AI Agent Types

TL;DR 

Choose from 6 prebuilt AI agents - Revision Tracker (counts review cycles), Project Coordinator (automates kickoff & subtasks), Missed Deadline (escalates overdue work), Triaging (classifies & routes tasks), Intake (validates request completeness), and Risk (flags delays early) - or build a Custom agent with your own logic, triggers, and actions for unique workflows.

• Overview
• Revision Tracker Agent 
• Project Coordinator Agent 
• Missed Deadline Agent
• Triaging Agent
• Intake Agent
• Risk Agent
• Custom Agent
• Comparison Table
• What’s Next? 

Overview

You can start with six built-in (prebuilt) agents or design your own custom agent to suit unique workflows.

Revision Tracker Agent 1

• Purpose: Track review frequency and improve team visibility into iterative cycles.
• What it does: Monitors task status changes, counts how many times a deliverable re-enters review, and posts an automated summary comment with each cycle.
• Ideal for: Design, content, and QA teams managing multi-stage approval workflows.
• Setup tip: Define the exact trigger statuses that represent a "review" state so counter accuracy remains high.

Project Coordinator Agent 2

• Purpose: Automate new project initialization and stakeholder onboarding.
• What it does: Generates standardized subtask lists, schedules key milestone deadlines, and sends a formal kickoff notification to the designated Customer Success Manager.
• Ideal for: Operations and client services teams launching frequent, template-driven projects.
• Setup tip: Maintain an up-to-date mapping of account owners to ensure kickoff emails reach the correct manager.

Missed Deadline Agent 3

• Purpose: Escalate overdue items instantly to mitigate project delays.
• What it does: Scans active tasks for passed due dates, notifies relevant stakeholders, and attaches contextual details alongside recommended recovery actions.
• Ideal for: Fast-paced project managers handling tight timelines and complex dependencies.
• Setup tip: Set clear notification thresholds (e.g., alert immediately or after a 24-hour grace period) to prevent alert fatigue.

Triaging Agent 4

• Purpose: Classify and route incoming work based on content.
• What it does: Reads new task descriptions, identifies intent, and sets custom field values like priority or category.
• Ideal for: Teams with high volumes of incoming requests.
• Setup tip: Define which custom fields to populate and the classification options.

Intake Agent 5

• Purpose: Validate that new requests contain all required details before work begins.
• What it does: Reviews task descriptions for missing info and posts validation comments.
• Ideal for: Teams that rely on structured request intake.
• Setup tip: Define what "complete" means for your team (e.g., deadline, design link, assignee).

Risk Agent 6

• Purpose: Identify potential project risks early.
• What it does: Scans projects and tasks for overdue or blocked items and posts a summary comment.
• Ideal for: Project managers who want a quick project health check.
• Setup tip: Schedule daily or weekly runs; the agent posts its risk report as a comment automatically.

Custom Agent 7

• Purpose: Build your own intelligent automation tailored to your workflow.
• What it does: You define the role, logic, and triggers; choose actions like posting comments or updating fields.
• Ideal for: Advanced teams that want to automate unique workflows.
• Setup tip: Write a clear prompt describing what the agent should look for, how to decide, and what to do in each case. Test it in the Playground before deploying.

Comparison Table

What’s Next?

Create an AI Agent