AI Super Agents

Super Agent Not Ready for Primetime
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.
4
·
building now
📬Floating SuperAgents...Hear Me Out...📫
I bet my eyesight that anyone who is using SuperAgents at this point have discovered this as well: 🫵🏻You're talking with an agent, they share a related task list, doc, whiteboard etc... you click it...✵your work appears, and the agent is gone! 💨Poof!💨 The only real work around is to open another windowed instance of ClickUp. (I do this on a 2nd monitor)💻🖥️ ❓WHAT IF INSTEAD: The agent panel, floats on the right, resize-able, and whatever you click to open can be opened without losing the focus of the agent.😉 ⭕️TRY THIS And YOU'LL SEE WHAT I MEAN: To truly get a sense for how this would work.. 1️⃣ Open a doc, then click ASK in the top right to open the Brain. The dock moves over to the left, and you can chat with Brain. NOW: 2️⃣While still in this view, (Doc on the left, Brain chat on the right...) Click to open Planner, or Clips, or Spaces (Try them all if they are close at hand in your 'HomeBar" 🤯EACH opens and the brain stays put. This is how I want my Agents to flow with me through my navigation as I work. Arguably the agents and the Brain should all share the same window. 💡BONUS Idea for CLickUp💡: 1️⃣Create a new Artificial Intelligence Manager. 2️⃣Call it 👩‍🦰L.i.S.A. which stands for Linguistically intelligent Silicone Agents. 👩‍🦰L.i.S.A. will be the overseer of: 🧠Brain, which (In my newly proposed hierarchy, is then the company wide 'Agent" that is the single source of truth for all employees.) As well as the overseer of all created Agents. ℹ️HOW THIS WOULD WORK: 👩‍🦰LiSA would have personal memory for each user that is private to them. 🧠BRAIN would be company wide. 👤Agents would be personal, but also available as "Clone-able"👥 (aka Templates) for redeploying to different teams or members. (Zeb told me that he is going to name the ability to share agents CLONES after my suggestion, and I'm flattered if he actually does.)
0
Load More