@FinanceYF5: 3/【Chintan Turakhia · Coinbase】 Leading a 1000-person engineering team to truly adopt AI, PR review time cut from 150 hours to 15 hours, and achieved a "legendary feat": merging 70 PRs in 15 minutes. He says: Stop talking about adopting AI, go solve problems.
Summary
Chintan Turakhia, engineering lead at Coinbase, shares how the team used AI for code review, reducing PR review time from 150 hours to 15 hours, and setting a record of merging 70 PRs in 15 minutes. He emphasizes focusing on solving problems rather than just talking about adopting AI.
View Cached Full Text
Cached at: 06/28/26, 05:57 AM
3/ [Chintan Turakhia · Coinbase]
Leading a 1,000-person engineering team to truly start using AI
PR review time slashed from 150 hours to 15 hours
And pulled off a “legendary operation”: Merging 70 PRs in 15 minutes
He says: Stop talking about adopting AI—go solve problems
1/ AGI Summit SF 2026 speaker lineup is out
Microsoft, Coinbase, OpenAI, Google DeepMind, a16z ecosystem all present
This edition is genuinely more impactful
2/ [Carol S. Scott · Microsoft]
Steering a $70B Azure & AI business
Responsible for Copilot and Azure OpenAI enterprise rollout across Europe, Middle East, and Africa
Her take: The AI winner isn’t the first company to adopt AI—it’s the one that moves the fastest
4/ [Prakhar Bhargava · OpenAI]
Responsible for bringing OpenAI’s frontier models into the real world
From research to enterprise deployment, he owns the full pipeline
“No matter how powerful the model, if it’s not used, it’s zero”
5/ [Yichong Xu · Google DeepMind]
Co-author of the G-Eval paper (8000+ citations)
Evaluating LLMs with LLMs — he’s a pioneer in this direction
AI is getting stronger, but how do you measure how strong? This talk delivers answers
6/ [Scott Clark · Distributional]
AI reliability platform backed by a16z + Two Sigma
Founder of SigOpt, acquired by Intel in 2020
His analogy is spot on:
“Everyone wants a faster car, but what you really need is a Honda Civic that starts every time”
July 18–19, Palace of Fine Arts, San Francisco
5 tracks: Enterprise adoption, Engineering in practice, Model deployment, AI evaluation, Reliability
Interested? Use code WILL for a discount
http://luma.com/agisummit2026?coupon=will…
Which session are you most excited about?
Learn more:
That’s all for now
If you like this topic:
- Follow me (@FinanceYF5)
- Like + retweet the first post below
Similar Articles
@KKaWSB: Coinbase CEO laid off a large number of employees, claiming: "Non-technical teams are now writing production code with AI." Yet less than 24 hours later, Coinbase's trading engine went down — and even the status page mysteriously crashed. Did they move too fast and blow it?
Coinbase's CEO laid off employees and claimed non-technical teams are already writing production code with AI, but less than 24 hours later, Coinbase's trading engine and status page both went down — sparking widespread skepticism about over-relying on AI to replace technical staff.
@agisummitai: Speaker Spotlight: Chintan Turakhia How do you get 1,000+ engineers to actually build with AI — not just talk about it?…
Speaker spotlight for Chintan Turakhia, Senior Director of Engineering at Coinbase, at the AGI Summit SF 2026. He will share how he led 1,000+ engineers to build with AI, including reducing PR review times from 150 hours to 15 using AI agents.
@thinkszyg: The AI Coding Speed Paradox: Coding 48% Faster, Review 6x Slower. How to Rebuild the Review Process? SD Times Analyzes Data from 250,000 Developers: AI Boosts Coding Speed by 48-58%, But AI-Generated PRs Get Stuck in Review for 4-6x Longer…
The article points out that AI coding increases coding speed by 48-58%, but code review time increases by 4-6x, and security vulnerabilities also rise. It proposes a three-step plan to rebuild the review process: AI pre-review, focusing on architectural decisions, and using Microsoft's open-source ASSERT framework for behavioral verification.
Built an AI PR review workflow that generates actual fix PRs instead of just comments
The author built an AI-powered PR review workflow that generates actual fix PRs instead of just comments, claiming to be 6x cheaper than CodeRabbit and more accurate on large PRs.
@FinanceYF5: 1/ There's a new tax on AI engineering. According to BVP's latest survey, 90% of tech/engineering teams have already integrated AI into their core workflows; code generation 92%, code review augmentation 79%, Agentic development 60%. The real differentiator is not whether you use AI, but whether you can still maintain quality and understanding after accelerating.
BVP's latest survey shows that 90% of tech teams have integrated AI into core workflows, with code generation at 92%, code review augmentation at 79%, and Agentic development at 60%. The report emphasizes that maintaining quality and understanding after AI acceleration is the key differentiator.