Interact with agent-created visualizations in canvases

Summary

Cursor introduces canvases, allowing agents to represent information through interactive visual interfaces instead of chat text or markdown. In the Agents Window, these durable artifacts sit alongside tools including the terminal, browser, and source control, and agents can build dashboards, PR review interfaces, architecture diagrams, and eval-failure investigations. Canvases use a React-based UI library with first-party tables, boxes, diagrams, and charts, plus existing Cursor components such as diffs and to-do lists; skills can teach agents to create specific canvas types. Cursor reports that combining observability data from Datadog, Databricks, and Sentry MCPs with local debug files makes time-series analysis easier, while eval skills group rollout failures to expose hidden harness bugs. The company is also using canvases to visualize autoresearch progress and current hypotheses during client-performance experiments.

Takeaways

1. 1

   Canvases are durable artifacts in Cursor’s Agents Window and can combine data from sources such as Datadog, Databricks, Sentry MCPs, and local debug files in a single visualization.

2. 2

   A Cursor skill can read all rollouts in an eval, group failures, and build a canvas for investigating failure clusters and previously hidden harness bugs.

3. 3

   Cursor uses canvases during autoresearch experiments so users can monitor progress and see the hypothesis currently being tested while optimization work runs.