AIBuild with LLMs and agents, from prompts to production apps.

Gen AI Bootcamp

Build and ship LLM products: prompting, retrieval, agents, evals, production.

Python and Git; no machine-learning background needed.

1. Week 1Prompt LabA prompt notebook that compares three prompts on the same inputs and records the outputs side by side
2. Weeks 1–2LLM foundationsA deployed assistant with structured output and a test suite
3. Week 3Embedding ExplorerA small script that embeds a document set and returns the closest passages for a question

Agentic AI Bootcamp

Multi-agent systems that plan, coordinate and run in production.

You have built at least one LLM application; Python and Git.

1. Week 1Tool Calling LabA Python script where Claude calls two typed tools and handles their errors
2. Weeks 1–2One agent, done properlyA single agent that completes a bounded task reliably, deployed with traces
3. Week 3Handoff PrototypeA planner and worker pair that pass a task through a shared JSON state file

RAG and Search Engineering Bootcamp

Retrieval that actually finds the right thing, measured, at scale.

Python and SQL; some exposure to an LLM API.

1. Week 1Keyword IndexA BM25 index over a small corpus with a search script that returns ranked passages
2. Weeks 1–2Search fundamentalsA hybrid search service over a real corpus, deployed
3. Week 3Chunking ComparisonA notebook that splits one document set three ways and compares retrieval hits

Voice AI Agents Bootcamp

Phone and in-app voice agents that hold a conversation and complete a task.

You have built an LLM application; Python and webhooks.

1. Week 1Transcription ScriptA Python script that transcribes recorded audio and prints the text with timestamps
2. Weeks 1–2Speech in and outA voice loop you can talk to in the browser, deployed
3. Week 3Call WebhookA FastAPI webhook that answers an incoming call and plays a greeting