Elixir Mentor

In this episode of the Elixir Mentor Podcast, I chat with Coby Benveniste and Daniel Garcia-Shulman from MarkeTeam.ai about building intelligent AI marketing agents with Elixir. They share their experience migrating from Python and React to a full Elixir and LiveView stack, and explain why the BEAM VM is ideal for powering autonomous agent workflows.Coby and Daniel explain their approach to agent architecture, including why they chose gen state machine over gen server for managing agent state machines. They walk through the ReAct pattern (reasoning, actions, observations) and how it maps naturally to Erlang's state machine behaviors. The conversation covers their custom marketing strategy LLM, how they use RAG patterns for brand context, and why specialized agents outperform single all-purpose agents.We explore the technical details of their stack, including how they handle DevOps without a dedicated team using mix release, their use of Fun with Flags for feature flagging, and how Broadway and Oban power their data pipelines. The discussion also covers practical workflows with Claude Code, context management using Beads, and the usage rules library for better LLM documentation.The episode wraps up with insights on hiring Elixir developers, the emerging field of AEO (Answer Engine Optimization), and advice for developers learning Elixir with LLM assistance. Whether you're building AI agents, exploring marketing automation, or curious about advanced Elixir patterns, this conversation offers practical insights from engineers shipping production AI systems.Resources Mentioned:- MarkeTeam AI: https://www.marketeam.ai- Beads (Claude Code context tool): https://github.com/steveyegge/beadsConnect with Coby & Daniel:- Coby: https://www.linkedin.com/in/coby-benveniste/- Daniel: https://www.linkedin.com/in/danielegsh/SUPPORT ELIXIR MENTOR- Elixir Mentor: https://elixirmentor.com

Mikh Ahmed joins me to talk about SWARMMO, a massively multiplayer online browser game he's building entirely with Elixir and Godot. After experiencing burnout from AWS Lambda and serverless tooling at a Canadian fintech startup, Mikh discovered Elixir and realized it was exactly what he'd been looking for to build his dream game project.We explore how the BEAM's actor model maps perfectly to game architecture, with individual player processes, hierarchical AI units that form squads and platoons, and a simulation where NPCs actively compete for territory. Mikh shares his experience going from zero Elixir knowledge to building a game server that can handle a thousand concurrent AI units while using only 4GB of RAM and 50% CPU.The conversation covers the realities of indie game development: failed crowdfunding campaigns that led to private support, the challenge of marketing when you'd rather be coding, and plans for a Steam release and version 1.0 launch. We also discuss the potential for LLM-powered NPC personalities, why minimal dependencies matter, and how game design psychology from board games applies to digital experiences.Connect with Mikh:- X: https://x.com/SWARMMOOFFICIAL- SWARMMO: https://swarmmo.games/?lang=enSUPPORT ELIXIR MENTOR- Elixir Mentor: https://elixirmentor.com/?utm_source=elixir-mentor

In this episode of the Elixir Mentor Podcast, I chat with George Guimarães about Soothsayer, his time series forecasting library inspired by NeuralProphet and built on Axon and NX for business data analysis.We explore how Soothsayer decomposes business data into seasonal components, handles holidays as special events, and uses neural networks to model nonlinear patterns. George explains why Elixir's ecosystem with NX, Axon, and Bumblebee provides unique advantages for machine learning workflows, allowing you to run models directly in your supervision tree without external infrastructure.The conversation expands into why Elixir is particularly well-suited for AI agent development. George shares insights from his current work building agentic commerce solutions, where the BEAM's actor model, fault tolerance, and message passing provide battle-tested patterns that other ecosystems are now trying to replicate for LLM workflows. We also discuss AEO (Agent Engine Optimization) as the new SEO, and how websites will evolve to serve both human and agent visitors.Whether you're interested in time series forecasting, building AI-powered applications in Elixir, or understanding why the BEAM's concurrency model is perfect for the agentic future, this conversation offers valuable perspective from an Elixir community OG.Resources Mentioned:- Soothsayer: https://github.com/georgeguimaraes/soothsayerConnect with George:- X: https://x.com/georgeguimaraes- Website: https://georgeguimaraes.comSUPPORT ELIXIR MENTOR- Elixir Mentor: https://elixirmentor.com/?utm_source=elixir-mentor

In this episode of the Elixir Mentor Podcast, I chat with Isaak Tsalicoglou, author of Elixir Software Engineering. Isaak shares hard-won lessons from building production Elixir API clients, covering validation strategies, error handling approaches, authentication flows, and architectural patterns that actually work in the real world.We explore Isaak's journey back into programming through building internal tools for his family's industrial equipment business, and how that led to writing a comprehensive guide on REST API client development. He explains his approach to request validation, why he ultimately decided against using Ecto schemas for API responses, and the importance of resisting unnecessary complexity in software architecture.The conversation covers practical API design topics including how to structure clean RESTful routes, avoiding tight coupling between APIs and UIs, and finding the right balance between over-serving and under-serving data. Isaak also shares his thoughts on LLM-assisted development, explaining why he prefers using AI as a code reviewer rather than fully automated coding, and discusses his self-hosting infrastructure setup for privacy-conscious applications.This episode offers valuable insights for anyone building API clients in Elixir or thinking critically about software architecture decisions and their long-term implications.Resources Mentioned:- Elixir Software Engineering: https://leanpub.com/elixir-software-engineeringConnect with Isaak:- X: https://x.com/realMrLaminar- LinkTree: https://linktr.ee/tisaakxSUPPORT ELIXIR MENTOR- Elixir Mentor: https://elixirmentor.com/?utm_source=elixir-mentor

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/AutoCodeBenchmarkConnect with José:- X: https://x.com/josevalim- Tidewave: https://tidewave.ai- Dashbit: https://dashbit.coSUPPORT ELIXIR MENTOR- Elixir Mentor: https://elixirmentor.com