THE PEOPLE BEHIND THE WEB
Good questions.
Great conversations.
Go beyond the docs with the people building your favorite tools. Honest conversations about code, craft, and what comes next.
Ido Evergreen
A FEW FAMILIAR VOICES
START HERE · LATEST CONVERSATION
AI Agents, Developer Experience & GitHub Copilot — Cassidy Williams
October 26, 2026 · 39:34
THE CONVERSATIONS
A little curiosity goes a long way.
39:34October 26, 2026
AI Agents, Developer Experience & GitHub Copilot — Cassidy Williams
Cassidy Williams joins Ido Evergreen to discuss GitHub Copilot, trust in AI agents, and why engineering judgment and product direction still matter. We explore how developer experience is changing, how Cassidy decides what to delegate, and why trying to keep up with every new AI tool can work against you. Cassidy also shares her perspective on using multiple models, MCP and skills, WebMCP, and the pressure AI-generated pull requests put on open-source maintainers. In this episode: • Choosing when to write code yourself and when to use agents • Staying relevant without chasing every new tool • GitHub Copilot’s evolution beyond autocomplete • Building trust in agents through small, practical experiments • Why faster implementation still needs product judgment • Accessibility and the future of an agent-driven web • Contributing responsibly to open source • Cassidy’s predictions for the next five years of software development What do you delegate to AI—and what do you still prefer to do yourself? Share your approach in the comments. Subscribe for more conversations about building software, and share this episode with a developer friend. 00:00 intro 02:37 Introduction to AI and Developer Experience 04:44 The Evolution of Developer Tools 07:23 The Role of AI in Software Development 10:04 Navigating the Future of Development 12:52 GitHub Copilot: Beyond Autocompletion 15:27 The Agentic Framework of GitHub Copilot 17:24 Trusting AI in Development 20:18 The Changing Landscape of Developer Roles 21:46 Open Source in the Age of AI 24:06 Predictions for the Future of Development #SoftwareDevelopment #GitHubCopilot #aiagents #github
Explore episode
22:56October 7, 2026
Accessible agent Web? WebMCP || Alex Nahas
What would the web look like if AI agents could use websites alongside people? I sat down with Alex Nahas to discuss WebMCP: a way for websites to expose useful actions to agents without making them navigate every task through screenshots and clicks. We talk about the browser’s existing authentication and security systems, why a website might use WebMCP even when it already has APIs, and why human-facing interfaces still matter. Alex also shares practical advice for developers: expose a small number of powerful tools that match real tasks, rather than turning every button into a separate tool. What would you let an agent do on your website? Subscribe for more conversations about AI, software, and the future of the web. 00:00 Why you shouldn’t expose every action to AI 00:48 Introducing WebMCP and Alex Nahas 01:20 How Alex started working on WebMCP 04:23 The browser and the authentication problem 06:56 What an agent-accessible web looks like 09:32 A web for agents, people, or both? 10:00 Why user interfaces still matter 12:31 “My website already has APIs. Why add WebMCP?” 14:03 What should people control in the interface? 14:22 Which actions should a website expose to agents?
