Engineering with AI

Rob Zuber is seeing the gap widen

Rob is the CTO at Circle CI, and I was really interested to hear what all he can see from their vantage point - and it didn’t disappoint. He had lots of broad ranging insights in to what teams are doing all over the capability map; median to P90, how they’re different and what’s working. A super insightful conversation! And he’s also just got a great energy, super fun conversation. Key Topics AI’s impact on software development and testing Organizational adaptation to rapid change with AI Tools and mental models for AI-driven coding Revising requirements and workflows in the AI era Merge efficiency and reducing friction in CI/CD pipelines The role of agents and prompts in software engineering Organizational hiring and contribution patterns in AI-driven environments Impact of AI on software testing and debugging Shift towards product thinking and distributed decision-making The role of tooling and automation in quality assurance Changing team structures and roles in software organizations Strategies for managing system complexity and incident response As usual, thanks to Navalia our founding sponsor! We have an embarrassment of riches when it comes to deciding what will be next, I have interviews ready from so many super interesting guests that I can’t decide who will be next yet: Maybe Pete Hodgson; our second ever guest, super insightful and in a new role where he’s seeing even more, back to talk about what he’s been up to Or Shingai Samudzi, CEO and Founder of Asoba about how they’re using JEPA world models to improve solar in Africa or Ian Johnson, author of https://leanpub.com/harness-engineering who has been building agent factories at Parento? Plus, I have even more interviews scheduled! It’s been a great summer and its looking like it will be a fantastic fall on Engineering With AI.

• Transcript

Chris Ford: Agentic Engineering at Scale

Chris Ford is one of my favourite speakers, curators, and writers on AI. His first episode on our show was a big hit, the most downloaded on most platforms. So when I heard he was writing a book, I had to have him back! Check out the book: Agentic Engineering at Scale

• Transcript

Birgitta Boeckeler is bringing structure to the madness

You may know Birgitta from her articles on MartinFowler.com, or from her own space at birgitta.info. She’s been in the role of Distinguished Engineer for assisted Software Delivery for the last three of her nearly fourteen years at ThoughtWorks. - In “Understanding Spec-Driven-Development” she described “Spec-first”, “Spec-anchored” and “Spec-as-source”, using Kiro, spec-kit and Tessl to explore the concepts - In “Harness engineering for coding agent users” she starts with some fundamental concepts, how we “feed-forward” using guides, and use sensors for feedback; and then she goes deep, covering harness engineering thoroughly The first person to tell me she was doing interesting stuff was Pete Hodgson, our 2nd ever guest - so I’ve been working on getting her to come on the show since December of 2025. It was worth the wait! Mentions and links: Ivette Ordog https://ivettordog.com/ https://lexler.github.io/augmented-coding-patterns/patterns/approved-scenarios/ AI assisted legacy modernisation : From UX to code — XConf India 2025 https://www.youtube.com/watch?v=nV0bfPd9chw https://swamp-club.com/

• Transcript

Jonas Claesson has AI deep in the pipeline

Jonas Claesson is a Principal Engineer at Provision Analytics. He’s the toolsmith and chief agent herder for a team of six developers with product managers and UX designers to help. He’s building tools his team uses every day; QA bots that use exploratory testing approaches for each story, commands that automatically compare SQL queries when they change, and generally keeping tech debt minimal. Check out his LinkedIn feed, its been good reading! We have some really amazing episodes planned, and some that we are working to schedule! However, the next episode may not come out on the normal cadence. As always, special thanks to our founding sponsor, Navalia!

• Transcript

Ahmed Misbah has spicy takes on Engineering With AI!

