Elixir Mentor

In this episode of the Elixir Mentor Podcast, I chat with Mike Ratliff, a 30-year tech veteran and CTO currently building an energy tech startup. Mike shares his path from Ruby threading nightmares to leading 20-engineer Elixir teams, and how discovering the BEAM transformed his approach to building 24/7 grid systems.
We dig into the technical challenges of power grid software, including distributed energy resource management, solar intermittency, and why utilities remain cautious about new technology. Mike explains how his current startup is tackling transmission interconnection problems using Elixir, and his plans to incorporate AI agents through the Jido framework.
The conversation shifts to how AI is reshaping development teams and startup economics. Mike makes a compelling case for small, elite teams over large engineering organizations, sharing his philosophy on profit per headcount and why he believes we'll see one-person unicorn companies emerge. We discuss rethinking technical interviews for the LLM era, the Ash framework in production, and why great engineers become even greater with AI tools.
Mike wraps up with hard-won startup wisdom: build painkillers not vitamins, learn to tell stories that move people, and understand that nobody buys on facts alone. Whether you're building energy infrastructure or SaaS products, this conversation offers practical perspective on scaling with small teams.
Connect with Mike:
- LinkedIn: https://www.linkedin.com/in/mike-ratliff-3096571/
Sponsors:
- Paraxial.io: https://paraxial.io
- Jido Discord: https://agentjido.xyz/discord
SUPPORT ELIXIR MENTOR
- Elixir Mentor: https://elixirmentor.com/?utm_source=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/beads
Connect 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=en
SUPPORT 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/soothsayer
Connect with George:
- X: https://x.com/georgeguimaraes
- Website: https://georgeguimaraes.com
SUPPORT 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-engineering
Connect with Isaak:
- X: https://x.com/realMrLaminar
- LinkTree: https://linktr.ee/tisaakx
SUPPORT ELIXIR MENTOR
- Elixir Mentor: https://elixirmentor.com/?utm_source=elixir-mentor