---
title: "How technical support at Cursor uses Cursor"
description: "Cursor’s technical support team treats customer investigations as research problems, using a single session to combine code, logs, team knowledge, and past conversations. Engineers typically start in Ask Mode, use semantic search across a locally indexed codebase and documentation, and group related repositories with multi-root workspaces. MCP servers bring customer data, Datadog logs and traces, Slack and support history, runbooks, account details, and ticketing context into those investigations; Linear MCP turns evidence into escalations, while a Slack-mentioned cloud agent can open documentation pull requests. Slash commands, Rules, Skills, and parallel subagents automate repeated work, including failure analysis, known-issue searches, ticket writing, and customer-response drafting. The team reports that more than 75% of support interactions run through Cursor, with stated throughput gains of 5–10x and estimated productivity improvements of up to an order of magnitude."
---

# How technical support at Cursor uses Cursor

[Cursor](https://yomu.fyi/company/cursor) · Kody Fisher & Zach Hudson · Mar 3, 2026

**Type:** Explainer

## Summary

Cursor’s technical support team treats customer investigations as research problems, using a single session to combine code, logs, team knowledge, and past conversations. Engineers typically start in Ask Mode, use semantic search across a locally indexed codebase and documentation, and group related repositories with multi-root workspaces. MCP servers bring customer data, Datadog logs and traces, Slack and support history, runbooks, account details, and ticketing context into those investigations; Linear MCP turns evidence into escalations, while a Slack-mentioned cloud agent can open documentation pull requests. Slash commands, Rules, Skills, and parallel subagents automate repeated work, including failure analysis, known-issue searches, ticket writing, and customer-response drafting. The team reports that more than 75% of support interactions run through Cursor, with stated throughput gains of 5–10x and estimated productivity improvements of up to an order of magnitude.

## Context

Support investigations were slowed by the need to gather context across code, logs, team knowledge, customer information, and past conversations from multiple tools and teams.

## Approach / What changed

The team combines locally indexed code and multi-root workspaces with MCP integrations for customer data, Datadog, Slack, support platforms, Notion, Linear, and internal services. Slash commands, Rules, Skills, and parallel subagents automate recurring investigation, escalation, and response-drafting steps.

## Takeaways

- More than 75% of the team’s support interactions run through Cursor, with reported support engineer throughput increasing 5–10x.
- Multi-root workspaces let engineers investigate questions spanning frontend logic, backend policy checks, documentation, and other repositories in one thread.
- Parallel subagents divide recurring work among LogInvestigator, KnownIssueMiner, TicketWriter, and CustomerReplyDrafter before merging results for review.

**Tags:** [AI Agents](https://yomu.fyi/topic/ai-agents), [Cursor](https://yomu.fyi/topic/cursor), [MCP](https://yomu.fyi/topic/mcp), [Technical Support](https://yomu.fyi/topic/technical-support)

- Source: [Cursor](https://cursor.com/blog/cursor-support)
- Source URL: https://cursor.com/blog/cursor-support
- Ingested by Yomu: 2026-09-02T11:44:03.462Z

[Read original post](https://cursor.com/blog/cursor-support)