Cursor Launches Automations to Enable Always-On AI Coding Agents

Cursor introduced Automations on March 5, 2026, a system designed to create agents that operate continuously within coding environments.

The feature allows these agents to activate based on specific schedules or external triggers, such as incoming Slack messages, newly created Linear issues, merged GitHub pull requests, or PagerDuty incidents.

Credit: Cursor

Users can also set up custom events through webhooks to initiate agent actions.

The system addresses imbalances in software development processes where code production has accelerated due to AI tools, but areas like code review, monitoring, and maintenance have lagged.

When an automation triggers, the agent initializes a cloud-based sandbox, executes instructions with configured models and multi-cloud providers (MCPs), and self-verifies its results.

Agents gain access to a memory tool that enables them to retain information from previous executions and refine performance over time.

Review and Monitoring with Automations

Automations facilitate detailed code reviews by identifying and resolving issues ranging from stylistic inconsistencies to security vulnerabilities and performance problems.

Bugbot serves as an early example of this capability, activating on pull request openings or updates to scan for errors, with usage reaching thousands of daily triggers and detecting millions of bugs since its inception.

Specific implementations include a security review agent that activates on every push to the main branch, analyzing diffs for vulnerabilities, bypassing previously discussed issues, and notifying teams via Slack for high-risk findings.

Another variant assigns reviewers to pull requests by evaluating risk factors like blast radius, complexity, and infrastructure effects, auto-approving low-risk changes and logging decisions in tools like Notion for auditing.

For incident handling, an automation responds to PagerDuty alerts by examining logs through Datadog integration, reviewing recent code changes, and delivering summaries plus proposed fixes to engineers via Slack, which has cut response times.

Automations for Routine Tasks

The feature supports automation of recurring chores that integrate data across multiple platforms. One such task generates weekly Slack summaries of repository changes, highlighting merged pull requests, bug fixes, technical debt resolutions, and updates to security or dependencies.

Daily agents assess merged code for test coverage gaps, add tests following established patterns, execute relevant tests, and submit pull requests only if production code remains unchanged unless required. Bug report triage automates duplicate checks, issue creation in Linear, root cause investigations, fix attempts, and threaded responses with summaries.

Real-World Applications at Rippling

Engineers at Rippling have deployed automations for personal and team workflows. One setup aggregates meeting notes, action items, TODOs, and video links from Slack, combining them with GitHub pull requests, Jira issues, and mentions to produce deduplicated dashboards every two hours.

Additional automations handle Jira issue creation from Slack threads, discussion summaries in Confluence, incident triage, weekly status reports, and on-call transitions. Shared automations extend these benefits team-wide.

Trent Haines, Software Engineer at Decagon said:

"I love that automations work for both quick wins and more complex workflows. I can schedule the obvious stuff in seconds, but I still have full flexibility to catch any webhook or plug into custom MCPs when I need to."

And Tim Fall, a Senior Staff Software Engineer at Rippling, said:

"Automations have made the repetitive aspects of my work easy to offload. By making automations to round up tasks, deal with doc updates, and respond to Slack messages, I can focus on the things that matter. Anything can be an automation!"

 While Cursor made its founders billionaires, it is beocoming the backbone of so many other companies.

Building Software Factories with Automations

Cloud agents underpin all automations by using dedicated computers to develop, test, and demonstrate outputs. This setup permits configuration of agent networks that persistently oversee and enhance codebases.

Tal Peretz, Co-founder of Runlayer said:

"We built our software factory using Cursor Automations with Runlayer MCP and plugins. We move faster than teams five times our size because our agents have the right tools, the right context, and the right guardrails."

Users can start using automations feature via cursor.com/automations or templates, with further details available in documentation.