Skip to main content
Advanced ~14 hours

RAG Strategy Doc for a Product

Author a strategic doc for adding retrieval-augmented generation to an existing product — what to index, eval criteria, rollout plan.

Notion / Google DocsDiagram tools for architecture

About this project

RAG is the most common production AI pattern. This project teaches the strategic discipline: source-of-truth definition, chunking strategies, eval set design, citation UX, and the trade-offs of self-hosted vs vendor (Pinecone vs pgvector). Pick a real product (yours or hypothetical) and ship a 5-7 page strategy doc.

Why build this in 2026?

RAG is the most-asked-about AI feature in 2026 enterprise sales. Strong RAG strategy docs differentiate senior AI PM candidates.

What you'll ship

  • Strategy doc (5-7 pages)
Architecture diagram
Eval criteria + sample eval set
Phased rollout plan

Sign up to see the full project brief

Full deliverables, success criteria, and AI Career Tutor support — free.

You'll unlock:Complete project brief, AI tutor that knows this project, and progress tracking when you start.

Skills you'll practice

large language modelsretrieval augmented generationproduct management