The AI Trinity

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.

Prerequisite: 

• Basic Python skills 
• Introductory level exposure to LLMs and RAG
• Familiarity with LangChain or similar frameworks 
• Exposure to vector databases and embeddings

*Note: These are tentative details and are subject to change.

This workshop introduces AgentOps, a subcategory of GenAIOps, which focuses on the operationalization of AI agents. It dives into how we can create, manage, and scale generative AI agents effectively within production environments. You’ll learn the essential principles of AgentOps, from external tool integration and memory management to task orchestration, multi-agent systems, and Agentic RAG. By the end of the workshop, participants will have the skills to build and deploy intelligent agents that can automate complex tasks, handle multi-step processes, and operate within enterprise environments.

Prerequisites:

• Basic understanding of AI/ML and LLMs (Large Language Models)
• Familiarity with Python programming and using frameworks like LangChain or LangGraph
• Experience with APIs and web-based tool integrations (e.g., basic knowledge of calling external APIs)
• Familiarity with cloud-based environments (e.g., AWS, Google Cloud) is a plus, but not required

*Note: These are tentative details and are subject to change.

In this hands-on workshop, participants will explore the cutting-edge world of Large Language Models (LLMs), Reinforcement Learning (RL), and building autonomous AI agents. Combining theory with hands-on coding examples, this session is designed to bridge the gap between theoretical concepts and real-world applications. By the end of the workshop, participants will have a solid understanding of how to build, train, and fine-tune an LLM for specific applications as well as how to increase their utility with RAG and AI Agents.

Prerequisites: Basic Python programming skills

*Note: These are tentative details and are subject to change.

This full-day workshop equips business and enterprise leaders with the essential knowledge to confidently navigate the AI revolution.

Through simple explanations, real-world examples, and live demos, you'll demystify AI and ML concepts, uncover actionable GenAI use cases, and master the art of prompting for better business outcomes.

From foundational techniques to strategic adoption roadmaps, this session will empower you to spot opportunities, manage risks, and build a future-ready GenAI strategy — without needing a technical background.

Prerequisites: No technical expertise is necessary, but understanding basic business processes is important across functions.

*Note: These are tentative details and are subject to change.

Learn how to train LLMs with HuggingFace and use RAG with Qdrant 

Deploy and create automated pipelines for LLMs with SageMaker

Build multi-agent workflows with LangGraph

How to test, monitor, and evaluate LLMs with LangSmith 

Through practical labs, participants will build production-ready LLM systems incorporating best practices for scalability and reliability.

Prerequisite: Basic Python programming skills, basic understanding of machine learning concepts, and familiarity with AWS services.

*Note: These are tentative details and are subject to change.

In this hands-on technical workshop, we’ll explore multi-agent orchestration using CrewAI, diving into how autonomous agents can collaborate to solve complex problems. You’ll learn how to define, configure, and coordinate agents using CrewAI’s core components, all in Python.

We’ll walk through the main classes of problems this approach is suited for and guide you step by step through building real-world workflows. Topics include agent creation, orchestration strategies, tool integration (including custom tools), and LLM-agnostic setups. We’ll also look at how to connect CrewAI with external libraries such as Streamlit to bring your solutions to life.

What You’ll Learn:

• How to define agents and tasks in CrewAI
• Coordinating agents through orchestration flows
• Using and creating tools and custom tools
• Working with different LLMs (LLM-agnostic setups)
• Integrating with libraries like Streamlit
• Best practices for building maintainable and scalable agent systems

Prerequisites:

• Basic Python knowledge (e.g., installing packages, creating environments, defining classes)
• Please come prepared with:
• An OpenAI API key (or another LLM provider)
• A Serper.dev API key

*Note: These are tentative details and are subject to change.

In this hands-on technical workshop, you'll master the fundamentals of building production-grade AI agent applications with AG2 (formerly AutoGen), a lending  open-source AI Agent framework that is adopted by millions of users and downloaded over 700k times per month. 

You'll explore essential AI agent design patterns and discover how to customize agents for specific domains using reference implementations from the AG2 team. You'll also learn production deployment strategies using FastAgency and build complete agent solutions for real business scenarios.

Through guided exercises, you'll develop AI agent systems that can tackle real-world applications like customer support, marketing research, and data analysis. By the end of the day, you'll have the knowledge to build specialized, scalable agent applications that deliver reliable results in production environments.

