Domesticating AI

Domesticating AI is a bi-weekly podcast about practical AI for developers. We cover self-hosted models, local AI, homelabs, hardware, agents, security, and reliability so software engineers can build - Miriah Peterson: Software engineer, Go educator, and community builder focused on *production-first* AI. Runs SoyPete Tech (streams + writing + open-source).- Matt Sharp: AI Engineer/Strategist, co-author of *LLMs in Production*, MLOps practitioner. Writes **The Data Pioneer**.- Chris Brousseau: NLP practitioner, co-author of LLMs in Production, VP of AI at VEOX. You can find him as IMJONEZZ

Domesticating AI is a technology podcast hosted by SoyPete Tech, with 17 episodes on record and a Required Pod Score of 80. PitchCentric scores this show on Booking Probability, Listen Score, and live audience signals refreshed every 24 hours.

SoyPete Tech hosts Domesticating AI, a technology show with 17 episodes published.

Our AI reads these to draft pitches. Use them as grounding for a pitch that cites a real guest and a specific topic.

• 

  Episode #17

  AI Agents, Data Models, and the Post-Literate Engineer — with Joe Reis

  Sep 11, 202648 minS1

  AI agents can consume more information than ever. That doesn't mean they understand your data. For the Season 1 finale of Domesticating AI, we're joined by Joe Reis, co-author of Fundamentals of Data Engineering , for a conversation that went somewhere completely different than we planned. We start with Joe's practical take on local AI. If subscriptions to frontier models are cheaper than buying hardware, when does self-hosting actually make sense? Privacy, IP, fine-tuning, and inference costs at scale all change that calculation. Then we get into data modeling. Humans are remarkably good at working around bad schemas, missing documentation, tribal knowledge, and ambiguous business definitions. Agents aren't. If machines are going to operate on our data, the structure, relationships, provenance, and meaning of that data become much harder to ignore. From there, things get weird. We talk about corporate knowledge bases, ontologies, the post-literate engineer, AI-generated summaries, whether engineers still need to read the research, and the increasingly shaky state of reproducible AI benchmarks. Topics include: • Local models vs. cloud AI economics • Bonsai 27B and 1-bit models on phones • Data modeling for AI agents • Knowledge bases and organizational knowledge • Ontologies and semantic modeling • The post-literate engineer • AI summaries vs. actually reading research • Reproducibility and AI benchmarks • Why agent security doesn't require Skynet to be dangerous Links mentioned: Joe Reis — The Post-Literate Engineer https://joereis.substack.com/p/the-post-literate-engineer Joe Reis — Practical Data Modeling / Mixed Model Arts https://practicaldatamodeling.substack.com/ The Mixed Model Arts Manifesto https://practicaldatamodeling.substack.com/p/the-mixed-model-arts-manifesto Fundamentals of Data Engineering — Joe Reis & Matt Housley https://www.oreilly.com/library/view/fundamentals-of-data/9781098108298/ PrismML — Bonsai 27B https://prismml.com/news/bonsai-27b DeepSeek V4 Flash https://api-docs.deepseek.com/updates/ William Kent — Data and Reality https://bkent.net/Doc/darxrp.htm Find Domesticating AI: YouTube https://www.youtube.com/@DomesticatingAI Apple Podcasts https://podcasts.apple.com/us/podcast/domesticating-ai/id1873338950 Spotify https://open.spotify.com/show/2WsAR4fvcXzp3vVZGVlkE2 Patreon https://patreon.com/DomesticatingAIPodcast That's a wrap on Season 1. Subscribe so you're here when Season 2 drops. Keep your AI on a leash.

  ListenShow Notes
• 

  Episode #16

  Your Homelab Is Where the Fun Starts

  Aug 28, 202653 minS1

  Your side project starts on the free tier. Then it gets interesting. This week, Tod from Catalyst Community joins us to talk about why the homelab is one of the best places to build open-source software, experiment with AI, and learn the infrastructure underneath the tools we use every day. We get into why Kubernetes does not need to turn you into a Kubernetes administrator, how Foundry is making it easier to stand up K3s on your own hardware, and why tools like Helm make adding databases, monitoring, storage, and other services much less painful once the foundation exists. Tod walks us through his own homelab: Proxmox, Debian, a three-node Kubernetes cluster, separate storage and GPU machines, and the open-source tooling he uses to build on top of it. We also get into Tailscale, KServe, Ray, CloudNativePG, Prometheus, Grafana, Loki, Whisper, and running GPUs both inside and outside Kubernetes. But the bigger conversation is about building. Matt talks about the GPU machine he originally bought to train a StarCraft bot and how that experimentation turned into skills he could use professionally. Miriah talks about replacing a Supabase free-tier database with Postgres on her homelab. Tod talks about replacing GitHub-hosted CI/CD infrastructure with his own open-source system. The common thread: doing the foundational work once gives you a platform where the next idea is much cheaper to try. And with modern hardware, open-source software, and LLM-assisted development, the barrier to building something useful at home has never been lower. So our question for you: What are you building for yourself, for fun, or for open source? Projects mentioned in the episode include Foundry, K3s, Kubernetes, Helm, Proxmox, Tailscale, KServe, Ray, CloudNativePG, Prometheus, Grafana, Loki, MLflow, Whisper, Render, Supabase, and Anthropic Claude. Keep your AI on a leash.

