More How I AI episodes

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

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

Published 2 Mar 2026

Duration: 00:58:57

AI tools are transforming workflows and daily life through automation, personalization, and enhanced productivity.

Episode Description

Chintan Turakhia is Senior Director of Engineering at Coinbase, where hes led the transformation of a 1,000-plus-engineer organization to embrace AI t...

Overview

The podcast discusses how AI tools are transforming workflows, productivity, and collaboration across various platforms. Cursor, Rovo, and Cloudbot are highlighted as key examples: Cursor streamlines coding with AI-driven features like bug fixes, playbook generation, and the creation of "Super Builders" to enhance productivity. Rovo integrates Atlassian tools (JIRA, Confluence) into a unified "teamwork graph," enabling personalized insights and automation. Cloudbot automates the conversion of unstructured feedback into actionable bug reports and QR codes for testing. These tools reduce friction in workflows, automate repetitive tasks, and improve efficiency by minimizing coordination overhead.

Beyond professional applications, AI is also personalizing daily experiences, such as automating calendar invites from school emails, generating wine recommendations based on handwritten tasting notes, and allowing users to customize AI outputs through platforms like Slack and Linear. In app development, the Base App (formerly Coinbase Wallet) is launching a consumer social app for crypto creators, emphasizing the need for engineers and AI specialists. The discussion also covers AI optimization techniques, such as using direct, assertive prompts or leveraging competition to improve AI compliance.

The content underscores AIs role as a catalyst for innovation, enabling both professional efficiency and personalization. It highlights the integration of AI into workflows, the growing demand for AI-driven roles, and the importance of refining AI interactions through tailored prompting strategies.

Recent Episodes of How I AI

22 Jun 2026 How Claude Mythos found a 15-year-old bug in Mozilla Firefox | Brian Grinstead

Recommended: AI finds bugs

Firefox employs AI agents as "coding archaeologists" to detect and address security vulnerabilities in its massive codebase, leveraging models like Mythos and custom validation tools to identify and systematically fix nearly 500 bugs, while balancing automation with human oversight and open-source collaboration to enhance scalability and security.

15 Jun 2026 How Braintrust uses AI agents, evals, and CI to ship better software | Ankur Goyal

AI integration in software engineering enables agents to handle complex tasks through benchmarking and optimization, shifts engineers toward higher-level work, and addresses challenges like reliability, data parsing, and balancing automation with human expertise while emphasizing outcome-focused systems over procedural methods.

9 Jun 2026 Claude Fable 5 review: what the new Mythos model gets right (and very wrong)

Anthropic's Claude Fable Five excels in long-term technical tasks with strong coding, vision, and async workflow capabilities but faces high token costs, design limitations, and restricted use in cybersecurity/biology, making it suitable for precise, extended projects rather than creative or agile workflows.

More How I AI episodes