Last checked: 21 Oct 2026. The facts below come from Cursor's own documentation on cloud agents, automations, environment setup and security and network settings, its pricing pages, changelog, release notes, Cursor Learn and Marketplace templates, and one published benchmark from LinearB, each linked where it is used.
Last updated: 21 Oct 2026.
Start with a job that is narrow, happens often, already has a number attached to it and can be judged within a few weeks. Let the first version report its findings to a person instead of changing code, and add write access, approvals and broader triggers only once you have seen what it produces. Many of Cursor's own templates start the same way.
How cloud agents and automations relate
A cloud agent is Cursor's coding agent running somewhere other than the developer's laptop. Cursor's documentation says cloud agents "run in isolated VMs in the cloud with full development environments instead of on your local machine", and that they were formerly called Background Agents. Each agent can build, test and run the software it has changed, and hands back screenshots, videos and logs showing how it checked its work.
When a cloud agent has finished, Cursor's security overview says it "pushes its branch and opens a draft pull request for a human to review before anything merges".
An automation is a cloud agent with a trigger. In Cursor's words, automations "run cloud agents in the background, either on a schedule or in response to events" from source control, Slack, webhooks, Linear and other services. Cursor launched them on 5 Mar 2026. Each has a trigger, a prompt, optional tools and a repository setting. Cursor's reference says you can create one in the Agents Window, at cursor.com/automations, from a Marketplace template, or with the built-in /automate skill in a local agent session, where you describe the workflow in plain language and Cursor configures the triggers, instructions and tools for you.
Ways to start a cloud agent by hand
As at 21 Oct 2026, Cursor's overview lists the desktop app, web, iOS, an @cursor mention in Slack or Linear, an @cursor comment on GitHub or Bitbucket, and the API. The CLI can hand a conversation to a cloud agent if you prefix a message with &. The Cloud Agents API is in public beta, and Cursor launched its SDK in public beta on 29 Apr 2026. Our guide to Cursor's Agents Window, CLI and cloud agents covers which surface suits which job and how to move work between local and cloud.
What can trigger an automation
The automations reference lists the following as at 21 Oct 2026. Cursor added five GitHub triggers and a Slack emoji trigger in Cursor 3.8 on 18 Jun 2026, so check the reference before you design around a gap.
| Trigger | Events | Limits worth knowing |
|---|---|---|
| Schedule | Preset options or a cron expression | Runs may start late but never before the set time |
| Source control | Draft opened, pull request opened (including a draft marked ready for review), pushed or merged, push to branch, comment added. GitHub adds CI completed, workflow run completed, labels and review events. GitLab adds label changed and approved, and Bitbucket Cloud adds approved | GitHub, GitLab and Bitbucket Cloud only. Bitbucket Server and Data Center are not supported. A repository is required. Pull request triggers do not run on pull requests from forks, except pull request merged |
| Slack | New message in channel, emoji reaction, channel created | Public channels only. Without a filter, only top-level messages fire. A keyword or regex filter also admits threaded replies |
| Webhook | A POST to a private endpoint | Save the automation first to get the URL and its API key |
| Linear | Issue created, status changed, end of cycle | |
| Sentry | Issue created, issue updated, any issue event | |
| PagerDuty | Incident triggered, acknowledged or resolved, or any incident event | Only team admins can connect it |
An automation can have more than one trigger and runs when any of them fires. Cursor's release notes record a fix in the week of 28 Sep 2026 so that an automation with several schedules runs on every one, not only the first. The notes for the week of 5 Oct 2026 also describe automations that listen to a Microsoft Teams channel, but the trigger reference does not list Teams, so check the automation editor if you need it.
Two settings decide how much an automation can do. The repository setting can be none, one or several. With none, the agent "does not clone code" and cannot edit code or open pull requests. That is the default for Slack and schedule triggers, while source control triggers need a repository. The tools list covers opening pull requests (on by default), commenting, requesting reviewers, Slack, MCP servers, memories and computer use.
Choosing your first automation
The Cursor pages we read for this post give advice on writing prompts and offer templates, but no method for choosing or measuring a first automation. What follows is our own approach. We use Cursor in our own engineering, and this is how we scope automation work generally. Our guide to where to start with AI agents applies the same thinking outside engineering. We score each candidate on five questions:
- Scope. Does it touch one repository and produce one kind of output?
- Volume. Will you have dozens of runs to judge within a few weeks?
- Baseline. Do you already know today's number, such as how long failed builds sit before someone looks?
- Speed to prove. Can a reviewer tell in minutes whether a run was useful?
- Cost of a bad run. If the agent is wrong, does someone read a poor summary, or does bad code reach a branch people trust?
The fifth question is why we start with report-only runs. Cursor's own template prompts lean the same way. The failed GitHub Actions template says "Default to triage only". The critical bugs template says "When in doubt, report your findings in Slack without opening a PR". Cursor's prompt advice asks writers to "Set a quality bar for when the agent should open a pull request, comment, or do nothing". Write that bar before the first run.