  ListenShow Notes
• 

  Episode #12

  The Skills Every AI Engineer Needs in 2026

  Jul 3, 202637 minS1

  Everyone seems to be hiring AI engineers—but what does that actually mean? Using Claude Code, Cursor, or ChatGPT doesn't automatically make someone an AI engineer. So where's the line between software engineering with AI and engineering AI systems? This week we're joined by Byron McKay , Director of Learning at Gauntlet AI, to discuss how they train engineers for AI roles, what companies are actually looking for, and why the most important AI engineering skills have surprisingly little to do with prompting. We explore why system design has become essential, why RAG is far from dead, whether you need to self-host or fine-tune models, and why communication and engineering fundamentals are still the biggest predictors of success. If you're wondering what skills to invest in next—or trying to break into AI engineering—this episode is for you. What actually defines an AI engineer? Why system design matters more than ever Is RAG still relevant in 2026? The difference between AI users and AI engineers Why engineering fundamentals still matter Communication as a technical skill Why experimentation is part of the job Do you need to fine-tune or self-host models? How Gauntlet AI prepares engineers for AI careers Advice for learning AI without chasing every new framework Gauntlet AI — https://gauntletai.com LLMs in Production — https://www.manning.com/books/llms-in-production Claude Code — https://www.anthropic.com/claude-code Ray — https://www.ray.io/ Qwen — https://qwen.ai/blog?id=qwen3.5 UV Package Manager — https://docs.astral.sh/uv/ Domesticating AI is a bi-weekly podcast for software engineers building practical AI systems. We cover self-hosted AI, agents, infrastructure, context engineering, security, and the engineering practices that make AI reliable in production. Subscribe wherever you get your podcasts, and if you're enjoying the show, leave a rating and review—it helps more engineers discover the show. Keep your AI on a leash.

  ListenShow Notes
• 

  Episode #11

  Trust AI? Stop Shipping Output You Didn’t Read

  Jun 19, 202636 minS1

  At a recent meetup, a room of about 55 people was asked: do you know every line of code you shipped to production? One person raised their hand: Chris. That moment became the center of this episode. Not because AI-assisted coding is bad, but because it exposes the real risk: developers are starting to trust AI-generated output without fully owning it. In this episode, Miriah, Chris, and Matt talk about AI psychosis: the slow offloading of judgment, skepticism, and responsibility to systems that sound confident by design. We dig into AI slop, sycophantic models, no-slop.ai, Mitchell Hashimoto’s warning about companies operating under AI psychosis, and why “Claude wrote it” is not a defense when production breaks. This is not an anti-AI episode. We use AI constantly. The point is to stop treating AI like an oracle and start treating it like a tool that needs constraints, review, and ownership. Topics: The 1-of-55 meetup story What AI psychosis means for developers Who owns AI-generated code? Why confident output is not the same as correct output no-slop.ai and the rule: don’t send AI output you haven’t read Mitchell Hashimoto on AI psychosis in companies Why arguing with AI usually wastes time How sycophantic models pull users into the spiral Practical ways to keep AI honest Why smaller or self-hosted models can make AI feel less magical Links: no-slop.ai: https://no-slop.ai Mitchell Hashimoto post: https://x.com/mitchellh/status/2055380239711457578 Timnit Gebru post on AI psychosis: https://www.linkedin.com/posts/timnit-gebru-7b3b407_surviving-ai-psychosis-activity-7454588079467593729-X1eT HBR trendslop article: https://hbr.org/2026/03/researchers-asked-llms-for-strategic-advice-they-got-trendslop-in-return Patreon: https://patreon.com/DomesticatingAIPodcast YouTube: https://www.youtube.com/@DomesticatingAI Apple Podcasts: https://podcasts.apple.com/us/podcast/domesticating-ai/id1873338950 Spotify: https://open.spotify.com/show/2WsAR4fvcXzp3vVZGVlkE2 Keep your AI on a leash.

  ListenShow Notes
• 

  Episode #10

  Stop Building AI Agents: Build Harnesses Instead | Hamza Tahir (ZenML / Kitaru)

  Jun 6, 202644 minS1

  <p>Everyone is building AI agents.</p><p>OpenAI SDKs, Claude Code, Deep Agent systems, custom workflows, and orchestration frameworks all promise more autonomous AI. But as these systems become more capable, they start running into familiar engineering problems:</p>retriesstate managementorchestrationcontext controldurable execution<p>This week we're joined by Hamza Tahir, CTO and co-founder of ZenML and creator of Kitaru, to discuss what happens when agents stop being simple chat interfaces and start behaving like long-running distributed systems.</p><p>We explore:</p>what an agent harness actually isdurable execution and why it mattersorchestration vs business logicstate management for...

  ListenShow Notes

Recent guests on Domesticating AI. Study who booked and why before you pitch.

Based on semantic analysis of episode topics and host coverage, this show is a strong guest fit for executives in:

Industry fit is computed by PitchCentric using vector embeddings of the show's episode catalog.