Feature Requests

Possibility to add/use skills such as Claude Cowork, Codex, OpenClaw, etc. So that you can also improve certain working conditions of agents and also combine them with other workflows and tools that you may already be using, such as Claude Cowork or Codex.

Clickup KI Voice to Text etc. generally charge above a fixed credit limit without feeling like 100 separate packages. So it feels like that despite the fact that you have the Clickup Business version and the “All in AI” package, you still have to add additional packages and that is super confusing and then it feels like functions are being removed from the packages over time. Wouldn't it be much easier simply to set up and bill everything on a fixed credit sum per plan and then every user can decide for themselves which functions they use and where how much. Some go more towards AI superagents, others more voice-to-text, etc. But in the end, you have a fixed credit sum with every license that is fair for all sides. I mean AI usage also costs ClickUp a bit about the models and we just passed it through and with z.B. 25% surcharge simply continues to charge us end users. But that would make it more flexible and easier what you spend where now and what is included where and then you can simply flexibly upgrade the credit limit flexibly if you need and/or scale more. Simply with every new user/employee that you integrate with a paid version, the company-wide credit limit increases by sum X and it is still consumed as necessary across all channels. With the AI Notetaker, Clickup z.B is very good. Because it is simply at the hour limit and regardless of whether 1 employee then consumes 80% of it alone because the others are less in meetings, it doesn't matter at all for ClickUp. So I would say it would also be as transparent as possible for all sides, fair and would cause less frustration as to what is already behind an older payment barrier, etc.

I’d love to see a feature in ClickUp AI similar to ChatGPT’s “Custom Instructions.” Instead of re-selecting a saved prompt every time, I want to define my AI style, tone, goals, and contextual preferences once—and have them automatically applied across all interactions with ClickUp Brain and AI Agents (in tasks, chat, etc.). Why this matters: • It’s key for creative brainstorming and maintaining consistent tone across work. • Saves time from having to reapply prompts. • Makes AI truly feel like an extension of my workflow and voice. Bonus feature idea: Allow workspaces to upload contextual documents (PDFs, strategy docs, style guides) that AI can reference persistently.

It'd be dope if clickup AI would support https://modelcontextprotocol.io/ . With that its agent could instantly integrate with a ton of tools without you having to do first party integrations in the first place. Some tools like cursor.ai just allow you to paste in an MCP link and bam, you have it in your agent. Support this ONE thing and save time integrating all the others. Let your users do the job and give them the power to integrate properly.

Either integrating with the AI scheduler Addie, or creating your own automatic scheduling AI that decides what order you should do things in based on priority, due date, etc

It would be great to be able to use AI to quickly generate clean, and cool looking whiteboards. Currently the AI Brain in whiteboard only generates images, and they are all cut off. Instead, i'd like to ask it to "pull all tasks from this board as headers with unique colors, and put descriptions as sub sticky notes". That way I could create a quick org chart, or view of specific tasks quickly, efficiently, and in a cool looking way. On some other tools this involves importing .json and .csv data which most LLM/AI tech can work with. If I could simply copy and paste in such formats and choose my template look or describe it then it would save tons of time in the long run. No current workaround to generate formatted whiteboard material. I can almost get there by importing .csv or .json as tasks using import or AI Brain. Then I have to drag in each tasks. However, once I try to do any whiteboarding the AI just generates faulty images instead of editable structures in a useful format. Final goal, open whiteboard, ask AI to pull in tasks I've already got of a tag type from X project, tell it to build a color coded structure using bubbles at the top and stickies below it (or from template example), and presto it builds a structure. Example attached. I've use a different tool and AI to do this with prompts so it's very possible. Giving users a few preset prompts and styles would solidify this as useful for all sorts of purposes in the whiteboard tool.

I would like ClickUp Brain and/or a super agent (preferably a super agent) to get access to PRIVATE notion pages via an API or integration to be able to read and write (preferably read at the minimum).

It would greatly improve productivity if AI models in ClickUp could remember my conversation preferences—such as preferred response format, tone, and level of detail—across sessions. This would save time by eliminating the need to repeat instructions and ensure a more personalized, consistent AI experience for ongoing projects.

We are going to need individual add on pricing for additional image gen, & AI Time-Blocking we don't need the AI notetaker. Also be aware click up is getting a bit price for AI features included in others at the higher levels, not an additional add on; like AI Automations Fields, Properties & more, AI Assign & Prioritize, Autopilot Agents, & AI Time-Blocking

The story goes like this: Open the "A.i" sidebar, and I type @ to see IF I can @ mention a Super Agent (I forgot if I could or not, so I wing it) it populates...ok cool so I guess I can. Then, I'm told, hey, this is Brain... NOT Sonata... (Sonata is my SuperAgent in charge of triaging tasks as they come in and better arranging them (assigning labels and info etc..) hence the name Sonata, which is an arangement, and ours being a music rooted orgnazation. (Some days being clever and cheeky is my only reward...) It gets worse, Brain then goes on to prompt me with: "Want me to ping Sonata for you, or is there something specific I can help with?" SO I of course ask Brain to indeed send Sonata a DM to check on her triage queue. (That was the exact prompt it provided me with, and I simply clicked it.) Then I'm told: (And I wish this were a joke but its not...) "Unfortunately I can't send DMs to other agents (like Sonata) on your behalf. You'd need to message her directly in your DM with her. Just pop into your Sonata DM and ask something like "What's in your triage queue right now?" and she'll respond based on her schedule and workspace knowledge. Want me to pull up her recent activity or check the lists she monitors instead?" I have no words other than, this is broken, please fix it. Also, I want to point out that in the lates update its touted that you can @ Mention Superagents in Slack. And I find it ironic as well as troubling to see that a 3rd party is tended to before first outfitting the ClickUp platform itself with a full breadth of capabilities. Seeems the priorities are off. Please course correct.