---
title: "Coinbase reduces time from idea to production by 90% with Cursor"
description: "Coinbase redesigned its engineering model around agent-first infrastructure rather than retrofitting AI into legacy processes, making time from idea to production its north-star metric. More than 2,400 developers use Cursor; engineers define intent, write requirements for agents, plan work with Plan Mode, delegate implementation, and validate results, often running 5–7 asynchronous agents in parallel. The company reports that some teams cut idea-to-production time from 20 days to less than two days, while first PR creation fell from eight days to under 30 minutes; 75% of PRs are agent-created, and average developers save seven hours of coding weekly. Coinbase also uses smaller working groups, internal champions, speedruns, and Superbuilders to spread these workflows and build tooling."
---

# Coinbase reduces time from idea to production by 90% with Cursor

[Cursor](https://yomu.fyi/company/cursor) · Cursor · Jun 23, 2026

**Type:** Explainer

## Summary

Coinbase redesigned its engineering model around agent-first infrastructure rather than retrofitting AI into legacy processes, making time from idea to production its north-star metric. More than 2,400 developers use Cursor; engineers define intent, write requirements for agents, plan work with Plan Mode, delegate implementation, and validate results, often running 5–7 asynchronous agents in parallel. The company reports that some teams cut idea-to-production time from 20 days to less than two days, while first PR creation fell from eight days to under 30 minutes; 75% of PRs are agent-created, and average developers save seven hours of coding weekly. Coinbase also uses smaller working groups, internal champions, speedruns, and Superbuilders to spread these workflows and build tooling.

## Context

Coinbase concluded that legacy systems and processes, rather than developers, were limiting software delivery, and that retrofitting AI into existing workflows would not capture the full impact of coding agents.

## Approach / What changed

Coinbase redesigned engineering around agents by revisiting sprint planning, shifting engineers toward requirements, architecture, and evaluation, enabling smaller full-stack teams, and using Cursor for planning, delegation, model selection, and result validation. Internal champions, agent speedruns, and Superbuilders supported adoption and tooling.

## Takeaways

- Some Coinbase teams reduced time from idea to production from 20 days to less than two days, with one reported improvement from 20 days to 1.8 days.
- Engineers write living product and technical requirements that guide agent execution and provide evaluation frameworks after implementation.
- Coinbase reports that 75% of PRs are created by agents, while the average developer saves seven hours of manual coding per week.

**Tags:** [AI Agents](https://yomu.fyi/topic/ai-agents), [Cursor](https://yomu.fyi/topic/cursor), [Productivity](https://yomu.fyi/topic/productivity)

- Source: [Cursor](https://cursor.com/blog/coinbase)
- Source URL: https://cursor.com/blog/coinbase
- Ingested by Yomu: 2026-09-02T11:42:21.022Z

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