AI Super Agents

Brain can create artifacts, but the agent cannot. It doesn't have the necessary skills or tools. Please add this feature, because currently the agent is unable to create a hosted URL with a presentation.

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.

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’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!

TLDR: Super Agents should scream when they lose a limb. Right now they just quietly bleed out. The Issue: When an MCP or integration connection breaks on a Super Agent, nothing happens. No notification. No alert. No email. No inbox ping. You only find out when the agent silently fails at something critical, like, say, RSVPing to an event you're supposed to attend in 4 hours. This morning my scheduling agent (Cal Giorno) couldn't complete an RSVP for an event because his Gmail (also his Fellow MCP) connection(s) had quietly disconnected. My EA Super Agent (Pepper Paltrow) flagged the failure, but only after the ball was already dropped. I had to RSVP myself (Gasp!) and then manually reconnect both integrations. The Ask: When any integration connection on a Super Agent breaks, disconnects, or fails auth, notify the Workspace owner and/or the agent's creator immediately. Inbox notification + email. That's it. What My Super Agent Suggested: A weekly scheduled "smoke test" where an agent deliberately pings every connector to see if it's still alive. That's creative, but it's a workaround for something the platform should handle natively. What I Did Instead: I built a saved prompt instead (see below) so anyone can run a quick diagnostic when something feels broken, but we shouldn't have to play doctor. If the platform knows when a connection drops it would be much more efficient if it could simply let us know at the time of failure. Sharing With the Community: Here's the saved prompt I wrote so you can diagnose connection issues on the fly without waiting for a feature that doesn't exist yet. Drop it into Brain or hand it to any agent: Connection Health Check Prompt: Use it any time an agent reports it "can't" do something it normally can. Nine times out of ten, it's a connection issue, not a prompt issue. "Check all of my Super Agents' external integrations for connection issues. For each agent, attempt a lightweight read-only call on every external connector and report back which connections succeeded and which returned errors. For any failures, tell me the agent name, the broken connector, the error message, and link me directly to the agent's settings so I can reconnect it."

I would like to have a Super agent create a list any time I click "create list" from a task in a certain list, and then adjust or set up the automations so that any time a task is added/moved to or created in the new list, it will link that task to the original trigger task. I have a list template with those automations set up and just want a super agent to be able to change the value of the action to be the original task. Since the super agent can't do this, it isn't able to actually shorten my process of creating those lists at all.

What a joke that "Super" agents can't do basic things like create boards or other basic automations. And when I provide a screenshot of an automation to make sure it's corrent before deploying, it seems not to be able to validate the automation.

allow super agents to communicate with other super agents as another category below triggers, tools, and Knowlege & Memory. I'd love for one agent to be able to ask another agent questions for what it may have access too where the first one does not. This allows for comment tracing within the ticket in case an agent deviates in the conversation.

I need Super Agents to be able to flag when time tracked was not marked as billable, but should have been. I also need Super Agents to be able to look at Billable time in general to understand and report on revenue generation. Right now, agents cannot distinguish between billable and non-billable tracked time.

Just adopted ClickUp for collaboration on projects with customers, but trying to use it as much as possible for other business task management as well. I love the concept of Super Agents, and created 2 to play around with it. I created one that send me a daily summary of things I need to get to, but...no integration with M365/Outlook. Only Google. Really? Why?? I don't know about the US, but here in Canada over 80% of SMBs I deal with are in M365! Wouldn't that integration make A LOT of people happy? Cheers!