Hari Krishnan is improving AI's skills with intent

Kyle Hodgson talks with Svet Bajlekov, co-founder of AMMP, a monitoring platform for commercial and industrial solar and battery sites. They get into how a team of about 14 uses AI agents across engineering and operations. In this episode:How Svet went from a physics PhD and consulting to mini-grids in Africa, and how AMP was spun out in 2018Why AMMP put collaborative AI agents in Slack.Their triage agent (Sparky) and coding agent (Coda) work in the open, which makes it clear who built whatHow the agents are set up: their own identities, Docker sandboxes, hosting, and how they connect to SlackGetting agents to stay quiet unless they're asked somethingRay, AMMP's customer-facing agent, which triages alerts, ranks site issues by impact and runs scheduled analysesWhy clean data matters more than clever promptsChoosing models, and why Svet thinks the model matters less than it used toUsing lightweight classification models for alert triageSvet on no longer reading every line of code, and what's giving him joy right nowAs always, special thanks to our founding sponsor, Navalia!Navalia.io

Ian Johnson is Staff Software Engineer at Parento and author of Harness Engineering. And, he's the first guest that talked to me about how they are building a factory.Ian's book, Harness Engineering:https://leanpub.com/harness-engineeringMore about Ian:https://www.tacoda.dev/aboutAs always, special thanks to our founding sponsor Navalia!Initially recorded: August 25, 2026

In this episode, Pete Hodgson discusses the evolving landscape of AI-assisted engineering, the importance of governance in AI workflows, and how organizations can empower grassroots innovation while maintaining control. He shares insights from his role at Tribe and explores the future of agentic workflows and token economics.

Hari Krishnan is back to talk about advancements in spec driven development, about advancements in open weights models, and about the book he's writing for Manning. You can get the book for 50% off (and possibly save even more this week?) with the Manning Early Access program here: https://www.manning.com/books/spec-driven-development You get access to the first three chapters, and the full book once its ready.

Asoba’s CEO Shingai Samudzi is no stranger to ML, as a data scientist he’s put it to use throughout his career. Now, as Asoba looks to accelerate solar energy in South Africa, he’s assembling a new approach; combining a per inverter JEPA world model with Nahenda, a model they’ve developed based on Qwen fine-tuned specifically for epistemic behaviour.Though this would be cool enough as an experiment, the early results are promising. On recent runs analyzing actual solar inverter data, they more accurately spotted problems (and ignored false positives) with equipment. In solar power, this improves margin, and can make or break a solar plant. https://huggingface.co/asobaMore of Shingai’s researchMore on SEP, Specification enhancement proposals

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 TopicsAI’s impact on software development and testingOrganizational adaptation to rapid change with AITools and mental models for AI-driven codingRevising requirements and workflows in the AI eraMerge efficiency and reducing friction in CI/CD pipelinesThe role of agents and prompts in software engineeringOrganizational hiring and contribution patterns in AI-driven environments Impact of AI on software testing and debuggingShift towards product thinking and distributed decision-makingThe role of tooling and automation in quality assuranceChanging team structures and roles in software organizationsStrategies for managing system complexity and incident responseAs 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 toOr Shingai Samudzi, CEO and Founder of Asoba about how they’re using JEPA world models to improve solar in Africaor 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.

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

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 thoroughlyThe 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 2025https://www.youtube.com/watch?v=nV0bfPd9chwhttps://swamp-club.com/

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!

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/