Grab's designers and ops teams ship their own fixes with Cursor
Grab, the Southeast Asian rides, delivery and payments company, opened Cursor to people outside engineering as well as to engineers. Designers now merge their own production UI fixes after Git training, analysts write SQL, product managers turn PRDs into working demos and ops and finance staff build small tools for their own problems. Cursor reports that about 98% of Grab's tech organisation uses it monthly and that tasks which took days now take a few hours.
The problem
When a UI did not look or behave as intended, a designer filed a bug or handed over a design file and waited for an engineer to pick it up. Analysts, product managers, ops and regional teams with a small tooling need sat in the same engineering queue, and engineers under time pressure skipped refactors and tests.
How they did it
- Start with bug fixing. In Grab's study of Cursor usage it was a top-three activity in every role, because an error, a failed test, a broken query or a UI that looks wrong gives both the person and the agent a place to begin and a way to check the result.
- Teach non-engineers Git fundamentals before they touch production code; Grab trained its designers in Git first.
- Let designers follow a visual bug into the implementation in Cursor and open a merge request with the working change, instead of filing a ticket.
- Keep a review gate. Each designer UI fix at Grab is reviewed by a design manager, and Engineering validates the change.
- Run hands-on workshops where each person brings a real problem they care about, then applies the tool to the next piece of work in their day; Grab treated it as enablement, not a mandate.
- Give the agent shared project context so non-engineers get the same conventions; Cursor's docs put project rules in .cursor/rules, read AGENTS.md from the repo, and let Team and Enterprise admins set required Team Rules from the dashboard.
Results as reported by Cursor
- About 98% of employees in Grab's tech organization use Cursor monthly and about 75% weekly, as reported by Cursor.
- Designers have merged hundreds of production UI fixes, often the same day, each reviewed by design managers, as reported by Cursor.
- Tasks that once took days now take a few hours, and engineers take on refactors and tests they used to skip, as reported by Cursor.
- Over a third of merge requests incorporate Cursor, and suggestion acceptance sits around 50%, as reported by Cursor.
- Across more than 100,000 sanitized Cursor messages from roughly 4,000 people, bug fixing accounted for about 39% of activity in both software engineering and ops-and-business roles, as reported by Cursor.
- Designers used Cursor 5.3x the company baseline for styling and layout, analytics 4.7x for SQL and transforms, and technical program management 3.1x for Git, build and deploy, as reported by Cursor.
- Workshops have trained several hundred people across 5 countries, including senior leaders who built and deployed their own apps, as reported by Cursor.
These figures are as reported by Cursor in Cursor customer story ↗ (Sep 15, 2026). Cursor sells the product used here. AgentGid did not measure or independently verify them.
This suits a company with a shared codebase, working code review and people outside engineering who already know what is broken: designers, analysts, PMs. It does not suit teams that cannot give non-engineers repo access or a reviewer for every change. Per AgentGid's Cursor pricing and limits pages (checked Nov 3–5, 2026), there is a free tier with limited Agent and Chat requests; Plus is $8 a month but covers Grok models only, Premium is $30 a month with third-party models at API list price from prepaid credit, and Teams seats cost $30, $100 or $200 a month by tier, with custom Enterprise pricing. Cursor is now owned by SpaceX, per its own announcement. All figures come from Cursor's customer story, are usage metrics rather than measured business outcomes, and are not independently checked; the story has no before/after baseline for most of them. For an open-source route, OpenCode (MIT) is free with paid plans from $10 a month per its AgentGid page (checked Nov 17, 2026).
The agent used here
Similar use cases
Mod almost any PC game with Claude Code and the universal-modder plugin
An open-source GitHub project packages skills, a command-line tool, a shared knowledge base and the fal MCP server so AI coding agents such as Claude Code can mod PC games the use…
The repository ships three worked examples: a Terraria tModLoader weapon and boss pack with sprites made through fal, an Age of Empires II DE civiliz… (as reported by the project's author)
IMDEX built a mining data platform in 8 months with Cursor
IMDEX, an Australian mining technology company, used Cursor to merge fragmented geological data products into one platform and to move a legacy Angular app to a React micro fronte…
The data platform landed in eight months; without Cursor it would have taken 20 additional engineers, two to three years and millions of dollars, as …
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. (as reported by Figma)
Guides
Malicious Claude Code 2.1.312 and 2.1.313 Extensions in Cursor: What It Did and How to Check
Tampered Claude Code extensions, versions 2.1.312 and 2.1.313, sat in Cursor's extension marketplace on October 29, 2026 and tried to plant an SSH backdoor. What Cursor's notice confirms, why the tunnel mostly failed, and how to check and clean a machine.
How to Cut Token Usage in Claude Code and Cursor (2026)
Practical ways to spend fewer tokens with Claude Code and Cursor: measure first, keep context small, match the model to the task, filter what the agent reads, and the open-source tools that help.
VoiceStudio: The Free, Local ElevenLabs Alternative
A viral post calls VoiceStudio a 100% free ElevenLabs replacement with 19.4K stars. We checked it against GitHub and the project's own pages: what it does, what is really free, the license catch in the default voice model, and how to plug it into Claude Code or Codex.
AI Coding Agent Pricing Explained: Claude Code, Cursor, Codex and Copilot (2026)
What Claude Code, Cursor, OpenAI Codex, GitHub Copilot and other coding agents really cost: plan prices, usage limits, subscription vs API billing, and how to estimate your monthly bill.