects with AI

  2. Deploy custom AI Agents

  3. Train AI Agents for any task

  4. Automate your workflows

  5. Create expert AI teams


​

Related Articles
Agent Tool (Automation Trigger)
Add Knowledge to Agent (Automation Action)
Find Task(s) (Automation Action)
Mark Task as Completed (Automation Action)
Ask Agent Team (Automation Action)
Did this answer your question?