Cursor's Support Team Uses Its Own AI Tool to Handle 75% of Interactions, Achieving Up to 10x Engineer Productivity
Summary
Cursor's support team is using its own AI tool to handle over 75% of interactions, achieving up to 10x engineer productivity by unifying code, logs, Slack threads, and real-time database context into a single session powered by MCP servers, slash commands, and parallel-running subagents.
Key Points
- Cursor's technical support team uses Cursor itself for over 75% of support interactions, boosting engineer throughput by 5–10x by consolidating code, logs, team knowledge, and past conversations into a single session.
- MCP servers are integrated to pull real-time context from databases, Datadog logs, Slack threads, Linear tickets, and internal documentation directly into investigations, eliminating the need to jump between multiple tools.
- Support workflows are further accelerated through slash commands, automated Rules and Skills, and parallel-running subagents that simultaneously investigate logs, mine known issues, draft bug tickets, and write customer replies in one unified output.