Feature Requests

DOCX is currently not allowed as a format to upload to the clickup chat. It would be good to be able to upload docx-like word documents, not just txt and pdf

It would be awesome for Brain to be able to read attachments that are uploaded in the Resources card in a space. Docs, images, etc; instead of having to upload them into Brain chat. That would unlock at lot of capacity for Brain to get better on-demand context into things and perform better.

ClickUp Brain currently appears to rely on a single AI model. I would like the ability to connect and use multiple AI models/providers within ClickUp Brain, so teams can choose the best model for each use case (quality, cost, speed, privacy, compliance). Key capabilities requested: Multi-provider connections: Allow admins to connect different AI providers/models (for example OpenAI, Anthropic, Google, etc.). Model selection controls: Let users (or workspace admins) select which model ClickUp Brain uses, either: * as a default per workspace/space/list, and/or * per action (summarize task, draft content, extract action items, analyze docs, etc.). Policy and governance: Admin controls for which models are allowed, where they can be used, and optional restrictions for sensitive Spaces/Lists. Quality and cost optimization: Enable teams to route lightweight tasks to cheaper/faster models, and complex reasoning tasks to stronger models. Auditability: Provide visibility into which model was used for an output (for troubleshooting, QA, and compliance). Value/Impact: Better outcomes across different Brain workflows (summaries, drafting, analysis). Flexibility for organizations with strict security/compliance requirements. Cost control by matching the model to the complexity of the request.

I find Brain AI very intrusive as it does not do much that i want it to and I am a butterfingers who is always accidentally triggering it, to the degree where I am considering staging a coup to get my company to change tools. To have the spacebar be what triggers Brain in certain contexts is sheer lunacy, in my opinion. In the same way that Commands are triggered by a / , I believe these are disingenous choices, in the sense that Clickup has chosen extremely common and very useful keys that we all constantly use in order to these trigger functions that can be useful but are very invasive when you didn't meant to trigger them. I assume that this is so you can say "check out these metrics, everyone uses it" to your financial backers, but who knows. In my view, these are wildly poor key choices from a usability perspective, especially if these features that cannot be turned off without admin permissions, since lowly users like myself end up with constant unwanted pop-ups when typing. It slows down work and making things more messy than they ought to be. Cheers

I need an AI Agent that watches a space and detects when work on a task in "In progress" without proper time tracking. The agent needs access to per-task time entries (start time and when they were created/updated) so it can: – See when a task moves To do / To edit / → In progress. – Check if time tracking starts within a 10-minute grace period, or is backfilled within 10 minutes. – Classify issues as Delayed tracking vs Missed tracking, and label them as from scratch / from edit / from resizing. Right now, AI Agents can’t read detailed time tracking history, so this workflow isn’t possible. Please expose time tracking data to AI Agents (or automations) so we can enforce accurate tracking for our team.

The problem with AI notetakers is that they're not discreet. My clients don't appreciate getting messages from a robot noting that they are being monitored. It would helpful if there is was a less involved option.

Problem: The current AI Usage dashboard provides a high-level overview but lacks the necessary granularity for effective resource management. Currently, while Super Agents have a clear breakdown, other high-consumption features like Autopilot Agents, AI Cards, AI Fields, and AI Tasks only show aggregate costs. Furthermore, the dashboard prioritizes monetary value (USD) over the actual credit count, and lacks historical month-over-month reporting for trial/bonus pools. Proposed Solution: I suggest a comprehensive update to the AI Usage interface to include: Dual Metric Visibility: Display "Credits Consumed" alongside "Monetary Cost (USD)" as standard columns. Relying on tooltips (hovering) makes it difficult to compare usage across different workflows quickly. Granular Breakdown for All AI Features: Extend the "Super Agent" level of detail to Autopilot Agents, AI Fields, and AI Cards. We need to see: Which specific Agent/Automation triggered the usage. The location (List/Folder/Space) of the trigger. The User/Member responsible for the action. Historical Data & Period Filtering: Ability to filter usage by previous months or custom date ranges. Currently, the breakdown resets on the 1st of each month, making it impossible to audit past consumption patterns once the month ends. Audit Log Integration: A dedicated "AI Audit Log" or better filtering in the existing Automation Audit Log to specifically isolate AI-related consumption events. Why this is important: As a decision-maker, I cannot confidently purchase additional AI Credit packs or add-ons without understanding exactly how our current credits are being spent. Clear visibility is the bridge between a "trial" and a "paid" commitment. Better governance tools will help teams optimize their workflows and scale their AI usage responsibly.

Feedback created by your AI... Summary: Please add a dedicated Super Agents section inside the Brain MAX desktop sidebar. Problem: Today, Super Agents are discoverable via search and other surfaces, but when I’m working in the Brain MAX sidebar, I don’t have a persistent, one-click place to: See my most-used Super Agents Jump into an Agent quickly Manage / browse Agents without leaving Brain MAX Request: Add a “Super Agents” section to the Brain MAX sidebar that supports: Showing pinned or recent Agents Search / browse all accessible Agents Quick actions (open, message, run, manage permissions if allowed) Why it matters: This would make Brain MAX feel like a true desktop control center and would reduce navigation friction for users who rely on Super Agents for daily workflows. Success criteria I can access my Super Agents from Brain MAX in 1 click. I can pin a few Agents so they always appear. The section respects existing Agent permissions and privacy.

claude opus 4.6 didn't run, page froze