Superpower Daily
OpenClaw Agent Canceled a Gym Waitlist Booking, Moving Its User...Nvidia Takes a Minority Stake in Cloverleaf to Push AI Data-Cen...SemiAnalysis Says AgentX Drove 50-Plus Upstream Fixes for AI Ag...MiniMax H3 Opens Its Video Weights, but Not Where Many Develope...Higgsfield Puts Its Video Engine Behind Grok Bot—and Keeps the...Anthropic Gives Enterprise Teams Mythos 5’s Bug Hunt, Not Its P...OpenClaw Agent Canceled a Gym Waitlist Booking, Moving Its User...Nvidia Takes a Minority Stake in Cloverleaf to Push AI Data-Cen...SemiAnalysis Says AgentX Drove 50-Plus Upstream Fixes for AI Ag...MiniMax H3 Opens Its Video Weights, but Not Where Many Develope...Higgsfield Puts Its Video Engine Behind Grok Bot—and Keeps the...Anthropic Gives Enterprise Teams Mythos 5’s Bug Hunt, Not Its P...
Productspublished

Cursor Gives Cloud Agents a Way to Come Back to the Job

The new workflow controls connect coding work to pull-request activity, Slack threads and schedules, while keeping subscriptions limited to cloud agents for now.

By 2 min read
Cursor Gives Cloud Agents a Way to Come Back to the Job
Sign in to save and react

Listen to this story

The audio brief

About 1:26
0:001:26
Read transcript
Cursor’s cloud agents can now wait for activity outside the chat, then return to the job when something happens. That turns an agent from a one-shot coding worker into a participant in a longer workflow. Its new Subscriptions can watch pull requests, Slack threads, and scheduled tasks, using events in those systems to trigger another pass. For a pull request an agent creates, the subscription is automatic. The agent can then respond to CI failures and bot comments until the pull request is complete, keeping the work attached to that same code review rather than starting over with a fresh prompt. Cursor is also separating the objective from the operating method. The slash-goal command gives an agent a target it keeps pursuing until completion. Custom Mode preserves a selected skill or playbook in the chat. Used together, they let an agent follow a consistent process while working toward a durable outcome. Goals can also pair with slash-loop for recurring checks, such as fixing flaky tests and getting CI green. For parallel work, subagents now receive their own virtual machines, isolated project copies, and clean context. That lets them test changes or investigate bugs without colliding with the parent agent or other workers. And if a human sends a correction mid-task, the steering message waits for the next tool call instead of interrupting the current action. The key constraint is that Subscriptions and this event-driven workflow currently work only with Cursor’s cloud agents, not other deployment modes.

Story brief

3 key points

Cursor is turning cloud coding agents into persistent workflow participants rather than one-shot chat workers. Agents can subscribe to pull requests, Slack activity, and scheduled tasks; automatically-created pull requests can remain under agent ownership through CI failures and bot feedback. Goals, Custom Modes, recurring loops, isolated virtual machines for subagents, and queued steering messages extend autonomy...

  1. 01

    Automatically-created pull requests can trigger agents to resolve CI failures and bot comments until completion.

  2. 02

    Subscriptions currently work only with Cursor’s cloud agents, not other deployment modes.

  3. 03

    The /goal command preserves an objective; Custom Mode preserves the operating playbook, and both can be combined.

Cursor’s cloud agents can now wait for activity outside the chat, return to a task when it arrives, and continue working toward a longer-lived objective. The changes push the product beyond a single uninterrupted coding run and toward a workflow that can react to development feedback.

The trigger moves into the work queue

Subscriptions let cloud agents monitor pull requests, Slack threads and scheduled tasks, then wake when activity occurs. That makes an event in a connected workflow—not just a new prompt—the trigger for another pass at a task.

For pull requests an agent creates, the subscription happens automatically. The agent can then work through CI failures and bot comments until the pull request is complete, keeping the pull request as the object of work after its initial creation.

Goals and modes split the task from the playbook

The new /goal command gives an agent an objective it keeps pursuing until completion. A Custom Mode does something different: it pins a selected skill in the chat, keeping that skill active while the agent works.

The two controls can be combined so an agent follows a chosen playbook while pursuing a durable target. Goals can also work with /loop for recurring check-ins; one supplied example is fixing flaky tests and making CI green in a new chat.

Parallel work gets separate computers

Subagents can now run on their own virtual machines. Each machine receives an isolated project copy and clean context, allowing one worker to test a parent agent’s changes in a fresh environment while others handle independent fixes without colliding.

That separation also supports bug-testing swarms, with multiple subagents examining an app in their own environments. It addresses a practical constraint of parallel coding work: workers need room to test or change a project without sharing the same working context.

New direction waits for the next tool call

Users can send a steering message while an agent is working without cutting off its current action. The follow-up waits for the next tool call, creating a defined point at which the agent can receive a correction or new instruction.

A follow-up can be sent with Send now or by pressing Enter twice. Together, the release adds event triggers, durable goals, isolated workers and queued steering to extended cloud-agent work without requiring each step to begin as a fresh chat request.

Related coverage

Continue reading