Feature Requests

When ClickUp Brain generates slide decks, one-pagers, or other file artifacts in chat, they only exist inside that specific conversation thread. There's no way to browse, search, or organize them after the fact. I'd love a dedicated Artifacts hub (similar to the Docs hub or Whiteboards hub) where all AI-generated files are automatically collected. Ideally you could tag them, attach them to tasks or projects, and search across everything you've ever generated. Without this, useful outputs get lost the moment you close or delete the chat. These files deserve to be as first-class as Docs already are.

I would like to be able to take an artifact I have created and move it to a list or folder level.

A dedicated page for where generated artifacts can be retrieved and organized. Like the Clips Panel.

Brain Artifacts (slides, documents, etc.) published via run.clickup.ai are currently accessible to anyone with the link, including people completely outside our workspace. Since ClickUp increasingly serves as the single source of truth for entire organizations, this is not just a missing feature — it's a critical data leak vector. Any artifact generated from workspace data (tasks, docs, dashboards) can unintentionally expose sensitive business information: financials, strategy docs, internal metrics, client data, and more. There is currently no way to restrict visibility or require internal approval before an artifact goes live on a public URL. Proposed Solution: Default to private. Artifact links should only be accessible to authenticated workspace members by default. Public publishing as an explicit opt-in. If a user wants to share an artifact externally, they should submit a "publish publicly" request. Admin approval workflow. Workspace admins (or a designated security role) should review and approve/deny public publish requests, ensuring sensitive data doesn't leave the organization without oversight. Visibility indicator. Clearly show whether an artifact is private (workspace-only) or public, so creators and viewers always know the exposure level. Why this is urgent: This isn't a nice-to-have. Organizations trusting ClickUp with their entire operational data need confidence that AI-generated outputs inherit the same permission model as the source data. Right now, every artifact created from internal data is one shared link away from being fully exposed to the internet. The more powerful Brain becomes, the higher the risk.

I have used artifacts to create visual aides based on data in my lists/projects. I would like to be able to have my agent automatically kickoff a refresh of those artifacts on a cadence. Today Agents cannot edit artifacts.

Allow Workspace Administrators to upload or write custom instructional files (e.g., SKILL.md format) to explicitly train ClickUp Brain or Super Agents on complex, multi-step company workflows, strict data validation rules, and context-dependent task creation. Currently, ClickUp Brain and Super Agents are excellent at scanning existing data and generating single-turn summaries or code. However, when it comes to executing complex, proprietary business workflows, the AI relies heavily on reactive prompt engineering. In contrast, Anthropic Claude uses a modular, token-saving "Skills" concept (via .md instruction packages and references). Without a native equivalent in ClickUp, teams must host external scripts on third-party servers or route data out of ClickUp via external MCP setups just to enforce rigid, step-by-step workflow procedures for the AI. Proposed Solution / Feature Request A native "AI Skill Builder / Manager" within ClickUp's settings where admins can deploy reusable AI blueprints: Skill Definition Files ( SKILL.md Editor): A dedicated text/markdown area for a Space or Folder where we define exactly when and how ClickUp Brain should execute a workflow (e.g., "When a ticket changes to 'SOW Signed', build 5 specific subtasks, assign them based on role, and calculate relative due dates"). Instead of feeding massive prompt templates into every single AI interaction (which drains performance and context limits), ClickUp Brain should dynamically load the specific "Skill" only when the defined trigger or manual @mention occurs. Also, skills should be added to agents and being able to execute actions with integrations (Google Drive, Docs, MCP Tools, etc.).

In ClickUp Docs, you can select a specific sentence or paragraph and ask AI to improve just that part. Brain Artifacts (presentations, one-pagers, etc.) have no equivalent. If you want to change slide 3 of a 10-slide deck, you either regenerate the entire artifact or manually describe which section to fix, hoping the rest stays intact. Allow users to select a specific section/slide within an Artifact and edit only that portion via Brain, exactly like inline AI editing in Docs. Click a slide > "Edit this slide" > give instructions > only that slide changes, everything else stays untouched. Without this, every small tweak risks breaking the slides you already approved. It makes iterating on presentations painfully slow and unpredictable.

Please, could you add option to hide all AI buttons from pages? It looks like visual garbage, that is annoying and begging to use it.

I find all the little pop ups and new icons about ClickUp AI incredibly distracting and would like the option to disable them regardless of if my organization's workspace is subscribed to the Clickapp or not. Make AI optional.

Please can you remove the excessive number of AI buttons recently added across the user interface? They add clutter and confusion to the UX, and are particuarly annoying when they're right next to a button you use often (eg the add description button on tasks). It's a nightmare! As someone who hasn't subscribed to the AI features, I'd expect them not to appear - a bit like how you never get irritated by an unused Clickapp if it's disabled on a space. I understand that you want to promote your new product, but having buttons everywhere is just a distraction from the main actions I want to do. It's really annoying and just makes me frustrated with the AI features rather than interested to buy them.