In this episode of the Elixir Mentor Podcast, I chat with Elixir creator José Valim about Tidewave, the AI coding agent that lives inside your web framework. José shares the journey from falling in love with MCP to discovering its limitations, and how Tidewave solves the copy-paste problem that plagues AI-assisted development.

We explore how Tidewave integrates directly with your browser to eliminate tedious workflows, automatically detecting exceptions and validating changes without manual intervention. José explains why the tool now supports Phoenix, Rails, Django, FastAPI, Flask, and Next.js, and how building one feature benefits all frameworks simultaneously. The conversation covers prompting strategies, context management, and the unique challenges of building Tidewave with Tidewave.

José offers candid insights on why MCP has fundamental limitations for user experience, the security concerns around AI agents, and why Elixir's message-passing architecture makes it ideal for building agentic systems. We discuss the evolving type system in Elixir, code review workflows with AI, and the upcoming Tidewave features including multi-element inspection and symbol search.

The episode concludes with José's perspective on transitioning from open source maintainer to product owner, collecting user feedback through Discord, and exciting developments with Tauri for building desktop applications with Elixir. This conversation provides valuable insights for developers interested in AI-powered tooling and the future of web development.

Resources Mentioned:
- Code Benchmark: https://github.com/Tencent-Hunyuan/AutoCodeBenchmark

Connect with José:
- X: https://x.com/josevalim
- Tidewave: https://tidewave.ai
- Dashbit: https://dashbit.co

SUPPORT ELIXIR MENTOR
- Elixir Mentor: https://elixirmentor.com

In this episode, I chat with Alex Koutmos, author of Elixir Patterns and creator of numerous open source libraries, about building EagleMMS—a SaaS platform helping collision repair shops accurately calculate consumable costs for vehicle repairs. Alex shares his journey from two failed startups to building a profitable business with nearly a thousand customers.

We discuss the outdated methods insurance companies use to calculate repair costs, the brutal reality of door-to-door sales, and how Alex's brother (a licensed auto body technician and appraiser) became his co-founder and sales partner. Alex explains why customer support load is heavier than expected when dealing with insurance company pushback and how they coach shops through negotiations.

On the technical side, Alex walks through his evolution from a Vue SPA to a full LiveView application, building PWAs that work seamlessly on mobile, and why Elixir has never been a bottleneck for his business needs. We cover ETS caching strategies for performance, database backup lessons learned the hard way, and why he refuses to do standups. Alex also previews his upcoming books on financial analytics with Explorer and Scholar, plus a Nerves book entering beta soon.

Connect with Alex:
- X: https://x.com/akoutmos
- Books: https://akoutmos.com/top/books/
- EagleMMS: https://eaglemms.com/

SUPPORT ELIXIR MENTOR
- Elixir Mentor: https://elixirmentor.com

In this episode of the Elixir Mentor Podcast, I chat with Nathan Hessler, an Elixir developer and organizer of the ExMex conference in Austin. Nathan shares his experience launching a successful regional conference just two weeks prior, offering invaluable insights for anyone considering organizing their own tech event.

We explore the intricate logistics of conference planning, from choosing the perfect venue to managing sponsorships and hidden costs. Nathan reveals why he opted for a single-track format at Capital Factory, how he approached speaker selection to promote new voices in the community, and the creative process behind ExMex's clever Texas-themed naming convention.

Our conversation shifts to Nathan's decade of experience in engineering leadership, where he shares wisdom on building healthy engineering cultures. We discuss the critical soft skills needed for technical management, strategies for creating trust and respect within teams, and how to foster environments where constructive debate thrives. Nathan emphasizes that the best engineering teams aren't built on shared hobbies but on mutual respect and the ability to engage in productive disagreement.

The episode concludes with practical advice for aspiring conference organizers, including the importance of talking to other organizers, loving your speakers, and celebrating the unique character of your location. Nathan also reveals plans for RBQ, his upcoming Ruby conference scheduled for March 2025, continuing his mission to strengthen the Austin tech community through meaningful in-person connections.

Resources Mentioned:
- ExMex Conference: https://exmexconf.com/
- RBQ Conference: Upcoming Ruby conference in Austin (March 2025)
- Capital Factory: Conference venue in Austin

Connect with Nathan:
- LinkedIn: https://www.linkedin.com/in/nathanhessler/
- Website: https://hesslerconsulting.com/
- ExMex: https://exmexconf.com/

SUPPORT ELIXIR MENTOR
- Elixir Mentor: https://elixirmentor.com/?utm_source=elixir-mentor
- Discord: https://elixirmentor.com/discord

In this episode of the Elixir Mentor Podcast, I sit down with Daniil Popov to discuss CyanView, a system that brings Phoenix LiveView to embedded devices for professional video production. We examine the challenges of creating unified camera control systems that work across 27+ different protocols from manufacturers like Sony, Canon, and RED.

Daniil shares how CyanView enables real-time camera shading for major broadcast events including the Olympics, Super Bowl, and Le Mans races. We discuss the technical implementation of LiveView on resource-constrained 32-bit ARM processors, managing distributed systems with MQTT, and solving complex problems like socket reconnection and performance optimization on embedded devices.

