# /multitask in Agents Window **URL:** \ **Category:** Release Discussions\ **Created:** [April 24, 2026, 6:47pm UTC](https://forum.cursor.com/t/multitask-in-agents-window/158955 "2026-04-24T18:47:19Z")\ **Posts on this page:** 20\ **Page:** 1
**Author:** ![Colin](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/colin/32/90452_2.png) [@Colin](https://forum.cursor.com/u/Colin)\ **Post date:** [April 24, 2026, 6:47pm UTC](https://forum.cursor.com/t/multitask-in-agents-window/158955/1 "2026-04-24T18:47:19Z")
_New in Cursor! · [Full changelog](https://cursor.com/changelog/3-2) · [Main announcement](https://forum.cursor.com/t/multitask-worktrees-multi-root-launch/158954/3)_ * * * We’re excited to introduce `/multitask`, a new way for Cursor to parallelize agent work with async subagents! Use `/multitask` in the Agents Window to have Cursor run async subagents instead of adding each request to the queue. Cursor can also break larger tasks into smaller chunks and assign them to multiple subagents at the same time. If you already have queued messages, you can ask Cursor to multitask on them instead of waiting for the current run to finish. `/multitask` is useful for: - Running several independent requests at once - Speeding up larger tasks that can be split into smaller pieces - Keeping agent work moving while a current run is still in progress **We’d love your feedback!** - What kinds of queued tasks are you using `/multitask` for? - How well does Cursor split larger tasks into useful subagent work? - What would make multitasking easier to control or understand? If you’ve found a bug, please post it in [Bug Reports](https://forum.cursor.com/c/bug-report/6) instead, so we can track and address it properly, but also feel free to drop a link to it in this thread for visibility. ---
**Author:** ![drewc](https://avatars.discourse-cdn.com/v4/letter/d/edb3f5/32.png) [@drewc](https://forum.cursor.com/u/drewc)\ **Post date:** [April 27, 2026, 1:08pm UTC](https://forum.cursor.com/t/multitask-in-agents-window/158955/5 "2026-04-27T13:08:41Z")
This is really interesting. Is there any mechanism that prevents the async agents from colliding with each other or stepping on each other’s toes with code changes? ---
**Author:** ![Colin](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/colin/32/90452_2.png) [@Colin](https://forum.cursor.com/u/Colin)\ **Post date:** [April 27, 2026, 5:15pm UTC](https://forum.cursor.com/t/multitask-in-agents-window/158955/6 "2026-04-27T17:15:50Z")
Hey @drewc! Great question. For this initial version (which we consider v0—there’s still a lot of work to do to make parallel agents feel seamless), there’s nothing specific in place. In our tests, agents have done a pretty good job of coordinating their changes and avoiding conflicts. We’re currently working on functionality to further improve this! ---
**Author:** ![Tomas\_Nagy](https://avatars.discourse-cdn.com/v4/letter/t/c57346/32.png) [@Tomas\_Nagy](https://forum.cursor.com/u/Tomas_Nagy)\ **Post date:** [April 28, 2026, 8:03am UTC](https://forum.cursor.com/t/multitask-in-agents-window/158955/7 "2026-04-28T08:03:17Z")
Hi @Colin, 2 questions: - How are the models chosen for the subagents? - Do we have any control over which models are allowed or preferred? ---
**Author:** ![Colin](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/colin/32/90452_2.png) [@Colin](https://forum.cursor.com/u/Colin)\ **Post date:** [April 28, 2026, 2:57pm UTC](https://forum.cursor.com/t/multitask-in-agents-window/158955/8 "2026-04-28T14:57:24Z")
> [@Tomas\_Nagy](#): > > 2 questions: > > - How are the models chosen for the subagents? > - Do we have any control over which models are allowed or preferred? In most cases, these subagents just use the same model as the parent agent. There are a few corner cases (BYOK, request-based pricing) where this is not the case. You can also request what model is used in natural language! ![Screenshot 2026-04-28 at 16.57.09](https://us1.discourse-cdn.com/cursor1/original/3X/1/8/185b9b465d17516e0bddc6f4e4e6abd31f6593c7.png) ---
**Author:** ![llinfeng](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/llinfeng/32/13644_2.png) [@llinfeng](https://forum.cursor.com/u/llinfeng)\ **Post date:** [May 6, 2026, 8:13am UTC](https://forum.cursor.com/t/multitask-in-agents-window/158955/9 "2026-05-06T08:13:08Z")
@Colin I’d like to ask for clarification on how BYOK works as an edge case for`/multitask`. Specifically, I’m using `/multitask` through the Cursor GUI with a BYOK model, `qwen3.6-plus`, which depends on my custom “OpenAI API Key” setting. However, Cursor seems to repeatedly turn off that custom OpenAI-compatible API key. As a result, some `/multitask` runs fail because the model is no longer available. In my recent testing, roughly 1 out of 4 `/multitask` runs failed for this reason. Is BYOK expected to be supported reliably inside `/multitask`, or is this currently a known limitation/edge case? ---
