About AI Agents
TL;DR:
Wrike AI Agents are intelligent assistants that monitor your projects, analyze context, and automate tasks like detecting risks, classifying requests, routing work, sending Slack/email notifications, and managing approvals. They work in two phases (Watcher and Do-er) and operate at the space level. Requires Space admin permissions, a signed AI Addendum, and Generative AI enabled. Response time is typically 2–5 seconds.
| Availability: Business, Pinnacle, Apex. ; Unavailability: Free, Team; |
AI Agents in Wrike are intelligent assistants designed to help your team work more efficiently. They monitor your projects, analyze context, and perform actions such as detecting risks, categorizing requests, or validating details. You can choose from prebuilt agents or create custom ones to suit your needs.
Note
AI Agents are currently available only in spaces and can be configured by Space admins.
Important
- AI Agents require the AI Addendum to be signed, as it's powered by Large Language Models, which require your acceptance of the Terms and Conditions.
- If you don't see the AI Agents button, make sure Generative AI is enabled in your settings to access all AI features.
Prerequisites
- Space admin permissions - required to create and configure agents.
- AI Addendum signed - acceptance of the Terms and Conditions.
- Generative AI enabled in your settings.
- AI Agents operate at the space level only.
What Can AI Agents Do?
AI agents bring intelligence and automation to your workflows:
- Intelligent analysis: Read task descriptions, comments, and context to make informed decisions.
- Proactive monitoring: Watch for risks, bottlenecks, and opportunities.
- Smart classification: Organize and route work based on content understanding.
- Quality assurance: Validate incoming requests for completeness.
- External integration: Changes made via the Wrike API also trigger agents, enabling integration with external systems and tools.
- Automatic routing: Move or add work items to folders based on content, field values, or workflow stage.
- Approval management: Start approval flows and manage approvers automatically.
- Email notifications: Send emails via Gmail or Outlook when agents detect changes worth notifying about.
- Slack notifications: Post messages to a Slack channel when agents detect changes worth notifying about.
Agents can post comments, update fields, send emails, post to Slack, and start approvals, usually within seconds of detecting a change.
Beyond the triggered item itself, agents can access additional context:
- Parent item custom fields: The agent can read custom field values from the parent task or project.
- Sibling and subtask items: The agent can see sibling items and subtasks, enabling cross-item reasoning.
- Location context: The agent knows where it sits in the space and account hierarchy.
- User profiles: Job title, department, country, timezone, email, and assigned task count.
- Approval status: Status, description, due date, and approvers.
- Predecessors and successors: Dependency chains with full field access (name, status, workflow, dates).
- Hierarchy traversal with filtering: Query subitems filtered by item type, name, custom fields, status, dates, assignee, or overdue flag.
- Overlap detection: Detects date range conflicts and similar-name matches among subitems.
Example: An agent triggered on a subtask can check the parent project's "Client" field to determine which team should be assigned, without the subtask needing its own Client field.
| Phase | Role |
|---|---|
| Watcher | Monitors spaces, projects, or folders for triggers (like new tasks or field changes). |
| Do-er | Analyzes the situation and takes action - posting comments, updating fields, or notifying teammates. |
Note
Response time is typically 2–5 seconds as the agent thinks through the best next step. Processing may take longer for larger items or when actions are applied in bulk, such as mass assignee changes.