Agentic RAG Workshop: From Fundamentals to Real-World Implementations
23 August 2025 | 09:30AM - 05:30PM
About the workshop
Agentic RAG adds a “brain” to the RAG pipeline – bringing reasoning, tool use, and adaptiveness – which translates to tangible business value in accuracy, flexibility, and user trust
This workshop is a deep dive into Agentic RAG (Retrieval-Augmented Generation) – an emerging approach that combines the power of LLM-based agents with retrieval techniques to build smarter AI applications. Over an 8-hour session (of course including breaks in between), participants will explore how to move beyond “vanilla” RAG pipelines and infuse them with agentic behavior for greater flexibility and intelligence. The workshop is hands-on, using Google Colab notebooks for each module so attendees can practice concepts live. We’ll leverage LangGraph (a LangChain-based framework for agent orchestration) along with the LangChain ecosystem (vector stores, tools, etc.) to design and implement these systems. The theme is highly relevant in today’s AI landscape – many enterprises are already moving from basic RAG to agent-driven systems to power next-generation assistants. In fact, new frameworks like LangGraph have emerged to meet this need, making now the perfect time to master Agentic RAG development. The workshop will also cover practical tips for building enterprise-grade agentic RAG applications
Big Business Benefits of Agentic RAG
Agentic RAG empowers large-scale, enterprise-ready AI systems by combining retrieval-augmented generation with intelligent, decision-making agents. The result? Smarter, more reliable, and adaptable GenAI solutions.
- Higher Accuracy & Trust: Agents reason through queries, validate retrieved information, and reduce hallucinations – essential for business-critical use cases.
- Dynamic Multi-Source Retrieval: Unlike traditional RAG limited to one vector DB, agents can pull context from multiple sources—internal files, databases, APIs, or the web—dynamically.
- Autonomous Problem Solving: Agentic systems can break down complex queries, reformulate them, and perform multi-step retrieval and reasoning with minimal human intervention.
- Scalable & Adaptable: Agent orchestration supports modular workflows that scale across domains, datasets, and tools—making the solution extensible and future-proof.
💡 Think of Agentic RAG as adding a decision-making brain to your RAG pipeline—boosting precision, flexibility, and business value.
*Note: These are tentative details and are subject to change.
Instructor
Modules
Gain a solid grasp of the RAG architecture and its value in grounding large language model outputs with factual, retrievable knowledge—critical for reducing hallucinations in enterprise GenAI systems.
Learn practical methods to enhance retrieval quality, including hybrid search (semantic + keyword), metadata filtering, reranking, and multi-hop retrieval strategies, enabling more relevant and precise information access.
Develop the ability to embed decision-making LLM agents into RAG workflows. Understand how agents use memory, tools, and multi-step reasoning to orchestrate complex information retrieval and response generation.
Gain hands-on experience with LangGraph to construct modular, interpretable agent flows—complete with state transitions, loops, and conditional paths—using LangChain’s ecosystem as a foundation.
Explore reusable design patterns like retrieval routers, self-correcting agents, and tool-selecting agents. Learn to choose the right pattern based on task complexity, accuracy needs, and operational constraints.
Work through an end-to-end use case (e.g., querying large annual reports) to build a robust Agentic RAG application that includes source validation, tool use, and intelligent retrieval orchestration.
Develop a clear understanding of when agentic RAG provides strategic advantage over traditional pipelines. Learn how to balance the benefits of reasoning and adaptability with considerations like latency and complexity.
Take away field-tested strategies for deploying Agentic RAG in real-world settings—modularize workflows, structure agent reasoning, handle failures gracefully, use smart caching, validate outputs, test comprehensively, and ensure governance and observability from day one.