**Author:** ![Colin](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/colin/32/90452_2.png) [@Colin](https://forum.cursor.com/u/Colin)\ **Post date:** [May 6, 2026, 2:27pm UTC](https://forum.cursor.com/t/multitask-in-agents-window/158955/10 "2026-05-06T14:27:18Z")
Hi @llinfeng! My understanding was that BYOK (overriding the OpenAI base URL) does not work with subagents, but sounds like I might be wrong! > [@llinfeng](#): > > However, Cursor seems to repeatedly turn off that custom OpenAI-compatible API key. As a result, some `/multitask` runs fail because the model is no longer available. This is a bug that should be fixed in 3.3 (rolling out now). ---
**Author:** ![llinfeng](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/llinfeng/32/13644_2.png) [@llinfeng](https://forum.cursor.com/u/llinfeng)\ **Post date:** [May 7, 2026, 8:21am UTC](https://forum.cursor.com/t/multitask-in-agents-window/158955/11 "2026-05-07T08:21:37Z")
@Colin Yeah, I have seen subagents launch when using a BYOK model in Planning mode. However, I still run into some limitations. For example, with qwen3.6-plus, Cursor sometimes gets stuck in the “Reconnecting” state for no apparent reason. Restarting the Cursor GUI usually resolves it. Btw, could you clarify what’s being fixed here? > This is a bug that should be fixed in 3.3 (rolling out now). Specifically, I’m now on version 3.3.16, and I’m glad to report that the OpenAI API Key toggle didn’t get switched off once during a full workday 🙂 ---
**Author:** ![Colin](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/colin/32/90452_2.png) [@Colin](https://forum.cursor.com/u/Colin)\ **Post date:** [May 7, 2026, 9:02am UTC](https://forum.cursor.com/t/multitask-in-agents-window/158955/12 "2026-05-07T09:02:55Z")
The toggling off repeatedly is the thing that was fixed! With that fixed, wonder if you’re still facing an issue here? > [@llinfeng](#): > > Cursor sometimes gets stuck in the “Reconnecting” state for no apparent reason. ---
**Author:** ![llinfeng](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/llinfeng/32/13644_2.png) [@llinfeng](https://forum.cursor.com/u/llinfeng)\ **Post date:** [May 7, 2026, 9:35am UTC](https://forum.cursor.com/t/multitask-in-agents-window/158955/13 "2026-05-07T09:35:19Z")
Cool, thanks for confirming! > With that fixed, wonder if you’re still facing an issue here? > > > Cursor sometimes gets stuck in the “Reconnecting” state for no apparent reason. Nope, the “Reconneting” thing was actually observed on version 3.3.16, where restarting Cursor GUI and launching into the same workspace resolved this connection issue. * * * This being said, though, is there a best practice guide on troubleshooting BYOK connection issue, with Cursor GUI (and maybe with the Agent on CLI as well)? @Colin Thanks again! ---
**Author:** ![Colin](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/colin/32/90452_2.png) [@Colin](https://forum.cursor.com/u/Colin)\ **Post date:** [May 7, 2026, 7:36pm UTC](https://forum.cursor.com/t/multitask-in-agents-window/158955/14 "2026-05-07T19:36:38Z")
If you face it again and are able to collect a [Request ID](https://cursor.com/help/troubleshooting/reporting-bugs#what-is-a-request-id), that would be ideal! ---
**Author:** ![cxmplex](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/cxmplex/32/73179_2.png) [@cxmplex](https://forum.cursor.com/u/cxmplex)\ **Post date:** [May 17, 2026, 4:26pm UTC](https://forum.cursor.com/t/multitask-in-agents-window/158955/15 "2026-05-17T16:26:38Z")
I haven’t found a good use for this yet. I’ve always found it better to use subagents that are on their own worktrees. I have the model run them with run\_in\_background: False so the model waits on them to finish, and I specify to launch them all with the same request, so that they’re done in parallel and it blocks on that request. Each subagent creates its worktree, receives its prompt, and gets to work. Once all 3 finish, the model that was running it applies the changes from each after reviewing them. When should I be using this? Is it just an alternative for people who don’t want to use subagents or separate chats w/ worktrees? ---
