scripod.com
How Coinbase scaled AI to 1,000+ engineers | Chintan Turakhia

Overview

Shownote

Highlights

Transcript

Chapters

Pins

How Coinbase scaled AI to 1,000+ engineers | Chintan Turakhia

How I AI

1 DAYS AGO
How I AI

How I AI

1 DAYS AGO
OverviewShownoteHighlightsTranscriptChaptersPins

Shownote

Chintan Turakhia is Senior Director of Engineering at Coinbase, where he’s led the transformation of a 1,000-plus-engineer organization to embrace AI tools at scale. When tasked with rewriting Coinbase’s self-custody wallet into a consumer social app in ju...

Highlights

Chintan Turakhia shares hard-won insights from leading AI adoption across Coinbase’s 1,000+ engineer organization—focusing not on theoretical potential, but on tangible, repeatable practices that accelerate delivery, deepen engagement, and shift engineering culture.
00:00
A hands-on leader is critical to drive effective AI implementation
05:40
Cursor's initial release in late 2024 was disappointing as its models couldn't perform well, like writing unit tests
08:00
Leaders should get back to coding to identify AI use cases and eliminate mundane tasks for engineers
10:35
A PR speed run with 100 engineers generated 70 pull requests in 15 minutes—so many that GitHub broke, exposing infrastructure bottlenecks
17:59
Fixed a product issue live during a user call
22:30
Cursor.sh is my daily operating system to get answers to various questions
31:54
16x more AI super users achieved through gamified adoption strategies
33:16
Using code allows for quick problem-solving, a fast feedback loop, and an enjoyable experience compared to traditional documents and dashboards
38:58
Missing numbers in the 'from' field on the trade tab prevent trades
40:50
The custom Slack bot uses an LLM to summarize live user feedback and recommend fixes, then creates a PR in Linear
47:10
Getting AI-related things into Slack can make them go viral within a company
52:52
AI analyzes wine menus to recommend bottles based on personal taste, price, and occasion
55:23
AI has emptied his calendar and made him spend more time in the codebase

Chapters

Introduction to Chintan
00:00
How Coinbase approached rewriting their app with AI assistance
02:38
The importance of leadership conviction and hands-on demonstration
08:00
The “PR speed run” technique that transformed team adoption
10:30
Measuring success
17:57
Demo: Real-time feedback-to-feature implementation
19:20
Using Cursor to analyze AI adoption patterns
23:14
Quick recap and appreciation
33:15
Demo: Building a live feedback capture system using AI transcription
36:00
Using custom Slack bots to automate engineering workflows
40:50
Advice for driving AI adoption within your organization
47:10
Personal use case: AI for wine selection based on taste preferences
50:00
Lightning round and final thoughts
55:23

Transcript

Claire Vo: People are skeptical that large, established, highly technical, highly capable engineering organizations can deploy AI at scale and get any effect. But I think you've proven it's possible. Chintan Turakhia: It's not only possible, it's adapt or...