The AI Native Dev - from Copilot today to AI Native Software Development tomorrow
Tessl
Welcome to The AI Native Developer, hosted by Guy Podjarny and Simon Maple. Join us as we explore and help shape the future of software development through the lens of AI. In this new paradigm of AI Native Software Development, we delve into how AI is transforming the way we build software, from tools and practices to the very structure of development teams.Our target audience includes developers and development leaders eager to stay ahead of the curve. If you're passionate about the future of software development and curious about how to leverage AI to build effective teams and groundbreaking software, this podcast is for you.Each week, we bring you insights into the latest AI tools and best practices, keeping you up-to-date with the cutting-edge advancements in the industry. Additionally, every two weeks, we present deep dives with experts and leaders in the AI and software development space, offering a glimpse into the future of AI development.Tune in to discover how AI will revolutionize your workflows, roles, and organizations. Get inspired by the latest tools and best practices, and prepare to be part of the next generation of software development.
Episodes
Mentioned books
Apr 7, 2026 • 40min
How DeepSeek leveraged Qwen and Llama to build its model in $5M
Amanda Brock, CEO of OpenUK and open technology law expert, discusses true openness in AI and the rise of openwashing. She covers how DeepSeek built a frontier model for $5M using Qwen and Llama. She compares Western and Chinese open-source approaches and explains how to verify model openness and why national strategies and community-building matter.
29 snips
Mar 31, 2026 • 1h 1min
Why Every Developer needs to know about WebMCP Now
Maximiliano Firtman, a 30-year web developer and author now focused on web-facing AI, talks about agents visiting websites and why screenshots are a dead end. He explains WebMCP, a Chrome API that lets sites expose callable client-side functions. They discuss e-commerce, payments, client-side models, and how in-browser AI and local models change web app design.
64 snips
Mar 24, 2026 • 1h 2min
Stop Maintaining Your Code. Start Replacing It
Chad Fowler, VC and former Wunderlist CTO known for pragmatic engineering and the Phoenix Architecture, outlines treating code as disposable and systems as assets. He discusses tiny, replaceable services, spec-first designs, deploying AI-written code safely, shadow specs from agents, and building systems that work even with weaker LLMs.
54 snips
Mar 17, 2026 • 35min
We Scanned 3,984 Skills — 1 in 7 Can Hack Your Machine
Brian Vermeer, a security pro at Snyk focused on developer-facing tooling, explains risks hidden in agent skills. They scanned nearly 4,000 skills and found widespread critical issues. Brian breaks down prompt injection, obfuscation tricks, supply-chain and credential risks, how trusted skills can turn malicious, and how Snyk’s agent scan and registry integrations help spot problems before you install.
62 snips
Mar 10, 2026 • 1h 2min
The Greatest Time to Build a Startup (The AI-Native Advantage)
Daniel Jones, partner at re:cinq who helps firms adopt agentic coding and AI-native development. He unpacks hidden pitfalls of agentic development, why tests and version control matter with agents, how to manage context to avoid hallucinations, and practical rollout and platform strategies for scaling AI in enterprises.
37 snips
Mar 3, 2026 • 45min
Why Your Agent Needs Memory, Not Just Context
Richmond Alake, Director of AI Developer Experience at Oracle, brings experience in developer advocacy and memory engineering. He argues agent failures stem from memory, not models. He compares file systems and databases for agent memory. He explains skills as SOPs and outlines the memory lifecycle, security trade offs, and how continuous learning will merge agent and training loops.
4 snips
Feb 25, 2026 • 34min
Cisco Principal Engineer's Fix for AI Code Security
John Groetzinger, Principal Engineer at Cisco who built CodeGuard, a security skills layer for AI coding agents. He explains how CodeGuard teaches agents to write and review code securely. They discuss simplifying security guidance, packaging skills across IDEs, measuring activation and using task evals. John also covers design lessons, when to run evaluations, and why Cisco open sourced the project.
34 snips
Feb 17, 2026 • 31min
Why Context Beats Every Prompt You'll Ever Write
Guy Podjarny, a seasoned tech leader building developer tools and agent enablement platforms, explores why managing context matters more than crafting prompts. He breaks down context layers like policies, platform docs, and application state. Short practical takes cover building regression and torture tests, the Context Development Lifecycle, and treating context as a reusable organizational asset.
11 snips
Feb 10, 2026 • 57min
From IBM Acquisition to AI-Native Observability | Dash0 CEO
Mirko Novakovic, founder/CEO building Dash0 and former founder of Instana, pioneers AI-native observability. He discusses OpenTelemetry’s fit for LLMs, designing tooling and UX for agent consumers, agent-driven triage and dashboards, and how agents can capture and democratize production debugging knowledge.
104 snips
Feb 3, 2026 • 45min
The End of Fragmented Agent Context
They reveal results from testing 1,000+ agent skills and which skills help or hurt agent performance. They explain why anecdotal evidence is not enough and show how systematic evals and task reviews catch surprises. They describe treating skills as versioned software with package management, CI/CD, and observability to make reuse reliable.