Explore episode
57:54July 28, 2026
Backend Engineering Isn't Dying. It's Evolving || Solomon Eseme
In this episode of Talks with Ido Evergreen, I'm joined by @solomoneseme Solomon Eseme, Senior Backend Engineer and educator, to unpack the realities of backend engineering in the age of AI. We discuss: What backend engineers actually do beyond building APIs Backend as a Service vs traditional backend architecture AI's impact on backend engineering System design and scalability Vendor lock-in and long-term architectural decisions How junior developers should learn backend today The skills AI can't replace Advice for developers building a long-term career Checkout Mastering backend: https://masteringbackend.com/ 🔔 Subscribe for more conversations with engineers, founders, and product builders shaping the future of technology. #BackendEngineering #SoftwareEngineering #AI #SystemDesign #Developer #Programming #Podcast #TechPodcast #SolomonEseme #IdoEvergreen
Explore episode
56:33December 25, 2025
Tanstack AI - Alem Tuzlak
TanStack AI is one of the most talked-about AI SDKs right now, and it’s still in alpha. In this episode, I’m joined by Alem Tuzlak, core maintainer at TanStack and lead on TanStack AI and TanStack DevTools, to break down what TanStack AI actually is, why it was built, and where it’s headed. Follow Alem's on X : https://x.com/AlemTuzlak 00:00 -- Introduction 02:00 – Alem’s background & open-source journey 03:00 – What daily life as an open-source maintainer looks like 07:15 – Why TanStack AI was created 09:50 – How TanStack AI differs from other AI SDKs 13:00 – Type safety, APIs, and DX philosophy 16:30 – Framework-agnostic design explained 19:30 – Learning curve of building AI apps 22:00 – Tool calling and real-world AI workflows 27:30 – Handling new model releases and TypeScript updates 31:15 – Common mistakes developers make with AI 33:10 – How TanStack AI fits into the TanStack roadmap 37:00 – Alpha launch feedback and GitHub growth 39:30 – Hardest parts of maintaining TanStack AI 43:20 – How to contribute to TanStack AI 47:50 – AI tools Alem actually uses 49:00 – Final thoughts and what’s coming next
Explore episode
57:11December 16, 2025
Software Testing 101 - Artem Zakharchenko
In this new episode, Artem Zakharchenko @kettanaito creator of Mock Service Worker (MSW) and a Testing Instructor at Epic Web join me to break down why testing is the most valuable skill a developer can master. Artem argues that testing is an inseparable part of development, not a chore, and explains how to build trust in your code by writing effective tests. He tackles common developer frustrations, from the fear of over-testing to the headache of flaky tests, and offers his best-kept secrets for maintaining a high-quality test suite using modern tools like Playwright and Vitest. If you're starting your testing journey, dealing with brittle end-to-end tests, or simply looking to elevate your code quality, this conversation is essential viewing! Connect & Resources: Artem's Website: kettanaito.com Artem on X (Twitter): https://x.com/kettanaito?lang=en Artem's Workshops & Articles (Epic Web): EpicWeb.dev/contributors/artem-zakharchenko Timestamp 00:00 Introduction to Testing and Background 03:16 Understanding Software Testing 06:37 Common Misconceptions About Testing 09:40 The Concept of Over-Testing 13:30 Examples of Useless Tests 17:41 Focusing on Business Logic 22:22 The Role of Tools in Testing 24:25 Challenges for New Testers 26:47 Dealing with Flaky Tests 30:00 Understanding Test Driven Development (TDD) 30:55 The Nature of Software Development 33:12 Understanding Test-Driven Development (TDD) 35:46 Testing Before Shipping: Finding the Balance 38:08 Personal Testing Processes and Best Practices 41:07 Naming and Organizing Tests 45:09 Common Mistakes in Testing 47:07 The Future of Testing with AI 51:04 Advice for New Developers on Testing 52:15 Collecting Metrics on Test Coverage 54:15 Upcoming Workshops on Testing
Explore episode
34:25December 9, 2025
Vibe Coding , MCP and AI Agents - Rizel Scarlett
In this conversation, Rizel Scarlett joins me and dives into how AI is reshaping the way developers work. Rizel walks through what Goose actually is, why MCP matters, and how agents move beyond autocomplete into real autonomy. We get into practical workflows, how to keep agents from hallucinating, what tasks you should hand off vs keep for yourself, and why the Chrome DevTools MCP server changes the game. If you’ve been curious about agentic workflows, vibe-coding, or the future of engineering productivity, this episode lays it out in a way that actually makes sense. Timestamp: 00:00 — introduction 02:45 — What exactly is Goose? 05:10 — How does Goose differ from a normal LLM? 07:58 — Can AI help developers solve harder problems? 09:40 — When should you trust an agent vs doing it yourself? 11:12 — What does a healthy AI-powered workflow look like? 14:40 — What are MCPs and why do they matter? 17:30 — How does the Chrome DevTools MCP server help engineers? 19:55 — What does “vibe coding” actually mean? 23:30 — How do you avoid hallucinations from agents? 25:20 — What are the best ways to use AI in development today? 27:05 — Which tools or workflows are worth learning now? 29:10 — Where is AI tooling heading next?
Explore episode
YOUR HOST, IDO EVERGREEN
A developer.
An educator.
Always curious.
I sit down with developers and creators to understand the ideas, decisions, and people behind the tools we use. Come for the technology. Stay for the conversation.
A little more about me