How do you turn AI coding chaos into a repeatable playbook?

Vivek Raghunathan, SVP of engineering at Snowflake, joins Leaders of Code at Snowflake Summit to break down the five-stage framework his org used to go from "let chaos reign" to a repeatable, org-wide system for AI-assisted engineering.

Vivek explains how Snowflake systematically rolled out coding agents across its engineering org — starting with unrestricted experimentation, then codifying what worked into a shared vocabulary of 14 "AI design patterns," from plan-in-English to fencing off parallel agents to reducing on-call toil through continuously updated skills. Vivek walks through the "inner loop" and "outer loop" of software development, explains Snowflake's internal Yegge scale for measuring how far engineers have progressed along that continuum, and shares how a three-person team used coding agents to deliver a 40x improvement on Snowflake's query compiler.

The discussion also:

Breaks down Snowflake's "focus weeks," where engineers get dedicated time to either catch up on best practices or push the frontier further.
Explores the pioneers/settlers/skeptics framework for meeting engineers where they are in adopting AI tools, and why the shift can trigger something like the stages of grief.
Covers how Snowflake cut release validation time from 15 days to a single day, and why more automated testing hasn't come at the cost of production stability.
Looks ahead to a four-step maturity model for on-call and incident response, where agents may eventually take primary on-call duty.

Connect with Vivek Raghunathan on LinkedIn.

See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Denne episoden er hentet fra en åpen RSS-feed og er ikke publisert av Podme. Den kan derfor inneholde annonser.

Episoder(987)

Professional skepticism is a dev’s best skill

Ryan chats with David Burns, Head of Developer Advocacy and Open Source at BrowserStack, about the value of professional skepticism in an AI-driven world, applying test-driven development to agentic e...

25 Sep 28min

Multiplayer AI: Why your team (and its agents) need a group chat

SPONSORED BY SLACK BY SALESFORCEIn this episode, Ryan chats with the GM of Slack, Rob Seaman, about how their new Code Channels feature is bringing multiplayer AI to your team chats. They discuss how ...

23 Sep 30min

Haters think AI agents can't write GPU code? This'll ROCm

Ryan chats with Anush Elangovan, VP of Software at AMD, about ROCm's open-source unified toolchain for GPUs, how agentic AI is drastically lowering the barrier to entry for low-level hardware programm...

22 Sep 26min

The AI magic words

Ryan sits down with Tim O'Reilly, founder and CEO at O'Reilly Media, to talk about the role of books as user interfaces to knowledge, the power of "magic words" to extract better outputs from AI, and ...

18 Sep 24min

AI, JD, and other letters of the law

Ryan chats with Kevin Frazier, director of the AI Innovation and Law program at the University of Texas School of Law, about the legal and social impacts of data centers, the realities of workforce di...

15 Sep 38min

AI cybersecurity is a cat and mouse game

Ryan chats with Sam Curry, CSO at Zscaler, about where human intelligence sits in the new security landscape with AI, why shifting security protections closer to applications helps limit probes for vu...

11 Sep 27min

Java’s age is its AI superpower

SPONSORED BY IBMRyan welcomes Markus Eisele to the program to talk about why your coding agent should be writing Java. They talk about why the long history of Java both makes for a stable language and...

9 Sep 35min

Scaling your money safely with AI

Episode notes: This episode with Paypal’s CTO Srini Venkatesan was recorded at the Ai4 conference. Listen to our other Ai4 conversation with Greg Jennings, VP of Engineering for AI Products at Anacond...

8 Sep 28min