Live cohorts · weekends

Learn AI by shipping it.

Every session ends with something that runs — a deployed app, a working agent, a live voice bot. You finish with a portfolio, not a certificate.

Programs

Pick a cohort and start building

Eight weekends of building. Every session ends with something that runs.

How a weekend runs

How the thing actually works underneath — token sampling, distance metrics, agent loops, audio pipelines.

How engineers assemble it in production: the trade-offs, the failure modes, the cost decisions.

We build it together, on screen, start to finish. When the hour ends, it runs on your machine.

What you walk away with

W1
LLM foundations and the four pillars of AI engineering
A custom Claude Code skill that drafts technical posts from your week's code activity, plus the reasoning engine behind an AI travel planner.
W2
Enterprise RAG and knowledge graphs
A document assistant that answers from internal policy PDFs with page-level citations, and a knowledge graph for multi-hop questions.
W3
AI-assisted web coding and one-click deployment
A live portfolio website, and the Week 1 travel planner wired to a React front end on a public URL.
W4
Tool-calling agents and the Model Context Protocol
Your own MCP server with authenticated access to your machine, plus an agent that tailors a PDF resume per job listing.
W5
Real-time voice agents
Two voice agents: one enterprise-grade at sub-800 ms latency, one on an open-source stack at a fraction of the cost.
W6
Multi-agent orchestration and building "Jarvis"
A four-agent research swarm and "Jarvis", a desktop assistant for calendar, email and files on near-zero API spend.
W7
Digital twins and the multi-channel brand engine
Your digital twin plugged into a pipeline that scripts, renders and stages posts across platforms.
W8
Capstone hackathon and demo day
A capstone product, deployed and pitched live to guest judges with an architecture diagram and a business case.

Every approved build lands on your public portfolio, verified by the instructors.