This builds on our existing research on multi-agent systems, with a key addition: verifiers. Planners spawn workers that write code and verifiers that run it. If verification fails, the planner spawns a new worker to fix it.
@cursor_ai
-
Cursor uses old Composer models to train new, smarter ones
By
–
We use previous generations of Composer to train future ones. Our autoinstall system has earlier Composer models set up dev environments for RL training. That way, the next generation can focus on learning to solve harder problems.
-
Cursor 3.3 shows agent context usage breakdown for better setup
By
–
You can now see a breakdown of your agent's context usage in Cursor 3.3.
— Cursor (@cursor_ai) 6 mai 2026
Use these stats to diagnose context issues and improve your setup across rules, skills, MCPs, and subagents. pic.twitter.com/lqs2lp8pn2You can now see a breakdown of your agent's context usage in Cursor 3.3. Use these stats to diagnose context issues and improve your setup across rules, skills, MCPs, and subagents.
-
Cursor automatically fixes CI failures with always-on agents monitoring GitHub
By
–
Cursor can now automatically fix CI failures.
— Cursor (@cursor_ai) 5 mai 2026
Set up always-on agents that monitor GitHub, investigate root causes, and open PRs with fixes. pic.twitter.com/5roWAjjkfYCursor can now automatically fix CI failures. Set up always-on agents that monitor GitHub, investigate root causes, and open PRs with fixes.
-
Cursor AI Tests Harness for Models to Improve Speed and Efficiency
By
–
Our agent harness makes models inside Cursor faster, smarter, and more token-efficient. Here's how we test improvements to the harness, monitor and repair degradations, and customize it for different models.
-
Cursor SDK Enables AI Agents for Automated Code Development
By
–
Customers like Rippling, Notion, C3 AI, and Faire are using the Cursor SDK to build custom background agents, take bugs from ticket to merge-ready PR, and maintain self-healing codebases. Learn more:
-
Open-source AI agent starter projects for developers
By
–
We've open-sourced a few starter projects for you to build on: a coding agent CLI, a prototyping tool, and an agent-powered kanban board. Use Cursor to customize them for your use case:
-
Cursor SDK Enables Local and Cloud Agent Deployment
By
–
With the Cursor SDK, you can run agents locally or deploy them in our cloud.
-
Cursor SDK Enables Building AI Agents for Workflows
By
–
We’re introducing the Cursor SDK so you can build agents with the same runtime, harness, and models that power Cursor.
— Cursor (@cursor_ai) 29 avril 2026
Run agents from CI/CD pipelines, create automations for end-to-end workflows, or embed agents directly inside your products. pic.twitter.com/bRcn9xjuVzWe’re introducing the Cursor SDK so you can build agents with the same runtime, harness, and models that power Cursor. Run agents from CI/CD pipelines, create automations for end-to-end workflows, or embed agents directly inside your products.
-
Cursor 3.2 Releases New Agents Window Features
By
–
Download Cursor 3.2 to try these new features in the agents window: