Feature Requests

Summary Enable ClickUp Brain to generate executable “mini‑apps” from natural language prompts and workspace context. These apps should read and write ClickUp data (Lists, Tasks, Docs, Dashboards, Custom Fields, Tags, Comments, Attachments) with permission‑aware access and run as dynamic, interactive tools embedded in ClickUp. Support both internal workflows (inside ClickUp) and external use (lightweight client portals, prototypes, single‑task utilities). Problem Brain is strong at reasoning and content generation, but many high‑value workflows still require stitching views together, manual data transforms, or repetitive actions across Lists/Docs/Tasks. Teams need small, purpose‑built interactive tools that bind to live ClickUp data, execute multi‑step actions, and share outputs without leaving ClickUp or building separate integrations. Proposed Solution Introduce Brain‑generated mini‑apps that: Bind to data: Connect to Lists, Tasks, Docs, Dashboards, Saved Filters; expose fields and relations; support query, aggregate, and live updates. Extend to external data: Connect to Google Drive, GMail, Google Calendar, and other data sources. Provide interactive UI: Forms, tables, charts, buttons, wizards; adapt based on context (assignees, statuses, tags, custom fields). Execute actions: Create/update tasks and docs, set statuses, add comments, trigger automations, post to Chat, write to custom fields. Are permission‑aware: Enforce roles/custom roles/sharing for all reads and writes. Are deployable: Launch from Chat, Task, Doc, Dashboard, or standalone panel; share internally or externally with controlled access. Are composable: Save as templates, version apps, branch/test changes, reuse across Spaces. Example Mini‑Apps NDA Generator: Pick a template, fill variables (party names, dates, jurisdiction, term), render a final NDA, attach to the Task/Doc, post a Chat message, and open a “Sign & Track” task with due dates. Marketing Spend Planner: A calculator bound to campaign Lists and budget fields; model scenarios, generate a summary Doc with charts, and create tasks to adjust budgets and assign owners. Contract Clause Analyzer: Paste text or select a Doc; the app highlights risky clauses, suggests redlines, and opens subtasks for each recommended change, citing sections. KPI Narrative Builder: Read Dashboard widgets; explain trends, anomalies, and risks; propose follow‑up tasks with owners and dates; post a summary to the channel. Spec‑to‑Plan Converter: Pull a Doc, extract milestones, produce a dependency graph and sequenced subtasks, each citing source sections; dry‑run changes, then commit. Bug Triage Console: Intake reports (attachments, text), group by component/severity using workspace fields, mass‑create/update tasks, and publish a triage summary back to Chat. Governance & Safety Admin controls: Enable/disable Brain mini‑apps; define scopes (space/folder/list); approve data bindings and actions; set external sharing rules. Audit & observability: Log prompts, context accessed, data mutations, and app versions; exportable for compliance. Data boundaries: No cross‑workspace leakage; retention and deletion aligned with ClickUp policies; strict permission inheritance. Cost/performance: Rate limits, quotas, resource controls; “dry run” previews for bulk changes. Success Metrics Reduced time‑to‑action from prompt to committed changes. Lower app‑switching; faster decisions in Chat/Tasks/Docs. Improved data quality via structured inputs and governed bulk updates. Adoption of mini‑apps across teams; increased external collaboration.

My suggestion is to be able to integrate Hermes into the clickup chat, as we have local LLMs running together with Hermes, the tendency is that more and more companies have this, I know that Brain IA exists, but for small companies it doesn't make sense to pay such a high amount if I can use local LLM for free with my team in an almost unlimited way. SLACK, which is the main rival of clickup chat, has easy integration with Hermes, having this in the clickup would be another advantage to beat Slack.

With Cloudflares new update they've also rolled out an Accountability program that allows AI providers like clickup to register with them and allow AI agents to continue crawling websites who have opted out of AI training. It would be great if Clickup participated in this program so user agents can still effectively search the web.

I have used artifacts to create visual aides based on data in my lists/projects. I would like to be able to have my agent automatically kickoff a refresh of those artifacts on a cadence. Today Agents cannot edit artifacts.

Since the Brain2 update, two features I relied on in the Brain chat interface are no longer available: the ability to regenerate a Brain response, and the ability to edit a previously sent message. Both were present in the original Brain chat and helped me iterate on prompts without starting a new conversation. If these were intentionally removed, I'd like to formally request they be reinstated. If this is a phased rollout or a known gap, any timeline or workaround would be appreciated.

Expose assigned comments per user via the API / ClickUp Brain so teams can programmatically audit open assigned comments across tasks and channels.

Artifacts can build a complete client-ready document, but they cannot deliver it anywhere. Because they run with no network access, an artifact that generates a quotation, invoice, or report has no way to attach the finished file back to the ClickUp task it was opened from. The user has to save a PDF locally, go find the task, and upload it by hand. That breaks what should be the most valuable artifact use case: operational documents that belong on a record. To be clear about what I am not asking for. Calling the ClickUp API from artifact JavaScript would mean embedding an API token in the artifact source, where anyone who can view the artifact can read it. That is not acceptable. Neither is general outbound network access, which would let a malicious or prompt-injected artifact exfiltrate workspace data. The sandbox exists for good reasons and should stay. What I am proposing instead is a narrow, host-mediated capability bridge. Expose a small API to artifact code where the ClickUp shell performs the action on the viewing user's behalf, under that user's own permissions, so the artifact never holds a credential and never makes an outbound request itself. Three verbs would cover almost every document workflow: attach a file to a task, post a comment on a task, and read the task, list, or doc the artifact was opened from. This is safe by construction rather than by trust. There is no credential in the artifact source, so there is nothing to leak. The host enforces permissions, so a user can only write where they already have edit rights. The verbs are specific rather than arbitrary HTTP, so there is no exfiltration path. Every write happens through ClickUp and is therefore attributable in an audit trail. And each call can be gated behind a real user gesture, so nothing fires silently in the background. Alongside that, please consider a host-level PDF export rendered server-side rather than through browser print, exposed both as a native Export PDF action in the artifact chrome and as a callable method. Browser printing of artifacts is currently unreliable and truncates output to a single page, and shared artifact links cannot be printed properly at all. Server-side headless rendering would produce correct multi-page A4 output with @page rules and print stylesheets honored, fixing the existing truncation bug and the shared-link printing reports in the same change. We did try the alternative of having a Super Agent compose the document conversationally, since agents can already attach files. For anything with many line items and custom per-line detail it is slower than filling in a form, and dramatically slower on amendments, where you end up re-describing the whole quote instead of editing one field. Direct manipulation is simply the right interface for structured documents. The artifact is the correct tool here. It just needs one narrow, safe way to deliver its output. The impact reaches well beyond our use case. Any artifact that produces a document, whether that is a quotation, invoice, SOW, certificate, report, or inspection form, would become an end-to-end workflow instead of a dead end.

I would REALLY like to use ClickUp's super agents for project building but it is cost prohibitive to upgrade our entire team to Enterprise+. I'd like to be able to purchase AI credits and turn on AI capabilities for a specific number of users.

I have a conversation for every brand I work, but there's another chats with Brain for other random stuffs. I need a way to pin my brand chats, or use folders to group AI conversations on Brain AI.

AI agents currently only have access to public lists - this prevents us from building "AI Agenta" of any kind in our workspace as our lists are all private and client facing.