Production-Ready RAG: From Prototype to Production

Most Retrieval-Augmented Generation (RAG) workshops stop at getting a chatbot to answer questions.
This workshop starts there—and then goes much further.
Join us for a hands-on, code-first session where you'll build a RAG application in Python and learn what it actually takes to deploy and operate it in production. We'll cover the complete RAG lifecycle, from document ingestion to evaluation, while exploring the engineering challenges that separate demos from real-world systems.

What You'll Learn

• What RAG is and when to use it
• Document ingestion and chunking strategies
• Retrieval techniques and vector search
• Generation and prompt orchestration
• Evaluating RAG systems for accuracy and reliability
• Advanced RAG patterns used in modern AI applications
• Production readiness considerations including:
• Latency optimization
• Scaling strategies
• Monitoring and observability
• High availability
• Performance drift detection
• Cost management

Workshop Details

Light snack provided during the afternoon

Location: St. Thomas University, St Paul – exact room coming soon
Format: Hands-on coding workshop
Requirements

• Basic Python programming experience
• Bring your own laptop
• Be ready to write code and experiment with real-world RAG architecture

Attendance
Seats are intentionally limited to ensure a highly interactive experience.

Every participant will receive a certificate from Applied AI.

Whether you're building internal AI tools, customer-facing assistants, or enterprise knowledge systems, you'll leave with practical techniques and production-minded patterns that you can apply immediately.