The Cursor Marketplace automations listing linked to 27 templates on 21 Oct 2026. These four make reasonable first candidates to test against the five questions:
| Candidate | Trigger shown on the template | Default output | What you would measure |
|---|---|---|---|
| Daily change digest | Schedule, every day | One Slack message citing commits and pull requests | Whether people read it and stop asking for status updates |
| Failed GitHub Actions triage | Workflow run failed or cancelled | Triage only, with a fix only at high confidence | Time from a failed run to a known cause |
| Sentry issue investigation | Any issue event | Analysis posted to Slack when a fix is not high confidence | Time to first triage and share of findings an engineer agrees with |
| Vulnerability review on pull requests | Pull request opened or pushed | Pull request comments and Slack, no code changes | Share of comments accepted, and review time per pull request |
The Sentry template and the critical bugs template both open a pull request when the agent is confident of a fix, so a strictly report-only first run means editing the prompt or turning pull request creation off. Which candidate suits you depends on where your volume and existing numbers are. Bugbot, Cursor's managed review agent, has its own calibration questions, covered in our post on AI code review with Cursor Bugbot. Once a report-only automation has earned trust, our post on building a bug-to-pull-request pipeline with Cursor covers adding Bugbot, the Security Reviewer and approval agents one stage at a time.
What memories are for
Memories let an automation keep notes between runs. Cursor's automations reference says each memory is a named entry (MEMORIES.md by default) held outside the agent's working filesystem and shared by every run of the same automation. They are on by default, can be switched off, and can be viewed, edited and deleted from the tool configuration. Cursor's critical bugs template shows a plain use: it records each bug already reported with its pull request, so it does not open a duplicate, and removes the entry once the pull request merges. The risk with untrusted input is covered under what to hold back.
Set up the environment before the automation
Cursor's setup guide says "Environment setup is the most important step to improve the effectiveness of your cloud agents", because an agent that cannot run tests, query services or reach APIs "cannot close the loop on its work". Every automation inherits that environment.
Cloud agents run on isolated Ubuntu machines. Cursor's setup guide describes two main routes, agent-led setup from the Cloud Agents dashboard or a Dockerfile referenced in .cursor/environment.json, and its cloud agent overview also lists a saved snapshot, which can be named in the same file. Cursor says agent-led setup takes less than ten minutes. The parts that matter:
installruns when Cursor creates a Build, so dependencies are ready before an agent starts. It must be idempotent, and long-running processes do not belong in it.startruns after an agent boots from a Build, followed by anyterminals, which run app processes in atmuxsession shared by you and the agent. Builds preserve disk state only, so services have to start here.- Builds. Cursor's Builds page says "New agents, automations, and code reviews start from the active Build". A failed Build does not replace the working one, and Builds cost nothing extra. Since the week of 28 Sep 2026, Cursor's cloud agent release notes say environment builds can no longer be turned off.
- Secrets are injected as environment variables when an agent starts, so running agents do not pick up new ones. Runtime secrets are hidden from the agent but still visible to anyone using the agent's terminal, and Cursor recommends short-lived OIDC tokens over long-lived keys.
Cursor recommends a section in AGENTS.md headed something like "Cursor Cloud specific instructions", and its best practices page makes a point we agree with: "If it is hard for a human developer to test locally, it will also be hard for an agent." Expect environments to need upkeep. If your repositories are not ready for this, the groundwork is in our guide to rolling out Cursor to an engineering team.
How to tell whether it is working
Take the baseline before you switch the automation on. Afterwards, measure the thing the automation was meant to change: time to first triage, the share of its comments engineers accept, or the share of its pull requests that merge. Run counts tell you it is busy, and say nothing about whether it helps. Our post on measuring whether AI is actually working covers the general method.
Cursor gives you some raw material. The built-in Cursor Cloud MCP can list runs filtered by source, status, date, code changes and pull request creation, along with transcripts and setup logs. Team admins see runs across the team, and anyone else sees only their own. None of that tells you whether the work saved anyone time, which is your baseline's job.
Merge rate by origin is worth tracking once an automation opens pull requests. LinearB's 2026 benchmark of 2.7 million pull requests (February to May 2026) reports that among its top 10% of organisations, 79% of agent-opened pull requests merged within 30 days against 92% for human-only ones. LinearB sells engineering metrics software, calls the figures correlational and is not measuring Cursor specifically, and we found no description of how it identified agent-opened pull requests. Its explanation is that pull requests nobody owns tend to sit unmerged. We take one practical point from it: give every automation's output a named owner.
What to hold back at first
Each of these can be switched on later, once the report-only version has earned it. For the full security picture, see our post on Cursor cloud agent security.
