AI Super Agents

Want to waste hours and have nothing to show for it! USE CLICKUP! Better yet, use clickup with their shitty AI "super agents"!

i find it very annoying having to manually check the answers in slack chats after my agent has send out a question. I would find it really usefull if you would let the agent see chathistory in chats inside of slack

Two things: It'd be great the possibility to limit how many credits each user can use per month per Super Agent It'd be great the possibility to know how many credits each user is using per Super Agent per day, week, month Why I need that ? I need to avoid one user to spend all IA Agent credits making excessive questions and be aware of that.

Why is it that no AI anywhere ever in any app no matter the model and no matter how supposedly "smart" it is- has no idea about its own interface? How hard is it to have it "swallow" a short document at the start of a convo, where it would get the current coordinates of every button in the very app it's supposed to be an agent in? And then when I ask my agent, "Where's this or that?", it doesn't tell me to go read a book?! And imagine this- this will make you rich if you're smart enough to listen!- to have it have the ability to really POINT IT OUT, show it, VISUALLY, highlight the button, or at the very least show a screenshot with the button marked. Instead, the thing writes novels, poetry, about buttons that don't exist, like any other retarded AI. Come on. I'll make the thing myself, but then you'll have to pay for it.

It is useless having a Super Agent surface me information from a page in my Docs and not be able to link me back to the block where that information comes from. It just links the page, and now I have to go and find it. It is at least now giving me sentences or headings to find with cmd+f in the page...but that's a janky workaround. When I share with my colleagues, I copy the Block Link and send them where they need to go - this expectation is the same for the Super Agents, regarding their ability to reference material or guide me to more information. This was the Super Agent's response: "At the moment I don’t have access to ClickUp’s internal “copy link to block” URLs for individual table rows/headings. If ClickUp later exposes true per‑block URLs to me via tools, I’ll be able to take this one step further and drop you right onto the exact row/paragraph rather than just the meeting page."

Agent tool - list-update/rename capability

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!

🧾 User Report – Broken Task Creation Workflow in ClickUp AI (Freelance Timeline Sentinel) Reporter: Katya Hernández Workspace: Ninja Cat Date: March 2 2026 Agent: Freelance Timeline Sentinel 📍 Context I spent more than an hour trying to create a structured timed project list (“Toptal Interview Prep”) inside my Freelance work space. The agent confirmed multiple times that it had write permissions (Create List, Task, Subtask tools were visibly enabled), and it kept saying, “This will take five minutes,” or “Ready to create the live list.” ❌ What actually happened No list or tasks were ever created, despite repeated confirmations. The agent instead created dozens of ClickUp Docs, logging its intent rather than performing the actual commands. When I asked for a workaround, it suggested generating a CSV import; I followed detailed steps and spent another 20–30 minutes trying to import. The CSV importer was buried multiple menus deep, asked for confusing field mappings, and produced mangled tasks: truncated names, no due dates, no start/end times, and no hierarchy. Every “quick fix” (“takes 5 minutes”) resulted in more wasted time and more confusion. ⏳ Time and Credits Lost I’ve spent over an hour trying to configure something that Gemini built in minutes. Because this uses paid credits, this failure directly wasted billable resources. I doubt I’ll be refunded for this, but I want it on record that this session burned my credits on repeated false confirmations. 💬 Emotional Impact / Feedback This was exhausting and demoralizing. I came to ClickUp AI for efficiency, not an endless documentation loop. The system repeatedly implied the agent could create ClickUp tasks directly, but evidently it couldn’t. Each failed attempt compounded frustration and sapped any confidence that the workflow is dependable. If the create_task and create_list tools aren’t functional, they should be clearly labeled as inactive or blocked — not shown as ready to use. The UX also buries the CSV import three levels deep, and the importer’s instructions conflict with the latest interface design. ✅ Desired Resolution Refund or credit restoration for the session. Confirmation from ClickUp AI Support whether agent write permissions to create lists/tasks are actually functional. Simplified or fixed project‑creation logic for agents like this so users don’t waste time. Clear user guidance showing where CSV Import truly lives in the current UI. 🪶 Closing Note I’m a long‑time ClickUp user; I rely on automation because I manage multiple creative projects. This entire process undermined one of ClickUp’s key value propositions — saving me time. Tonight, it cost me productivity and patience AND money right before an important presentation.

I write this with love hoping someone at clickup seriously considers it. i am a HUGE clickup user - use it for almost every job at my company and have spent countless hours investing in it. The AI - specifically the marketing hype about 'replacing every software we have' - has us considering leaving clickup, because we're worried about the direction clickup is heading. i love clickup and tried to share this directly, but the AI bot keeps redirecting me to this public forum so here we are. focus on your core product. there are SO many basic AI use cases that would be wonderful to see (like in automations) without the 'Super Agent' marketing hype, and if you try to be every tool to every user you'll lose business. No one wants a tool that can do everything, because no one company can be the absolute best at everything. you were great at task management, and frankly your roadmap seems to have stalled for addressing customer concerns related to basic automation and task management features. the new UI with messaging channels has just made my workspace messier. i'd rather you improve your core product and be the best at that so i can do automations using formulas (for example) than build this AI agent that doesnt work. Your AI cant (and hasnt since the launch of Brain) handle basic IF/THEN tasks, so theres no way i'd trust the 'super agents.' for example, if i try to just say 'take all tasks in this list with custom field value X, and set the date to Y' it spends 40 minutes on it, completely botches the task (generally requiring work just to undo the damage it causes), and then when i ask for an update it confidently tells me its done. its confusing that you'd even launch the super agents when the basic ai brain is so useless. if you want super agents to succeed, build some templates with instructions or premade examples, and take the whole thing bac to beta. i try clicking a template button to try an agent, and am met with dozens of questions and no guidance, as if the bot were by invention, not an example template. i've tried to understand how these bots can actually be useful multiple times, and genuinely cant find any use for them. i tried to build a few, and the AI was totally unable to handle my fairly simple requests (if i add a line item to a contract that mentions 'product demo' in the task name, add it to my product demo production queue). Further, if you want it to succeed, put it back in Beta. Unless I am the problem, it seems like the AI just plain doesnt work. given the amount of time it takes to set up prompts, people aren't going to try more than a couple times. you're better off dropping it to beta and waiting until your product works and has gone through Q/C and has user documentation. at least then when you go out of beta people will try it a second time if it didnt work the first time.