Our conversation covers the unique advantages of using Elixir for embedded systems, from binary pattern matching for protocol reverse engineering to supervision trees for fault tolerance. Daniil explains how they utilize nearly 80% of Elixir's capabilities—far more than typical web applications—including NIFs for C integration, custom FPGA modules for color correction, and practical approaches to creating responsive interfaces on limited hardware.

The episode wraps up with discussion of the future of camera control technology, the challenges of working with proprietary protocols, and why Elixir's actor model and distributed computing capabilities make it uniquely suited for this complex problem space. Whether you're interested in embedded systems, LiveView applications, or the intersection of hardware and software, this conversation offers valuable perspectives on pushing Elixir beyond traditional web development.

Resources Mentioned:
- CyanView:https://cyanview.com/
- Phoenix LiveView Documentation
- MQTT Protocol and Mosquitto
- Burrito and Tauri for Binary Compilation

Connect with Daniil:
- X/Twitter:https://x.com/mrpopov_com

SUPPORT ELIXIR MENTOR
- Elixir Mentor:https://elixirmentor.com/?utm_source=elixir-mentor

In this episode of the Elixir Mentor Podcast, I chat with Mike Hostetler, creator of the Jido agent framework and ReqLLM library. Mike shares his journey building a unified interface for calling multiple LLM providers in Elixir, addressing the frustrating inconsistencies between different AI APIs.

We dive into ReqLLM's architecture, exploring how it normalizes the differences between providers like OpenAI, Anthropic, Google, and more. Mike explains his decision to build a lightweight alternative to existing libraries like Instructor and LangChain, creating something that handles streaming, tool calling, and structured outputs with simple one-line function calls.

Mike demonstrates the library live, showing how to test 112+ models across different providers, handle streaming responses, and calculate token usage costs. We discuss the challenges of supporting multiple providers, from handling deprecated models to dealing with provider-specific headers and parameter variations.

The conversation also covers Jido's evolution, the upcoming Phoenix dashboard for managing agents, and Mike's vision for hierarchical agent systems in Elixir. We explore how ReqLLM fits into the broader Elixir AI ecosystem and discuss future plans for local LLM support and integration with frameworks like Ash.

Resources Mentioned:
- ReqLLM GitHub: https://github.com/agentjido/req_llm
- Jido Framework: https://agentjido.xyz
- models.dev: https://models.dev

Connect with Mike:
- GitHub: https://github.com/agentjido
- Website: https://mike-hostetler.com

SUPPORT ELIXIR MENTOR
- Elixir Mentor: https://elixirmentor.com

In this episode of the Elixir Mentor Podcast, I sit down with Bobby Clayson, CEO of Crofter Market, who's tackling one of America's biggest challenges: food system centralization. Bobby shares his journey from building Tax Bit in the cryptocurrency space to creating a marketplace that connects local farmers directly with consumers.

We dive deep into the technical and business challenges of building a two-sided marketplace with Elixir. Bobby explains how COVID exposed critical weaknesses in our food supply chain—from beef rationing while farms had surplus livestock to the loss of 50% of American ranchers over four decades. He shares how Crofter evolved from a simple directory to a full third-party logistics operation with refrigerated delivery.

The conversation covers crucial startup lessons: solving the cold start problem, building trust with non-technical farmers, knowing when to pivot, and the importance of stepping away from code as a technical founder. Bobby offers candid advice about fundraising, hiring in the Elixir ecosystem, and why passion for your problem matters more than your idea. He emphasizes how functional programming naturally aligns with distributed systems and why Elixir's fault tolerance makes it perfect for marketplace infrastructure.

This episode provides valuable insights for anyone building marketplaces, working with physical logistics, or transitioning from technical to leadership roles. Bobby's story demonstrates how technology can address real-world problems while supporting local farmers and improving public health through better food access.

Resources Mentioned:
- Crofter Market: https://crofter.com
- The Cold Start Problem by Andrew Chen
- Platform Revolution

Connect with Bobby:
- LinkedIn: https://www.linkedin.com/in/bobbyclayson/

SUPPORT ELIXIR MENTOR
- Elixir Mentor: https://elixirmentor.com

In this episode of the Elixir Mentor Podcast, I sit down with Barnabas Jovanovics, a core engineer on the Ash framework team. Barnabas shares his unique journey from working as an electrician and automation engineer to becoming a key contributor to one of Elixir's most powerful frameworks.

We explore how Barnabas discovered Ash while building a booking platform, initially skeptical but quickly becoming convinced by its power. He discusses his major contributions including Ash RBAC for simplified role-based access control and GraphQL subscriptions, as well as his current work on a Discord bot framework that leverages Ash's architecture patterns.

Our conversation covers the philosophy of open source development, the challenges of maintaining large projects, and the exciting new Ash TypeScript integration that just launched. This feature automatically generates type-safe TypeScript client code from your Ash resources, supporting both fetch and Phoenix channels for real-time communication.

