Super Agents
Configurable ClickUp Brain AI agents that run multi-step work across a Workspace after manual, scheduled or Automation triggers, using configured instructions, Skills, knowledge, memory and tools that create and modify persistent ClickUp objects and, where integrated tools are added, act in connected external services.
Recorded characteristics
- Function
- ClickUp documents Super Agents as Brain AI-powered teammates that perform multi-step workflows across the Workspace. A Super Agent is created through a natural-language Super Agent Builder, from the Super Agent catalog, from scratch in the AI Hub, or by asking Brain, and is configured from its profile in five sections: Instructions & Skills (always required; the AI model is selected here), Triggers, Tools, Knowledge and Memory. At runtime a trigger starts the Agent, which follows its primary instructions plus any trigger-specific additional instructions, draws on selected knowledge and activated memory, and runs the tools added to its profile. Super Agent Activity records each run with the tools that were run and, for some actions, the Agent's own explanation of what it did. ClickUp states that if a Super Agent does not have a given toolset, for example the Docs toolset, it cannot perform the corresponding actions.
- Data access
- ClickUp states that Super Agents are required to have access to all public locations and items in the Workspace and automatically receive public Workspace data as it is added. Beyond that, the builder explicitly selects knowledge: Workspace locations and items, certain connected apps, ClickUp's public help articles, and the web. ClickUp states that when a Super Agent is triggered in a private location that was not selected in its knowledge, it has temporary access to that location's data for the duration of that interaction only, while selecting a location in knowledge or granting access in instructions gives persistent access. ClickUp states that if private or external data is shared with a Super Agent, including Personal Lists, the Agent can use that data when responding to anyone who has permission to trigger the Agent, even if they do not have direct access to that data, and that a warning is shown when configuring an Agent where such privacy exposure exists. Adding personal app knowledge or personal-connection tools exposes that connected app's data to anyone who can interact with the Agent.
- Actions
- Can take actions
- External actions
- Conditional
- Human confirmation
- Conditional
- Permission basis
- Mixed
- Administrative control
- ClickUp documents that the AI ClickApp must be activated for the Workspace, and the Chat ClickApp for Chat interaction. Anyone with Can manage permission can edit an Agent's configuration, including instructions, triggers, tools, knowledge and memory; users without Can manage see only the avatar and not instructions, triggers, tools or knowledge. Agents can be made private, visible only to their creator, or shared with individual users or Teams, and an Agent has a primary owner (its creator, listed as manager). Individual triggers are activated or deactivated by toggle, scheduled triggers are added and deleted individually, and the whole Agent is activated or deactivated in the Workspace. Business Plus and Enterprise Workspaces have a Custom Role Permission that prevents members and admins from creating Super Agents, and editing Super Agent permissions requires a paid plan. The Workspace audit log includes a dedicated Agents log, and Super Agent Activity plus Super Credit usage views are available in the AI Hub Analytics.
- Default state
- Disabled
- Availability
- ClickUp documents availability and limits varying by plan and user role. By default members, admins and owners can create, trigger, manage and interact with all public Super Agents; guests, view-only guests, permission-controlled guests, limited members and view-only limited members cannot see Super Agent profiles or create or trigger a Super Agent, although in locations they can access they can see Super Agent comments, generated content and avatars. ClickUp states that all plans get a trial of select Brain AI features and that after that only paid plans can purchase Brain AI add-ons, and that editing Super Agent permissions requires a paid plan. Super Agents are also documented on the mobile app and the Brain MAX mobile app.
- Licensing
- ClickUp documents that Super Agent runs consume Super Credits and that Super Credit usage for Super Agents can be viewed from the AI Hub. Brain AI features are subject to ClickUp's fair use policy, and ClickUp states that future restrictions may apply and usage limits may change. For a limited time all plans can connect external MCP servers, with pricing subject to change.
- External model or provider
- ClickUp documents that Max is the default model, that other premium AI models are offered, and that the model is selected in the Super Agent's Instructions section or from the model control in the Agent profile, where the default shown is Auto. A Super Agent reply can be retried with a different model. ClickUp does not enumerate the selectable Super Agent model versions in this documentation, so no specific external model versions are recorded here.
