AI Super Agents

SAs use ChatGPT 5.1, but would love have access to other base models like Claude, and select which model a SA would use for their specific tasks.

Super Agents currently cannot access existing ClickUp app integrations (e.g. GitHub, Zapier) for read-only analysis, search, or context. Please allow Super Agents to: Use already-connected integrations as read-only tools Search/analyze data from tools like GitHub repositories, PRs, files Use this context for better reasoning and answers This would make Super Agents far more useful in real workflows where ClickUp is the central hub.

Currently my Super Agent does not have the ability to assign other Super Agents to his workflow.

Add the ability to call ClickUp Super Agents via the ClickUp API and ClickUp MCP.

Super Agents can do almost all of what I would need a human employee to do. The main flaw I see is that it can't create content and export it to Google Drive. The agents can draft emails and create events for Google, so the two way integration is there, you just need to do the same for Google Docs and/or Google Drive. As it is, I have to create an annoying Zapier flow to facilitate this.

I've been watching a ton of videos and community events to try and get a sense of actual use cases. In the end, most ended up being marketing hype more than anything OR "we use agents to do x, y, z", but never showing them in action. I finally decided to give one a shot last week. I started with a template (personal assistant I think). After some iteration on the setup, I thought I was set. Each morning it would send me my focus items for the day and a list of my meetings. Well it changed the format from the first day to the second and then again on the third (with no prompting). I decided I liked the second day the best and asked it to take what it gives in the chat and create a parent task with sub-tasks each day so I could actually check something off (the checklist in chat is not interactive). EVERY day since, it messes up something. The tasks gets created and it's in my Overdue section. Bot says "You're right...let me fix that" and says it'll be correct moving forward. Sometimes it's missing the subtasks, other times its missing tags, other times the meetings. When I call it out, it tells me I'm right and that it'll fix it and update it's preferences, but it continues to not be consistent and therefore not reliable. I've burned through 4K credit this week because the agent can't lock in and stay consistent with it's instructions. As the company's ClickUp "champion", I can't recommend this to anyone else on the team at this time. It's all great in theory but it's wasting more time and effort in fighting with the agent to get things right than is worth for the output it provides. Intrigued with the concept (I use AI for a lot of things), but disappointment with the experience so far. Lastly, I found it interesting when I had a call with some of the product team this week when I asked if/when do the credits renew, neither had an answer. I still don't know if they renew monthly or we have what we have and when we run out we have to purchase another batch of credits.

The Super Agent AI responses have some unintended buggy behavior. Here are three cases in order of increasing severity: 1) In the Super Agent Builder, it asked 2 questions to the user, and the suggested Follow Up responses attempted to answer both. But the 1st question isn't answerable by multiple-choice, so the follow up responses repeated the option "Use this list for tasks". Furthermore, I was baffled by what was meant by "this", because "this" wasn't defined, and I thought the agent was referencing something I couldn't see. See image, "clickup weird question.png". The fix here is a slight tweak to the prompt on how the AI should format questions to the user and how to handle follow up suggestions for questions that can't be answered by multiple-choice. 2) In Brain, the purpose of the 3 suggested follow ups in its system prompt got interpreted incorrectly. Here you can see that the 3 follow ups are 3 things the AI could ask the user, rather than 3 things the user could ask the AI. See image, "poor followup questions.png". The fix here is a tweak to the system prompt that clearly define the roles of the "user" and the "AI", and that the follow up suggestions are for the former and not the latter. 3) A potentially serious issue. I made a Super Agent that spawns tasks in batches. I then used that agent to create 500 tasks with a single prompt, and it worked! See image, "500 clickup tasks.png". I was going to test how high I could push this number, but I ran out of free credits. However, if I could do 500, then potentially there is no limit, and a curious user could use a Super Agent to spawn Billions of tasks and flood the system and/or burn all their credits with a single prompt. Even at <500 tasks I was getting cases of breaking the Tasks webpage and causing it to freeze, even after clicking the browser's refresh button. (I could restore it only by killing the Tasks page and re-navigating to it from my home page). The fix here would be a combination of light prompt optimization to ward against some of the obvious malicious prompt-hacking techniques, combined with real limits on agent tool use. You'll also have to provide the AI in its context an understanding of what those limits are, lest well-intentioned users hit these limits and neither they nor the agents understand why they are blocked.

Superagents should be able to create a task from a template, or create a task and then apply a template to the task. Currently they can just 'mirror' a template, but often make formatting issues. It would be much better, if they can just apply the template to the task directly.

I’m using our Super Agent william – Prism Campaign Architect to design marketing campaigns. I’d like to be able to generate and return video files (e.g. 30s, 9:16 vertical, 2K MP4) directly from the agent. Please add a video creation / render tool to the Super Agent tool catalog (something like "Create Video"), so the agent can: – take a script + shot list – call a video generation service – return a downloadable MP4 file or link in ClickUp This would let us go from campaign concepts to ready‑to‑post Reels/Shorts without leaving ClickUp.

I’d like the ability to automatically share all newly created Docs—including AI Notetaker meeting notes—with selected Super Agents (or specific users/teams) by default. This would eliminate the need to manually adjust permissions every time a new Doc is created, ensuring that Super Agents can immediately access, process, and act on new documentation as part of automated workflows. Why this matters: Saves time and reduces repetitive manual work. Ensures Super Agents always have access to the latest Docs for summaries, automations, and knowledge management. Improves consistency and reduces the risk of missing important information due to forgotten sharing steps. Suggested implementation: Allow users to set default sharing rules for Docs at the workspace, folder, or Doc template level. Enable an option in AI Notetaker settings to auto-share meeting notes with specified Super Agents or teams. Thank you for considering this improvement!