Show notes
Wes and Scott talk with Kyle Cesmat about how Coinbase is writing nearly half its code with AI—while keeping quality and security front and center. They dig into tools like Cursor and Claude Code, agent-driven workflows, code review challenges, and how AI is reshaping developer productivity without replacing developers.Show Notes00:00 Welcome to Syntax!03:29 Defining and measuring “quality” at a large company05:05 How AI-generated code is reviewed and shipped at Coinbase07:35 A developer’s workflow using AI—from ticket to production10:30 Standard vs. team-specific tools for AI development12:55 Using MCP servers to power internal AI workflows14:42 MCP vs. custom agent integrations17:16 What kinds of code AI is writing at Coinbase19:48 Which languages and tasks does AI handle best?21:21 Getting AI to follow existing code conventionsgreptile24:36 Brought to you by Sentry.io25:01 How AI affects hiring, velocity, and developer focus28:16 AI’s role in speeding up code reviews31:28 The most valuable AI tool in Coinbase’s stack33:48 Managing AI costs and model choices35:10 Security considerations for using external AI models37:04 How often Coinbase tunes and adjusts its AI systems39:26 Using AI to write code vs. embedding AI in customer-facing features42:29 Kyle’s big-picture take on AI as a tool—not a magic bulletMeasuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity44:33 The future of hiring engineers with their own “backpack” of agents45:53 Sick Picks + Shameless PlugsSick PicksKyle: UltraShelfHit us up on Socials!Syntax: X Instagram Tiktok LinkedIn ThreadsWes: X Instagram Tiktok LinkedIn ThreadsScott: X Instagram Tiktok LinkedIn ThreadsRandy: X Instagram YouTube Threads