We also discuss valuable perspectives on the Elixir community, conference experiences at Goatmire and Alchemy Conf, and practical advice for developers navigating the rapidly evolving landscape of AI-assisted programming. Whether you're new to Ash or an experienced user, this conversation provides valuable insights into the framework's architecture and future direction.

Resources Mentioned:
- Ash Framework: https://ash-hq.org/

Connect with Barnabas:
- X: https://x.com/barnabasMJ

SUPPORT ELIXIR MENTOR
- Elixir Mentor: https://elixirmentor.com

In this episode of the Elixir Mentor Podcast, I welcome back Michael Lubas, founder of Paraxial.io, where he's building comprehensive security tooling specifically designed for the Elixir ecosystem. We explore how AI-generated code is impacting application security and why traditional scanning tools aren't catching critical vulnerabilities.

Michael shares his experience with the most common security mistakes in Elixir projects, including binary deserialization exploits that can lead to remote code execution. We discuss how Phoenix 1.8's improved security documentation helps developers, the rise of organized ransomware attacks, and why security scanning is more crucial than ever with AI-assisted development becoming mainstream.

Our conversation covers the challenges of enterprise security tooling, the differences between Rails and Elixir security patterns, and how Paraxial 3.0 is addressing the unique needs of Elixir developers. Michael explains why most enterprise security tools fail developers and how Paraxial takes a developer-first approach to vulnerability detection and remediation.

We also discuss the future of AI in software development, identity verification challenges in an age of deepfakes, and the evolving hiring landscape for developers. This conversation provides essential context for anyone building production Elixir applications or concerned about security in the age of AI-generated code.

Resources Mentioned:
- Paraxial.io Security Platform: https://paraxial.io/
- Phoenix Security Documentation: https://hexdocs.pm/phoenix/security.html

Connect with Michael Lubas:
- X/Twitter: https://x.com/paraxialio
- LinkedIn: https://www.linkedin.com/in/michaellubas/

SUPPORT ELIXIR MENTOR
- Elixir Mentor: https://elixirmentor.com

In this episode of the Elixir Mentor Podcast, I chat with Chris McCord, creator of Phoenix Framework and LiveView. We dive deep into Phoenix 1.8's groundbreaking AI features, including the revolutionary AGENTS.md file that's transforming how developers work with LLMs in their Elixir applications.

Chris shares the fascinating evolution from Phoenix channels to LiveView, explaining how his early experiments with real-time Rails applications led to creating the framework that powers some of today's most ambitious web applications. We explore Phoenix.new, the browser-based development platform that lets anyone build Elixir apps without installing anything locally, and discuss how Tidewave MCP brings intelligent AI assistance directly into your development workflow.

Our conversation reveals why Elixir's concurrency model and OTP primitives make it the perfect platform for building AI agents, with Chris explaining how gen servers naturally solve the complex state management and routing problems that other ecosystems struggle with. He provides valuable insights on using LLMs effectively in development, from avoiding common pitfalls to leveraging AI for code porting and debugging.

The episode concludes with Chris's thoughts on open source sustainability, the importance of community culture, and practical advice for developers looking to level up their skills with AI-assisted development. This conversation offers essential perspective for anyone working with Elixir or considering how AI will shape the future of software development.

Resources Mentioned:
- Phoenix Framework: https://phoenixframework.org/
- Metaprogramming Elixir book
- Phoenix.new - Browser-based development platform
- Tidewave MCP - Local AI development integration

Connect with Chris:
- Website: https://chrismccord.com/
- LinkedIn: https://www.linkedin.com/in/chris-mccord-98b47a37/

SUPPORT ELIXIR MENTOR
- Elixir Mentor: https://elixirmentor.com

In this episode of the Elixir Mentor Podcast, I chat with Adam Kirk, CTO and co-founder of Jump, where they're building AI-powered meeting intelligence for financial advisors. We dive deep into scaling Elixir applications, managing LiveView at thousands of concurrent connections, and building high-performance teams in competitive markets.

Adam shares his fascinating journey from PHP and Rails to Elixir, explaining how Jump pivoted from sales automation to financial advisor tools and found explosive product-market fit. We explore the technical challenges of real-time meeting processing, AI cost optimization, and the unique compliance requirements of the financial sector.

Our conversation covers Jump's innovative hiring philosophy, including their distinctive approach of 30-minute coding assessments followed by paid trial weeks. Adam explains how they've successfully hired 40+ engineers, many learning Elixir on the job, while maintaining a strong culture of full-stack ownership and work-life balance.

We also discuss practical aspects of scaling with LiveView, handling WebSocket reconnections gracefully, and why they chose Oban over traditional GenServer patterns in their Kubernetes environment. This episode provides valuable insights for anyone building AI-powered applications, scaling engineering teams, or navigating the challenges of startup growth.

Resources Mentioned:
- Jump: https://jumpapp.com/
- Jump Careers: https://careers.jumpapp.com/
- Adam on X: https://x.com/atomkirk

SUPPORT ELIXIR MENTOR
- Elixir Mentor: https://elixirmentor.com
- Recruitment Services: https://elixirmentor.com/?utm_source=elixir-mentor