**Author:** ![Bakhtiyor\_Akhatov](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/bakhtiyor_akhatov/32/109086_2.png) [@Bakhtiyor\_Akhatov](https://forum.cursor.com/u/Bakhtiyor_Akhatov)\ **Post date:** [May 19, 2026, 11:53pm UTC](https://forum.cursor.com/t/multitask-in-agents-window/158955/16 "2026-05-19T23:53:00Z")
Cool feature. But how do we know if multitask is necessary or an overkill? Is it useful in multi project environments? ---
**Author:** ![MFeighery](https://avatars.discourse-cdn.com/v4/letter/m/ac91a4/32.png) [@MFeighery](https://forum.cursor.com/u/MFeighery)\ **Post date:** [May 20, 2026, 10:16pm UTC](https://forum.cursor.com/t/multitask-in-agents-window/158955/17 "2026-05-20T22:16:06Z")
Can we add a button or make it automatic that in multitask mode the sub agents will auto split into their own panes. Tracking what’s being done is very hard without that. Although I did find that multi panel view to be quite buggy (not scrolling properly and not sticking to the bottom of the chat) so that needs work as well before I’d consider this feature regularly useable. ---
**Author:** ![ADTC](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/adtc/32/86671_2.png) [@ADTC](https://forum.cursor.com/u/ADTC)\ **Post date:** [May 21, 2026, 8:16am UTC](https://forum.cursor.com/t/multitask-in-agents-window/158955/18 "2026-05-21T08:16:11Z")
Can a second response of the main agent kick off a new sub-agent which still reuses the context of a previously run sub-agent? (Or in layman’s terms, it would feel like you’re asking that previously finished sub-agent to continue work using a new prompt additional to existing context, instead of creating a new sub-agent with a clean context.) PS: @Bakhtiyor_Akhatov try to imagine if your task can be split up into independent mini tasks spread out across a team of humans (or minions if you’re Gru), and all those mini-work are integrated back into a single body of large work. If it makes sense for the task at hand, then multitask can be useful. ---
**Author:** ![Robert\_Lura](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/robert_lura/32/109291_2.png) [@Robert\_Lura](https://forum.cursor.com/u/Robert_Lura)\ **Post date:** [May 21, 2026, 1:29pm UTC](https://forum.cursor.com/t/multitask-in-agents-window/158955/19 "2026-05-21T13:29:51Z")
I found this very useful for working on large tasks without using the whole context window for the same agent. So far this has been great. I am looking forward to future updates on this feature 👍 ---
**Author:** ![luca\_suanez](https://avatars.discourse-cdn.com/v4/letter/l/67e7ee/32.png) [@luca\_suanez](https://forum.cursor.com/u/luca_suanez)\ **Post date:** [May 25, 2026, 11:57pm UTC](https://forum.cursor.com/t/multitask-in-agents-window/158955/21 "2026-05-25T23:57:46Z")
How do we go from plan mode to multitask mode? Seems like no matter what when I hit build it just defaults back to agent mode with no tag. ---
**Author:** ![cxmplex](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/cxmplex/32/73179_2.png) [@cxmplex](https://forum.cursor.com/u/cxmplex)\ **Post date:** [May 26, 2026, 3:25am UTC](https://forum.cursor.com/t/multitask-in-agents-window/158955/22 "2026-05-26T03:25:28Z")
Yes I would like to try multi tasking plan items, it does not seem clear how to do this if its possible ---
**Author:** ![Colin](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/colin/32/90452_2.png) [@Colin](https://forum.cursor.com/u/Colin)\ **Post date:** [May 26, 2026, 12:20pm UTC](https://forum.cursor.com/t/multitask-in-agents-window/158955/23 "2026-05-26T12:20:14Z")
Hey @luca_suanez / @cxmplex ! Great question. If you use “Build in parallel” on a plan rather than the default (Build Locally), it will kick off multitask mode! ![image](https://us1.discourse-cdn.com/cursor1/original/3X/e/2/e2a34bb63bf5b9927e5fc2ea97599145a2b4614c.png) ---
**Author:** ![Colin](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/colin/32/90452_2.png) [@Colin](https://forum.cursor.com/u/Colin)\ **Post date:** [May 26, 2026, 12:21pm UTC](https://forum.cursor.com/t/multitask-in-agents-window/158955/24 "2026-05-26T12:21:37Z")
> [@Bakhtiyor\_Akhatov](#): > > Cool feature. But how do we know if multitask is necessary or an overkill? Is it useful in multi project environments? Multitask is worth it when there are genuinely independent workstreams or when you want the foreground free for follow-up questions while work happens in the background. It’s probably overkill for anything that shares context or is a single coherent task. [Next page](https://forum.cursor.com/t/multitask-in-agents-window/158955.md?page=2)