- Limitations and uncertainty
- Human approval is not universal. ClickUp's overview states Super Agents "seek human approval for critical decisions", but the permissions article states that if you want a Super Agent to check with a person before taking action you configure that in the Agent's instructions or preferences, and Super Agent Activity documents scheduled runs that show no Run By user; documented automatic approval is limited to the Agent asking before storing a Preferences memory. No documented list of actions that always require approval exists, so human confirmation is recorded as conditional. Permission basis is recorded as mixed: ClickUp states Super Agents "are treated as ClickUp users" with required access to all public Workspace locations, per-Agent Can trigger and Can manage permissions, and external tools running through personal or Workspace app connections, and ClickUp explicitly documents responses using data the triggering user cannot access directly; this is not a plain inheritance of the triggering user's permissions, and ClickUp does not describe an independent agent security principal beyond being treated as a user. Orchestration internals are not documented: ClickUp describes multi-step workflows, multi-step reasoning and learning from errors and feedback, and Activity shows which tools ran and when, but branching, retry logic and dynamic tool-selection mechanics are not specified. Failure handling is documented only at run level, where one failed step fails the whole run. Activity history retention is not documented and Activity is not an immutable audit log; the Agents audit log records configuration events, not every Agent action, though actions taken by Super Agents are included in the Task, Fields and Hierarchy logs. Authority documented for Autopilot Agents, Brain direct interaction, Brain MAX, the ClickUp MCP Server and AI Fields is excluded from this record.
Evidence
- What are Super Agents?
Supports: Function · General · Default state · Human confirmation · Admin controls · Primary source
Super Agents are described as ClickUp's Brain AI-powered teammates that perform multi-step workflows around the clock and can be triggered automatically or manually.
ClickUp distinguishes Super Agents from Autopilot Agents, which perform actions based on defined triggers and conditions rather than adaptive interactions.
Using Super Agents requires activating the AI ClickApp for the Workspace, and the Chat ClickApp for Chat interaction.
ClickUp's overview states that every action is logged and that Super Agents seek human approval for critical decisions, without defining which decisions are critical.
You control which tools and data sources Super Agents can access and who in the Workspace can trigger and manage them.
- Super Agent instructions, Skills, triggers, knowledge, and memory
Supports: Function · Human confirmation · General · Actions · Data access · Limitations · Primary source
A Super Agent profile contains Instructions & Skills, Triggers, Tools, Knowledge and Memory sections, with instructions always required and the AI model selected in the Instructions section.
Triggers can be any combination of Manual (@mention in task comments, Doc comments and Chat; Direct Message; Assign task), Scheduled (hourly, daily, weekly, monthly or custom) and Automated (triggered by Automations).
Scheduled triggers support repeat cadence, run time, start date, timezone, an end date defaulting to Never, and per-trigger additional instructions.
An Automation created in a Space, Folder, Subfolder, List or Channel can select Super Agents as its Action and run a chosen Super Agent with customised additional instructions.
Knowledge is the data the Agent can access: selected Workspace locations, external data sources, ClickUp's public help articles, certain connected apps and the web; items and locations mentioned in instructions are added to knowledge automatically.
Removing tools may cause the Super Agent to be unable to perform some or all of its instructions.
- What are ClickUp Brain AI tools?
Supports: Actions · General · Function · Limitations · External actions · Data access · Permission basis · Primary source
Tools available to Super Agents include Create task, Create subtask, Create Doc, Create page in Doc, Create List, Create view, Create attachment, Create Custom Field, Update task, Update Docs, Update comment, Post task comment, Add task to Lists, Move to List, Track time, Create and update reminders, and Manage Personal Priorities.
Update task covers assignees, Custom Fields, Checklists, dependencies, description, due date, name, priority, start date, status, tags, time estimate and related task links; Agents cannot delete Checklists or Checklist items.
Toolsets are curated packs (Docs, Tasks and subtasks, Comments, Edit tasks, Create and edit images) that can be mixed with individual tools; the Comments toolset is not available to Autopilot Agents.