Ahmed is an independent consultant and AI researcher, and he has some really spicy takes! We had a really fun interview. - AI finally makes "Classic" QA viable - Maybe Anthropic's Mythos .... is a myth? More on Ahmed at https://tekcaffe.com/

• Transcript

Hari Krishnan helps large teams adopt spec driven development at scale

Hari Krishnan writes about Gen AI adoption at intent-driven.dev and walks us through Open Spec, a "spec anchored" framework he is an advisor to. Things we talked about Hari's article at InfoQ: https://www.infoq.com/articles/enterprise-spec-driven-development/ Birgitta Böckeler’s article "Understanding Spec-Driven-Development: Kiro, spec-kit, and Tessl": https://martinfowler.com/articles/exploring-gen-ai/sdd-3-tools.html Lost in the Middle: https://cs.stanford.edu/~nfliu/papers/lost-in-the-middle.arxiv2023.pdf Tessl: https://docs.tessl.io/use/spec-driven-development-with-tessl

Navalia puts AI to use improving the bottom line for its customers

In this special episode of Engineering With AI we talk to Hany Elemary and Ibrahim Taha, co-founders, and Alina Murphy, Executive Program Manager about how AI is changing things for the businesses they serve. https://navalia.io https://engwith.ai

Guru's existential crisis: is coding over?

Guruprasad Venkatesh is Co-founder and Chief Architect for Beskar Technologies (beskar.tech), a custom software delivery company in Bangalore India that practices extreme programming (TDD, CI/CD, agile etc) and has taken steps to adopt AI to move even faster. He walks me through how he and Beskar are adopting AI, and about Baid, their own AI AI tool suite called Baid (https://baid.dev/bot) As usual, special thanks to our sponsor, Navalia (https://navalia.io)!

• Transcript

Chris Ford has spicy takes on Engineering With AI!

"Human in the loop won't work"! "Developers passing on tribal code base knowledge is over!" "Pair Programming still matters!" "Refactoring is not dead!" "We should stop calling things CD!" Wait, that last one is quite reasonable. (Continuous Delivery, Continuous Deployment, Continuous Design, Compact Disc, Certificate of Deposit...) This was a really great conversation! Chris has been thinking hard about the impacts AI is having on software engineering, and it showed! Books, blogs and other resources we mentioned: Working Effectively with Legacy Code (WELC) Continuous Deployment The Phoenix Architecture - Chad Fowler's writing on AI As usual, thanks to our founding sponsor, Navalia!

• Transcript

Tim Cochran is thinking about developer experience in the era of GenAI

Tim Cochran, Principal for Amazon Software Builder Experience, is no stranger to software development; in enterprise, scaleups and in startups. He’s well known for articles like Maximizing Developer Effectiveness, Measuring Developer Productivity via Humans, which focus on in developer experience, and Bottlenecks of Scaleups, a wide ranging series that focused on the challenges startups have as they scale up to become larger businesses. As always, special thanks to our sponsor Navalia for their support as a founding sponsor!

• Transcript

Sharan Karanth is keeping Binaxity’s team cohesion high using AI

Sharan Karanth is Principal Engineer and Head of Engineering at Binaxity, an "Invest now pay later" startup in Toronto. He talks us through how their team is using AI; what guardrails they have in place (human guardrails in this case!), how their engineering process works. Sharan went fairly deep in to the process, you can tell he's definitely still coding at Binaxity. More on Binaxity: https://www.binaxity.com/ As always, thanks to our Founding Sponsors, Navalia! https://navalia.io

• Transcript

Cassie Shum is having fun writing code with AI

Cassie was just back from a week in Utah with Martin Fowler, Kent Beck, Tim Cochran (next week's guest!) and too many cool people to list when we spoke. We covered everything from why it feels like we're testing all the time now, to an exploration of how "maybe refactoring is dead?" For more on what RelationalAI is doing with knowledge graphs, check out https://relational.ai As always, big thanks to our Founding Sponsor, Navalia.io!

• Transcript

John Jarosz uses GenAI to test ideas faster

John Jarosz is the Managing Partner and Co-Founder of Sightglass Partners, a product and technology studio that helps ambitious companies identify and create solutions that fulfil unmet needs. We talked about how Sightglass uses GenAI through market entry analysis, product design and how the tools help his business and his customers. https://sightglasspartners.com/

• Transcript

Aravindh Sridharan skips AI two days per week. He only uses it the other 5.

