Grounded Answers: Build and Evaluate a RAG Workflow

Design a retrieval-augmented workflow and test whether its answers stay grounded in sources.

Looking for step-by-step tutorials for individual AI tools?

Course overview

Move from document retrieval to a reviewable question-answering workflow. Learners compare local PDF-based systems, examine a self-checking retrieval approach, and plan an evaluation that tests retrieval and generation separately. Original activities emphasize source traceability, privacy, failure analysis, and human review rather than treating a fluent answer as proof.

Map a retrieval-augmented answer into query, retrieved evidence, generated response, and review steps. Evaluate whether cited passages actually support each answer claim and identify retrieval gaps. Design a small, privacy-conscious test set and use failures to decide what to revise or escalate.

Familiarity with generative AI prompts and basic file or document handling is helpful. No programming is required for the planning activities. Use public or synthetic documents only; do not upload confidential or personal material to an unapproved service.

Learners with basic familiarity who are ready to build practical, independent skills

People who learn best through examples, guided lessons, and hands-on practice

Professionals, creators, and independent builders looking for a repeatable workflow

Lesson 1 is free

4 lessons · Intermediate · Full course.

Open-license course content · CC BY licensed · license verified

This course uses CC BY licensed material attributed to its content provider or uploader. Lesson playback is available only through authenticated access after publication and licensing checks pass.