Cursor launches Rollouts and Security Review bots for production changes
Cursor’s September 23, 2026 release adds Rollouts for deployment health monitoring and Security Review for exploitable bugs on pull requests.
Editorial Team
The Authority AI Tools editorial team maintains this directory using vendor documentation, dated source checks, product changelogs, and clearly identified hands-on observations where available.
Cursor has launched two bots for the last mile of shipping code: Rollouts watches a change from pull request to production, while Security Review looks for exploitable bugs in pull requests. Cursor says both are available on Teams and Enterprise plans.
The AI-native code editor with $1B+ ARR, 25+ models, and background agents on dedicated VMs
Rollouts connects pull requests to production signals
Rollouts attaches a monitor to a pull request and creates a monitoring plan from the diff, the systems it touches, the intended effect, and the signals that can verify the change. Teams can edit that plan in the pull request before deployment.
After a deploy event, Rollouts compares logs, metrics, and traces against the pre-deploy baseline. It tracks environments separately, so a change can be healthy in staging and still show a regression in production. Its verdict can be verified healthy, regression detected, or inconclusive.
When it finds a regression, Rollouts names the suspected change and notifies the author. Cursor says it can also open a revert pull request for review or hand the finding to a cloud agent for a fix, but it does not merge or roll back on its own.
Rollouts connects to Cursor Origin or GitHub for source control, a continuous-delivery system for deploy events, and telemetry providers such as Datadog. Cursor says feature-flag integration is coming later.
Security Review focuses on exploitable bugs
Security Review reads each non-draft pull request in the context of the codebase and posts one review comment about exploitable issues. Cursor distinguishes this from Bugbot: style and general quality feedback remain with Bugbot.
The initial checks cover injection across SQL, command, and template surfaces; authentication and authorization bypasses; secrets and credentials; SSRF and unvalidated redirects; unsafe deserialization; and dependency changes that introduce known vulnerabilities. Each finding includes a severity, an attack path, and a proposed fix.
Teams can add rules for repository-specific constraints, such as routing external calls through a particular client or preventing request handlers from querying certain tables. Dismissing a finding with a reason tells Security Review not to raise it again on that pull request.
Availability and a sensible rollout
Enable either bot from Cursor’s automations dashboard. Cursor says the first ten days include usage credits for real changes, with roughly 50 changes for Teams customers and 500 for Enterprise customers.
These bots connect automation to production and security decisions, so start with a repository that has reliable deployment telemetry and a review policy for proposed fixes. Confirm the telemetry signals, pull-request permissions, and rollback approval path before allowing an agent to open remediation work automatically.
Sources
- Cursor — “Rollouts and Security Review” (September 23, 2026): https://cursor.com/changelog/rollouts-and-security-reviewer
- Cursor — “Bots for the last mile: Rollouts, Security Review”: https://cursor.com/blog/rollouts-and-security-reviewer
- Cursor on X — official product updates: https://x.com/cursor_ai
Tools Mentioned in This Article
Free Resource
2026 AI Coding Tools Comparison Chart
Side-by-side comparison of features, pricing, and capabilities for every major AI coding tool.
No spam, unsubscribe anytime.
Workflow Resources
Cookbook
AI-Powered Code Review & Quality
Automate code review and enforce quality standards using AI-powered tools and agentic workflows.
Cookbook
Building AI-Powered Applications
Build applications powered by LLMs, RAG, and AI agents using Claude Code, Cursor, and modern AI frameworks.
Cookbook
Building APIs & Backends with AI Agents
Design and build robust APIs and backend services with AI coding agents, from REST to GraphQL.
Cookbook
Debugging with AI Agents
Systematically debug complex issues using AI coding agents with structured workflows and MCP integrations.
MCP Server
AWS MCP Server
Interact with AWS services including S3, Lambda, CloudWatch, and ECS from your AI coding assistant.
MCP Server
Context7 MCP Server
Fetch up-to-date library documentation and code examples directly into your AI coding assistant.
MCP Server
Docker MCP Server
Manage Docker containers, images, and builds directly from your AI coding assistant.
MCP Server
Figma MCP Server
Access Figma designs, extract design tokens, and generate code from your design files.
Frequently Asked Questions
What is Cursor launches Rollouts and Security Review bots for production changes?
Related Articles
Codex 0.157.0 adds GPT-6 models, fullscreen transcripts, and smoother sessions
OpenAI Codex CLI 0.157.0 adds GPT-6 Sol and Luna, automatic background-server startup, fullscreen transcripts, conversation forking, and remote-session imports.
Read more →Product UpdatesGemini CLI 0.61.0 hardens sandbox boundaries and prompt-injection defenses
Google’s September 23, 2026 Gemini CLI 0.61.0 release hardens filesystem isolation, blocks indirect prompt injection paths, preserves versioned model IDs, and improves agent-loop reliability.
Read more →Product UpdatesOpenAI GPT-6 Sol and Luna bring lower-cost models and stronger prompt caching
OpenAI’s September 22, 2026 GPT-6 Sol and Luna release adds lower-cost API model IDs, Codex and ChatGPT Work access, and a prompt-caching dashboard.
Read more →