This sounds like a silly click bait joke, and it kind of is. It’s also just how Aravindh works - ever since I’ve known him (close to 20 years at this point) he’s had this intense work habit. I admire how he does it; he knows not to get too far ahead of his team mates, for instance - so me might spend 20 hours learning something new for fun, 20 hours on a side project (like the algorithmic trading bot he built), and only work 50 or so hours a week or so on his main job. All of this to say, setting down tools that make you arguably more productive 28% of the time is showing intense restraint - and I admire this about him, too. Aravindh swears by it - it helps him have a much better sense of the codebase that he and his GenAI tools are making. It also helps that he’s one of the best software developers I’ve ever worked with. He balances confidence, expertise and the openness of the “beginners mind” like no one I’ve known. The other thing he talked about in our interview makes new use of an existing axiom - that you should “own the seams”. In this interview, Aravindh argues that we should prioritize working closely with our GenAI tools to define REST interfaces, service contracts, classes, interfaces, traits and so on, and exert slightly less control over how it works between these seams. “Own the seams” often gets used when talking about systems integration; that if you use IBM’s Websphere Commerce (which has the shopping cart) and also Sterling’s Order Management System (which manages the order that the cart becomes), try to not let these two important packaged systems to talk directly to another. Even placing a thin shim of a proxy between them begins to give you some control - and better yet, place some kind of adapter between them to prevent Sterling from becoming aware of or dependent on Websphere Commerce’s internal domain jargon and vice versa. This particular use of owning the seams flips it on its head a little bit - instead of enterprise software teams placing domain facades between two massive packaged software systems in order to have more control, its you exerting control over your GenAI coding tools in order to have more control over your code. Spoken like someone who spends 28% of his week working in his code base by hand! As always, thanks to our Founding Sponsor, Navalia! The “long working hours” part of this story definitely deserves a “don’t try this at home” warning - it won’t work for everyone. I do think it works for Aravindh, though.

• Transcript

How Grainger is rolling out AI with high adoption

Philip Sears is the GenAI Enablement Lead at Grainger, where he helps engineering teams integrate AI tools across the software development lifecycle through strategy, evaluation, and hands-on learning. In this episode, he talks about how Grainger rolls out AI using a four-phase adoption model, measuring AI value beyond raw developer speed and how it’s beneficial across the SDLC at enterprise. As always, special thanks to our founding sponsor, Navalia! https://navalia.io

Jeff Langr uses AADV to get more out of LLMs

As an early devotee of Test Driven Development, Jeff Langr is the author of Pragmatic Unit Testing in Java with JUnit, Modern C++ Programming with Test-Driven Development, and co-author of Clean Code. Jeff is currently leading a team at Jack in the Box, and his team loves the mob code sessions he leads. If you want to follow Jeff about his AADV technique, check out his Substack. https://jjlangr.substack.com/ As always, special thanks to our founding sponsor, Navalia! https://navalia.io

Pete Hodgson explains the hidden cost of AI-Generated code

Our second interview, Pete Hodgson is an independent software delivery consultant in the San Francisco area. Pete has used a number of different approaches to AI as part of his workflow, and often helps teams get to the next level when working with AI as part of his consulting practice. It's a great conversation, he comes up with quite a few ideas on how to ease context management through automation, scripting, and providing context at the right time. You can find Pete here: https://thepete.net/ As always, special thanks to our founding sponsor, Navalia! https://navalia.io

Ahmad Nassri is *still* looking for the LLM magic

Ahmad Nassri sees a lot of promise in LLM based coding models, and talks us through the techniques, tools and approaches he takes personally, and that he sees teams taking when working with AI tools today. Our first, in person interview on Engineering With AI, Ahmad is the CTO of Socket (socket.dev), a leader in Software Composition Analysis tooling. https://www.ahmadnassri.com/ https://socket.dev/ As always, special thanks to our founding sponsor, Navalia! https://navalia.io

Season One Subscriber Update

A quick note for Engineering With AI subscribers! https://engwith.ai