Refactoring Podcast

Today's guest is Stuart Caborn, distinguished engineer at loveholidays, which is an online travel agency with millions of customers around the world.

I'm talking with Stuart because his team is doing AI coding for real.
They operate an extremely complex product and technology, with each engineer deploying to production more than 80 times a month, with more than 60% of production code being written with AI, all while maintaining an absolutely elite change failure rate under 1%, and with perfect code health.
So, let's see how they pull this off.

(01:29) Introduction
(02:30) What it loveholidays?
(06:04) Sponsor break
(07:00) loveholidays' AI approach
(10:16) Code quality
(13:36) Making quality visible
(14:52) AI, MCP and top use cases
(22:19) Code health and engineers' happiness
(29:35) How was AI implemented at loveholidays
(37:01) Experimenting with AI and skills
(42:30) How to spread AI into an org
(47:31) Guardrails in dev process
(56:40) Other process changes

—
You can also find this at:

• 📬 Newsletter: https://refactoring.fm
• 🎧 Spotify: https://open.spotify.com/show/7Luds9dmzZDoDC8Q7EMbSw
• 📱 Apple: https://podcasts.apple.com/us/podcast/refactoring-podcast/id1719137305

—
For inquiries about sponsoring the podcast, or appearing as a guest, email: [email protected]

Today’s guest is Chris Lattner, one of the most important engineers for modern computing. Chris invented key compiler infrastructure tech like LLVM and MLIR, but he’s also the inventor of the Swift language, a key contributor in bringing Google TPUs to market, and a lot more. Today he’s the founder and CEO of Modular, where he’s reinventing AI infrastructure to make software portable across GPUs and platforms.

So with Chris, we talked about his vision for AI and computing. We talked about how Modular’s mission makes us closer to a future where AI is open and portable. And we talked about open source, how AI is both empowering and straining contributors, how it’s changing intellectual property, and what workflows we need to change as engineers.

And finally, we discussed how AI is changing software craftsmanship, how he’s bullish about junior engineers, and a lot more.

(00:00) Preview
(02:11) Introduction
(04:05) What is Modular?
(06:13) Sponsor break
(07:10) From CPU to GPU landscape
(10:46) Objective-C Swift analogy
(15:37) What is Modular for Chris?
(17:37) The love for building
(20:21) Chris' view on AI future
(23:48) AI and open source
(29:34) Figuring out new workflows
(31:22) On licenses and copyright
(33:42) High quality software
(35:21) Coding faster with AI
(41:27) The landscape of junior engineers
(48:22) AI amplifies the good and the bad
(52:21) Modular ceremonies
(55:26) Tech debt

—
You can also find this at:

• 📬 Newsletter: https://refactoring.fm
• 🎧 Spotify: https://open.spotify.com/show/7Luds9d
• 📱 Apple: https://podcasts.apple.com/us/podcast

Today's guest is Amelia Wattenberger, former principal research engineer at GitHub and now partner at Sutter Hill Ventures.

But she's also a product lead at Augment Code, where she developed Intent, a developer workspace for orchestrating AI coding agents and delivering complex work. 
So this is a fascinating chat into the future and the present of software development with someone who has clearly been at the very frontier of this for many years.

(00:00) Preview
(01:11) Introduction
(03:26) What is "Intent"?
(09:56) Splitting agents for best performance
(12:32) Spec and subtasks
(17:46) Decision and generation
(22:15) Features, opinion and abstractions
(25:37) The note system
(27:41) Attitude is reflected in approach
(35:21) Engineers in the new era of crafting
(37:14) Managing skills applied to an agent environment
(39:46) Orchestrating agents
(45:50) The future of deep specialists

—
You can also find this at:

• 📬 Newsletter: https://refactoring.fm
• 🎧 Spotify: https://open.spotify.com/show/7Luds9d...
• 📱 Apple: https://podcasts.apple.com/us/podcast...

—
For inquiries about sponsoring the podcast, or appearing as a guest, email: [email protected]

Today's guest is Richard Hughes-Jones, a professional executive coach with more than 20 years of experience. 

With Richard, we talked about how to coach tech leaders through uncertainty and everything that's going on with AI, how to navigate it, how we should think about our role, and what it means to step outside of the framework.
We also explored how to leverage AI for coaching, how to blend human and AI advice to get the best of both worlds.

(00:00) Preview
(01:08) Introduction
(02:26) Richard's journey into coaching
(04:23) Sponsor break
(05:19) Coaching without engineering background
(07:27) Most common challenges
(11:39) Helping people in uncertainty
(19:10) Good for the team Vs Good for the business
(22:13) Are frameworks limiting?
(27:10) Creating a personal framework
(31:49) Am I trying to be the hero?
(34:35) Usual questions
(39:07) AI and coaching

Link to article mentioned in the interview: https://richardhughesjones.substack.com/p/052-special-edition-what-i-learned
—
You can also find this at:

• 📬 Newsletter: https://refactoring.fm
• 🎧 Spotify: https://open.spotify.com/show/7Luds9d...
• 📱 Apple: https://podcasts.apple.com/us/podcast...

—
For inquiries about sponsoring the podcast, or appearing as a guest, email: [email protected]

Today's guest is Austen McDonald, former hiring committee chair at Meta, and author of the book, "Mastering Behavioral Interviews." 

Austen, in his career, conducted more than 1,000 interviews and coached more than 200 engineers, and is here today to tell us everything about why behavioral interviews are more important than ever and how to run them right, as a candidate and as a recruiter.

(00:00) Preview
(01:02) Introduction
(01:37) Austen' interest in behavioral interviews
(06:25) Sponsor break
(07:31) Behavioral interviews as a senior or a junior engineer
(09:55) The question behind a question: signal areas
(13:09) Fails in behavioral interviews
(16:38) Decode, select, deliver
(17:15) The eight areas
(19:02) How company culture reflects in hiring
(21:59) Assessing company's culture as a candidate
(23:49) The big three questions
(29:26) Preparing for the big three questions
(37:37) Deliver a story
(40:28) Good preparation process
(43:15) Do not lie
(46:14) Recruiter side: biases
(51:42) Candidate experience with AI: value questions

—
You can also find this at:

• 📬 Newsletter: https://refactoring.fm
• 🎧 Spotify: https://open.spotify.com/show/7Luds9dmzZDoDC8Q7EMbSw
• 📱 Apple: https://podcasts.apple.com/us/podcast/refactoring-podcast/id1719137305

—
For inquiries about sponsoring the podcast, or appearing as a guest, email: [email protected]