Build a production AI app in one Saturday
RAG, agentic retrieval, evals and observability. Eight hours live with me building one real app from an empty folder. Then 30 days of Slack and office hours to make it work at your actual job.
No ML degree. No math. A lot of code.
Leave with a working AI app, or I fix it with you 1:1 or refund you. Your choice.
Your employer can probably pay. You get an invoice and a budget request template.
What developers are saying
Loading student reviews...
Using Claude every day is a fine habit. It won't get you through an AI engineer interview.
I helped design the interview process for an "AI Engineer" role at a startup I worked for. Nobody asked which chatbot you like. They asked how you'd chunk a pile of documents, what you'd do when retrieval comes back with garbage, and how you'd know your agent quietly got worse after a prompt change.
None of this needs a math degree. Most experienced developers can learn it. What's hard to find is someone who already made the expensive mistakes and can show you where things break.
That's what this Saturday is for.
What you walk away with
A working full-stack AI app
Load real documents, chunk and embed them, store them in a vector database and serve answers through an API and a UI. Built by you.
Agentic retrieval
An agent that writes its own search queries, decides when it has enough context and uses tool-calling with structured outputs.
Evals and observability
Tests that tell you when the agent is wrong, plus tracing so you can see token cost, latency and exactly what the model saw.
30 days of Slack + office hours
Slack access and weekly live office hours after the workshop. Bring your plan, your code or your boss's weird requirements and we figure out how to make it real at your company.
The full curriculum
Access to the Parsity AI engineering curriculum so you can keep going deeper on RAG, agents and evals at your own pace. Plus the recording of the whole day.
Jobs platform invite
An invite to a private platform where I share exclusive AI engineering roles. Not a job guarantee, just a direct line to companies hiring for this.
How the day goes
One app, from an empty folder to something with evals and tracing. Pacific time.
- 9:00Kickoff and setup checkHow LLMs and embeddings work, in plain English.
- 9:30Data for LLMsLoading documents, chunking strategies, metadata and storing vectors.
- 11:00Retrieval that doesn't suckSemantic search, metadata filters, relevance thresholds and re-ranking.
- 12:15LunchStep away from the screen.
- 1:00Agentic retrievalTool-calling, letting the agent plan its own queries, structured outputs.
- 2:30Make it full-stackWire the agent to an API and a UI people can actually use.
- 3:30EvalsTest cases, LLM-as-judge and catching regressions before your users do.
- 4:30ObservabilityToken cost, latency and traces. See where the agent goes off the rails.
- 5:15Your project planMap your own idea onto this architecture and leave with next steps.
- 5:45Q&A and wrapDone by 6pm.
Leave with a working app or don't pay
The guarantee
Show up and build along all day. If you don't leave with a working AI app, I'll get on a call and fix it with you 1:1, or refund you in full. You pick.
I don't take people's money and not deliver.
Your company can probably pay
Most companies have a learning budget that goes unused. You get an invoice at checkout plus a training budget request template written for your manager. A lot of our students go this route.
Is this right for you?
You're a good fit if
- You write code for a living, or you can drive Claude Code or Cursor well enough to ship working code and understand what it wrote.
- You keep hearing RAG, agents and evals and want to build them once, properly.
- You built a tutorial chatbot and aren't sure what you actually built.
- You want something real to show for your Saturday.
Skip this one if
- You've never written code. This moves fast and I won't be teaching loops.
- You want a slide deck about the future of AI. We'll be in an editor most of the day.
- You're already shipping RAG pipelines with evals in production. You'll be bored.
Taught by someone who has shipped this
I'm Brian Jenney. I've built and led production AI systems, including RAG pipelines and agents, at two companies with very different products. Both times I hit the problems you'll hit, usually the expensive way.
Only 20 seats, because I'll be looking at your code all day.
Questions people ask
What if I can't make the whole day live?
Everything is recorded, and you can move to the next workshop Saturday for free. Live is better because you can ask questions while you build.
How do the 30 days of Slack and office hours work?
For four weeks after your Saturday you're in our Slack, and there's a weekly live office hours session. Bring your project plan, your code or questions about getting this approved at work. You also get the full self-paced curriculum.
How does the guarantee work?
Build along during the day. If you don't have a working AI app by the end, email us. I'll fix it with you on a 1:1 call or refund you in full. Your choice.
Is the jobs platform a job guarantee?
No. You get an invite to a private platform where I share exclusive AI engineering roles. It's access to opportunities, not a promise of a job.
Do I need to know AI or machine learning already?
No. You need to know how to code, or be able to use coding agents well enough to build and read real code. We cover the AI parts from the ground up.
Can my company pay for this?
Probably. You get an invoice at checkout and a training budget request template you can send your manager.
What do I need on the day?
A laptop with a dev environment you like and a decent internet connection. Setup instructions go out before the workshop. API credits for the day are covered.
Ready player one?
Leave with a working app, or I fix it with you or refund you. Questions? assistant@parsity.io