- Approvals. With approvals enabled an automation can approve pull requests. Cursor's managed PR Routing & Approval agent says plainly that "It does not replace a full code review". Let branch protection in your source control decide what can merge.
- Pull request creation. It is on by default. Turn it off for a report-only first version.
- Memories on untrusted input. Memories are on by default and persist across runs (see what memories are for, above). Cursor warns that inputs "may lead to misleading or malicious memories" that affect later runs, so switch them off where an automation reads input from outside the team.
- Broad MCP servers. Connecting one gives the agent every tool that server exposes. On Enterprise plans, admins can control which MCP servers team members may use and set tool controls for each server.
- Wide Slack triggers on code-changing automations. Slack triggers see public channels, so anyone who can post there can start a run.
- Open network access. Cloud agents have internet access by default and auto-run terminal commands, and Cursor names the resulting prompt injection and data exfiltration risk. Allowlists are available, and locking them is Enterprise only.
Decide early who owns the automation's identity. An automation runs as its creator or, if a team admin chooses, as a service account, which stops working if the account is archived or deleted. Running as you opens pull requests from your GitHub account, and running as the service account opens them as cursor. If the automation uses a webhook, regenerate its webhook API key after switching it to a service account. GitHub comments, approvals and reviewer requests appear as cursor and Slack messages come from the Cursor bot, so keep your own record of which automation did what. Team admins can view and disable even private automations.
Who pays, and which plans include it
The identity choice also decides the bill: you pay when it runs as you, and the team's usage pool pays when it runs as a service account. Cursor's cloud agent page says cloud agents are charged at API pricing for the selected model, while its models and pricing page describes a weekly usage pool for Cursor models shared across the editor, CLI and Cloud Agents. Neither publishes a per-run cost, so watch real usage in the first weeks. When a team limit is reached, paid additional usage pauses until next month or until an admin raises it. Our post on Cursor spend controls and model choice covers capping it.
As at 21 Oct 2026, Plus excludes cloud agents and automations, Premium adds them, and Teams and Enterprise include them. Legacy Pro, Pro+ and Ultra plans include them too. Cursor is now sold directly by the vendor as part of The X Subscription, and its pricing page shows prices excluding VAT. Our guide to SpaceX Super Intelligence (SpaceXSI) for UK business explains how Cursor, Grok and Grok Bot fit together, including Cursor's acquisition by SpaceX on 14 Aug 2026 and the contract changes that followed.
Common questions
What is the difference between a Cursor cloud agent and a Cursor automation?
A cloud agent is Cursor's coding agent running in its own isolated virtual machine instead of on a developer's laptop, started by a person from the app, Slack, a pull request comment, the API or another route. An automation starts cloud agents for you, on a schedule or when an event happens in source control, Slack, a webhook, Linear, Sentry or PagerDuty.
What should a team automate first with Cursor?
Cursor's documentation offers templates and prompt advice but no method for choosing. Our view is to pick a job that touches one repository, fires often, already has a measured baseline and can be judged quickly, and to start it as report-only. A daily change digest, triage of failed GitHub Actions runs, or investigation of Sentry issues are reasonable candidates, and Cursor's own templates for these default to reporting before changing code.
Can Cursor automations run on GitLab or Bitbucket?
Yes, on GitLab and Bitbucket Cloud as well as GitHub, with the same core pull request and push triggers. GitLab adds label changed and approved, Bitbucket Cloud adds approved, and GitHub has the most, including CI and review events. Bitbucket Server and Data Center are not supported, and pull request triggers do not run on pull requests from forks, except pull request merged.
Who can trigger a Cursor automation, and who pays for it?
Anyone who can cause the trigger event can start a run, so with a Slack trigger that means anyone who can post in the connected public channel. An automation runs either as its creator, who is billed, or as a service account chosen by a team admin, which bills the team's usage pool. Automations are billed based on cloud agent usage, and Cursor's pricing pages describe the current model.
Do Cursor cloud agents store our code?
Yes, while they run. Cursor says code runs in isolated VMs in its AWS infrastructure and is stored on VM disks while the agent is accessible. Cloud agents work with Privacy Mode but not with the legacy no-storage mode. With Privacy Mode on, Cursor says it never trains on your code. Conversation history is kept indefinitely by default, and Enterprise admins can cap retention at 90 days. As at 21 Oct 2026, Cursor offers US-only data residency to Enterprise customers and EU and UK inference-only coverage on request, with no UK storage region stated.
If you want help choosing and setting up your first automation, including the environment it depends on, see our SpaceXSI and Cursor implementation service and Request a Quote.
John Kelleher holds the SpaceX Super Intelligence Partner Network Accreditation: Forward Deployed Engineer, and the SpaceX Super Intelligence Technical Architect Accreditation.
Get new articles by email
Practical guides from the SpotDev team, when we publish them.
By submitting this form, you consent to us sending you emails with our latest content. Privacy Policy



