This session will unpack the architectural patterns and pitfalls of implementing Retrieval-Augmented Generation (RAG) within Agentforce and will be held at Suite 200, 4388 Rue Saint-Denis, Montréal, H2J 2L1

Through real-world examples, we’ll

• Compare approaches like using the Agentforce Data Library vs. custom retrievers,

• Explore prompt template design, and

• Discuss metadata enrichment via SObjects and ContentDocument blobs.

This session is perfect for architects and developers looking to embed AI-driven document intelligence into Salesforce with scalability and maintainability in mind.

Key Takeaways To Expect At The End Of This Session:

• Design smarter embeddings — why custom chunking strategies can make or break accuracy when handling complex technical documents.

• Optimize retrieval performance — how hybrid search (keyword + semantic) outperforms pure semantic search when paired with structured metadata.

• Craft effective prompts — understand how prompt design and chunk size consistency impact the quality of your RAG responses.

• Establish robust feedback loops — learn how to evaluate, tune, and prevent RAG quality from degrading over time.

• Balance tooling and customization — when to rely on Agentforce Data Library accelerators, and when a custom prompt template delivers better results.

Why Attend?
If you’ve been curious about how RAG actually plays out in Salesforce—beyond the theory—this talk will show what worked, what didn’t, and how to make RAG architectures scale inside your org.