Build real AI products with LLM APIs: prompt engineering, embeddings, vector databases, RAG, tool calling and AI agents.
The most in-demand skill of 2026. Learn to build reliable applications on top of large language models.
You build chatbots over your own documents, agents that call tools and APIs, and you learn to evaluate and secure them.
Week 1
How LLMs work: tokens, context windows, model choice and cost
Week 2
Prompt engineering, structured output (JSON), function / tool calling
Week 3
Embeddings and vector databases (pgvector, Chroma, Pinecone)
Week 4
Retrieval-Augmented Generation (RAG): chunking, retrieval, re-ranking
Week 5
AI agents and workflows, Model Context Protocol (MCP), LangChain / LlamaIndex
Week 6
Evaluation, guardrails, prompt-injection safety and monitoring
Week 7
Building the UI (Next.js / Streamlit) and streaming responses
Week 8
Capstone deployment and demo day
Upcoming batches
The next batch is being scheduled. Apply now and we will add you to it and share the timing.
You will be asked to sign in or create a free student account, so you can track your application, offer letter and daily tasks.