---
title: "Build agents that run automatically"
description: "Cursor Automations introduces always-on agents that run on schedules or react to events from Slack, Linear, GitHub, PagerDuty, or custom webhooks. Each invocation spins up a cloud sandbox, uses configured models and MCPs, verifies its output, and can draw on memory from past runs. The product supports review and monitoring workflows, including security audits on pushes to main, risk-based codeowner assignment, and PagerDuty-driven incident investigation that proposes fixes. Other automations generate weekly repository digests, add tests after merged code, triage Slack bug reports through Linear, and assemble cross-tool dashboards. Examples from Cursor and Rippling report faster incident response and reduced repetitive work, while Runlayer describes a software factory built with Runlayer MCP and plugins."
---

# Build agents that run automatically

[Cursor](https://yomu.fyi/company/cursor) · Jack Pertschuk, Jon Kaplan & Josh Ma · Mar 5, 2026

**Type:** Announcement

## Summary

Cursor Automations introduces always-on agents that run on schedules or react to events from Slack, Linear, GitHub, PagerDuty, or custom webhooks. Each invocation spins up a cloud sandbox, uses configured models and MCPs, verifies its output, and can draw on memory from past runs. The product supports review and monitoring workflows, including security audits on pushes to main, risk-based codeowner assignment, and PagerDuty-driven incident investigation that proposes fixes. Other automations generate weekly repository digests, add tests after merged code, triage Slack bug reports through Linear, and assemble cross-tool dashboards. Examples from Cursor and Rippling report faster incident response and reduced repetitive work, while Runlayer describes a software factory built with Runlayer MCP and plugins.

## Context

Coding agents have increased the amount of code engineers can produce, while code review, monitoring, and maintenance have not sped up to the same extent. The automations are presented as a way to scale these parts of the software development lifecycle and offload repetitive cross-tool work.

## Approach / What changed

Automated agents run in cloud sandboxes with configured models, MCPs, plugins, instructions, verification, and a memory tool. They can be scheduled or triggered by built-in integrations and custom webhooks, then perform tasks such as reviewing changes, assigning codeowners, investigating incidents, adding tests, triaging bug reports, and compiling summaries.

## Takeaways

- A security review automation runs on every push to main, audits diffs for vulnerabilities, skips issues already discussed in the PR, and posts high-risk findings to Slack.
- Agentic codeowners classifies PR risk using blast radius, complexity, and infrastructure impact; low-risk changes are auto-approved, while higher-risk changes receive up to two reviewers based on contribution history.
- PagerDuty-triggered incident response uses the Datadog MCP to inspect logs and recent code changes, then sends on-call engineers a Slack message with the monitor message and a proposed-fix PR.

**Tags:** [AI Agents](https://yomu.fyi/topic/ai-agents), [Cursor](https://yomu.fyi/topic/cursor), [Incident Response](https://yomu.fyi/topic/incident-response), [MCP](https://yomu.fyi/topic/mcp)

- Source: [Cursor](https://cursor.com/blog/automations)
- Source URL: https://cursor.com/blog/automations
- Ingested by Yomu: 2026-09-02T11:43:58.427Z

[Read original post](https://cursor.com/blog/automations)