Default tools are automatically enabled when an Agent is created, vary by Agent type and cannot be deactivated; for Super Agents they are Create schedule, Generate image, Post reply, Load assets and objects, Load Custom Fields, Retrieve Chat messages, Retrieve task list, Search user activity, Search users and teams, Search Workspace and Write a to-do list.
Integrated tools available to Super Agents include Slack Send a Slack message, Google Calendar and Outlook Calendar create, update and delete events, Outlook Mail draft and folder management, Gmail tools excluding Send email and Send draft, and tools from connected external MCP servers, using Workspace or personal connections.
Search Workspace searches the Workspace and connected apps, and Search web and Load web pages are available to Super Agents.
Where a Workspace uses custom role permissions, members must have the Create Views permission enabled for Super Agents to successfully create Docs.
- Super Agent privacy, security, and permissions
Supports: Permission basis · Data access · Admin controls · Human confirmation · Actions · Primary source
ClickUp states Super Agents are treated as ClickUp users so that permissions can control their access to Workspace data, and that they are required to have access to all public locations and items in the Workspace.
Triggering a Super Agent in an unselected private location gives temporary access for that interaction only, while selecting a location in knowledge or granting it in instructions gives persistent access; Intelligence memory can store information from private locations.
If private or external data is shared with a Super Agent, including Personal Lists, it can use that data when responding to anyone with permission to trigger the Agent, even if they lack direct access; permissions are default and editable at Workspace and Agent level, Agents can be private or shared, users without Can manage see only the avatar, and Business Plus and Enterprise Workspaces have a Custom Role Permission preventing members and admins from creating Super Agents.
If you want a Super Agent to check with a person before taking action, you configure that in the Agent's instructions or preferences.
ClickUp gives the example that a Super Agent without the Docs toolset cannot create Docs and pages or edit existing Docs, confirming that tool configuration bounds its actions.
- Create a Super Agent
Supports: Function · Default state · Primary source
Super Agents are created through the natural-language builder, the Super Agent catalog, from scratch in the AI Hub, or by asking Brain, then configured and activated.
A Super Agent must be configured and then activated before it operates in the Workspace.
- Super Agent Activity
Supports: General · Human confirmation · Limitations · Primary source
Super Agent Activity records time run, Agent name, location, trigger, Run By, and status of Failed, Skipped or Completed, with expandable rows showing which AI tools ran and when, and Agent explanations for some actions.
For scheduled Agent runs, Run By does not display a user.
If one step fails the entire process fails; if the last step is skipped the run is marked skipped.
- What is Super Agent Memory?
Supports: General · Data access · Primary source
Memory types are Recent (episodic memory of recent interactions, recalling only memories the triggering user can access), Preferences (learned from feedback, with the Agent asking approval before storing) and Intelligence (stored automatically at the Agent's discretion, currently in beta).
Super Agents can store information from private locations and DMs in memory, that memory is visible to anyone with Can trigger or Can manage permissions, and it can be used in later interactions; managers can view and edit memory to remove sensitive information.
- ClickUp Brain AI feature availability and limits
Supports: Availability · Licensing · Primary source
Members, admins and owners can by default create, trigger, manage and interact with all public Super Agents, while guests and limited members cannot see Super Agent profiles or create or trigger a Super Agent, though they can see generated content in locations they can access.
All plans get a trial of select Brain AI features, after which only paid plans can purchase Brain AI add-ons, and editing Super Agent permissions requires a paid plan.
- Workspace audit logs
Supports: Admin controls · General · Primary source
The Workspace audit log includes an Agents log for Super Agents recording Agent Created, Deleted, Active, Assignee, DM, Knowledge, Mentions, Prompt, Tools, Triggers and Schedules setting updates.
Actions taken by Super Agents are included in the Task, Fields and Hierarchy audit logs, while Autopilot Agent activity is tracked in the Automations log.
- Select an AI model
Supports: External model · Primary source
Max is the default model for Super Agents, other premium models are offered, the Agent profile model control defaults to Auto, and a reply can be retried with a different model.