Cursor's planner-worker agents built a web browser from scratch in about a week
Cursor tested long-running autonomous coding with a hierarchy of planner agents that create tasks and worker agents that just complete them. The headline project was a browser engine, published as FastRender.
The problem
Single agents stall or lose track on very large codebases. Cursor tried to find an agent structure that keeps hundreds of agents productive on one repository for weeks.
How they did it
- Planner agents explore the codebase, create tasks and start sub-planners for specific areas.
- Worker agents focus on finishing their assigned task and don't coordinate with each other.
- Every agent pushes to the same branch.
Results
- The agents ran for close to a week, writing over 1 million lines of code across 1,000 files.
- Hundreds of workers run concurrently, pushing to the same branch with minimal conflicts.
- Other runs included a Solid-to-React migration in Cursor's own codebase (+266K/-193K edits), which the team says still needs careful review.
As reported by the source (Cursor Blog); AgentGid did not measure these figures.
This is a research-scale experiment, not a workflow to copy: running hundreds of concurrent agents for a week suits teams with deep engineering skill and a large model budget. Cursor's plans bill usage at model API rates with on-demand overage, so costs at that scale could climb fast. For smaller-scale agent work, Zed (open source, Free + $10/mo) lets you bring your own API keys.
The agent used here
Similar use cases
How National Australia Bank sped up legacy migrations with Cursor
NAB engineers used Cursor to understand and migrate legacy Silverlight/.NET and Assembly systems, and to build a new payment app. As reported by Cursor, delivery was well ahead of…
As reported by Cursor: NAB 'originally scoped six months of work' for the BizCalc migration and now expects it to finish in two months, 'a 3x improve…
Turn a Figma frame into code by connecting the Figma MCP server
Figma's hosted MCP server gives a coding agent the variables, components and layout data of a frame you link to, so the code it writes matches the design.
The agent gets design context such as variables, components and layout for the selected frame.
How PlanetScale uses Bugbot as an automated first pass on code review
PlanetScale added Cursor's Bugbot to its pull request workflow to catch logic issues before merge. As reported by Cursor, engineers act on most of its comments.
As reported by Cursor: 'roughly 80% of Bugbot comments are addressed before merge time'.
Guides
Best AI Agents in 2026: Live Rankings by Category
The leading AI agents for coding, design, research, data, marketing, sales, support, HR, finance, legal, DevOps and security, ranked by public usage data that refreshes daily, with prices and free options.
What Is an AI Agent? A Practical Explanation With Real Examples
What makes software an AI agent, how agents differ from chatbots and plain language models, the main types in use today and how to judge one.
Best AI Coding Agents in 2026: Ranked by Usage, Benchmarks and Price
The AI coding agents developers use most, with live download and install numbers, benchmark results, entry prices and a way to choose between terminal, IDE and cloud agents.
Claude Code vs Codex vs Cursor: Usage, Price and Benchmarks Compared
The three most discussed AI coding agents side by side on live data: downloads, installs, GitHub activity, release cadence, benchmark results and pricing.