Production RAG: From Naive Retrieval to Agentic Search

Build retrieval-augmented generation systems that actually work — hybrid search, reranking, evaluation, and agentic retrieval loops

Course Format and Delivery

Delivery Method: LiveOnline
Schedule: Full day

All sessions are delivered live by an expert instructor in a fully interactive online environment.

*20% off for group bookings when booking 3 or more attendees from the same organization on the same course dates in the same transaction.

About this course

Naive RAG fails approximately 40% of the time, with 80% of failures traceable to the ingestion pipeline. The market is saturated for 'intro to RAG' but wide open for production-grade patterns.

This full-day workshop moves participants beyond basic vector search into production-grade RAG architectures: hybrid BM25 + vector search, cross-encoder reranking (Cohere Rerank, FlashRank, ColBERT), chunking strategies that preserve context, agentic retrieval loops that self-correct, and systematic evaluation with RAGAS.

Participants also learn to defend their RAG pipeline against the documented vector DB poisoning attack where 1% injected vectors contaminate 99.85% of query results. The day progresses from a failing naive implementation to a reliable, evaluated, hardened agentic system.

This course is great for

For developers and ML engineers who have built basic RAG prototypes. Comfort with Python and conceptual understanding of embeddings and vector databases required.

Topics Covered

Document processing and chunking strategies,
Embedding model selection,
Hybrid search architectures,
Reranking pipelines,
Query transformation and expansion,
Agentic retrieval with self-reflection,
RAG security (poisoning detection, source allowlists),
Evaluation-driven development with RAGAS,
and cost optimization. Approximately 35% lecture, 65% hands-on labs.

Brent Laster

Facilitator

Brent Laster is a global trainer, author, speaker, and founder/president of Tech Skills Transformations LLC. He helps enterprise teams adopt modern software practices in AI engineering, AI-assisted development, DevOps, automation, and secure software delivery. He is the author of Learning GitHub Copilot, Learning GitHub Actions, Professional Git, and Jenkins 2: Up and Running, as well as multiple online and live training programs for companies such as O'Reilly. In addition to AI expertise, Brent brings more than 25 years of experience in software development, management and technical leadership, DevOps, release engineering, and open-source technologies. He regularly presents and conducts workshops at industry conferences and for private clients.