AI product systems
Isaac Flath
I help people building real AI products make retrieval, evals, memory, tools, traces, and product interfaces hold up in use.
Jake Selvey
Director of Analytics & Data Science
Centriam
“If I had to pick one individual to assist me in tackling an unknown data-related problem, large or small, it would be Isaac.”
I work on the parts of AI products that break in use.
The expensive failures usually show up after the demo: retrieval is a little off, context gets dropped, tool calls drift, evals miss regressions, and nobody trusts the trace enough to decide what to fix.
Education
Teach the systems behind reliable AI products
Retrieval, context management, tool calling, orchestration, evals, traces, and the product workflows around them.
Research
Sort the flood of releases into useful judgment
What is hype, what is practical now, and what is worth watching before it becomes a real product decision.
Decisions
Review the artifacts that show where systems break
Logs, traces, evals, screenshots, code paths, and workflow details that make the next engineering move clearer.
AI Engineering Club
AI Engineering Club is the weekly review loop around this work.
A vetted operator community for founders, PMs, Staff+ engineers, and ML engineers who own AI product outcomes. Bring the trace, eval, log, screenshot, workflow, or decision you are stuck on.
Audrey Roy Greenfeld
Co-founder, Feldroy
Co-creator of Cookiecutter; co-author of Two Scoops of Django
“I'm using AI to build everything I've dreamed of building, and it's in big part thanks to these teachings.”
Writing and Field Notes
Essays and tools on retrieval, evals, traces, memory, agents, and the product interface around AI systems.
Hugo Bowne-Anderson
Data & AI scientist, writer, educator, podcaster
“I'll read anything Isaac writes: it's high signal, makes me think, and helps me understand what's happening in AI.”
Teaching and Community
Courses, public writing, and the community all point at the same thing: practical systems people can understand, inspect, and improve.
Active course
Learn RAG
A practical course on retrieval augmented generation, from keyword search and vector search to multimodal retrieval, chat interfaces, and citation generation.
Prior course
AI-Assisted Coding
A course on AI-assisted development. The materials and testimonials show the same pattern: systems, constraints, feedback loops, and practical workflow design.
Emily Ekdahl
Founding AI Engineer
Stealth Startup
“I became radically more effective in how I build with AI agents.”
How I Got Here
I have spent the last 10 years building AI products. Before that, I taught dance full time. The constant has been education: I like helping people get from confused to capable.
Teaching first
I started by teaching dance full time. I loved teaching: taking something that felt hard or awkward and helping someone feel it click.
Operations, data, and software
I moved into operations, data, and software because I wanted to build the systems behind the work. That pulled me from spreadsheets and workflows into code and product.
Ten years in AI products
For the last decade I have worked on AI products and features with startups and larger companies, usually at the point where a promising demo has to become something people can trust.
Writing and teaching now
Now I write, teach, and build around retrieval, memory, evals, tools, traces, agents, and interfaces. It is still education at the core: make the work clear enough that people can use it.
A Personal Note
I met my wife, Alyssa, when we were both teaching dance full time. Dance has been one of the great joys in my life, and it is still a shared part of our story.
She now runs Art of Movement, a dance instruction business in the D.C. area.
Jelle de Jong
Data Specialist
Waterschap Drents Overijsselse Delta
“I can now add features more easily, hunt down and fix bugs faster, and make my code more secure and reliable.”
Stay up to date
I send useful notes when I have something worth sending: lessons from building with clients, new public posts, talks, tools, mistakes, and questions about retrieval, evals, agents, and AI product workflow.
5,000+ readers