What You’ll Learn

• Fundamentals of AI Agents: Understand the core concepts and architecture of agent-based AI systems
• AG2/AutoGen Framework: Master the key components and capabilities of AG2 framework
• AI Agentic Design Patterns:  Key AI Agent design patterns
• Customized Agent Creation: Build specialized agents for specific tasks and domains. Learn from reference agents built by the AG2 team.
• Integration Strategies: Connect your agent systems with external tools and APIs, and MCPs
• Development: Build specialized agents for specific tasks and domains
• Practical Applications: Apply agent technology to real-world use cases
• Best Practices: Optimize agent performance and reliability in production environments

 Prerequisites

• Basic Python programming knowledge
• Familiarity with LLMs 
• GitHub account for accessing workshop materials
• Local development environment with Python 3.9+

Technical Requirements

• Python 3.9 or higher
• Git
• API keys for language models (OpenAI, Anthropic, etc.)
• Code editor of choice
• Virtual environment management (venv, conda, etc.)

New to the world of Agentic AI and want to quickly get proficient in the key aspects of learning, building, deploying and monitoring Agentic AI Systems? This is the workshop for you! In this workshop you will get a comprehensive coverage of the breadth as well as deep dive into the depth of the vast world of Agentic AI Systems. Over the course of six modules, you will spend the entire day focusing on the following key areas:

• Learn essential concepts of Generative AI, Agentic AI and Agentic RAG Systems
• Deep dive into industry standard design patterns for architecting Agentic AI Systems - Tool-Use, Reflection, Planning, Multi-Agent
• Leverage Industry-Standard frameworks including LangChain, LangGraph and CrewAI to build simple and advanced Agentic AI & Agentic RAG Systems
• Learn basics of how to deploy Agentic AI Systems as APIs as well as debug and monitor them

While we want to keep the discussions as framework and tool-agnostic as possible, since 90% of the workshop will be hands-on focused; we will be using LangChain and LangGraph (currently the leading framework used in the industry)  for most of the hands-on demos for building Agents and also a bit of CrewAI. While the focus of the workshop is more on building Agentic AI Systems we will also showcase how you can build a basic web service or API on top of an Agent using FastAPI and deploy and monitor it using frameworks like LangFuse or Arize AI Phoenix.

Important Note: You may need to register for some platforms like Tavily, WeatherAPI etc for the workshop (no billing needed), we will send the instructions ahead of time. That will be essential for running the hands-on code demos live along with the instructor in the session.

Additional Points

• Prerequisites: Solid understanding of Python, NLP and Generative AI will be useful
• Content Provided: Slides, complete code notebooks, datasets
• Infrastructure: Most of the hands-on demos we will do on Google Colab for the deployment and monitoring section we will provide the cloud infrastructure (either Colab or Runpod.io).

*Note: These are tentative details and are subject to change.

In this workshop, we’ll build a fully functional multimodal Telegram agent, putting into practice a wide range of concepts from the world of Agentic AI. This isn’t just another PoC — it's designed for those who are ready to level up and build complex, production-ready agentic applications. 

Throughout the session, you’ll learn how to build a Telegram agent you can chat with directly from your phone, master the creation and management of workflows with LangGraph, and set up a long-term memory system using Qdrant as a vector database. We’ll also leverage the fast LLMs served by Groq to power the agent’s responses, implement Speech-to-Text capabilities with Whisper, and integrate Text-to-Speech using ElevenLabs. Beyond language, you’ll learn to generate high-quality images using diffusion models, and process visual inputs with Vision-Language Models such as Llama 3.2 Vision. 

Finally, we’ll bring it all together by connecting the complete agentic application directly to Telegram, enabling a rich, multimodal user experience. Throughout the day, you will focus on the following key areas:

• Understand the full architecture and stack for building production-grade multimodal agents.
• Learn to build and debug agent workflows using LangGraph and LangGraph Studio.
• Implement short-term (SQLite) and long-term memory (Qdrant) systems for your agent.
• Enable speech interactions using Whisper (STT) and ElevenLabs (TTS).
• Integrate vision-language understanding with Llama 3.2 Vision and generate images via diffusion models.
• Connect your agent to Telegram for real-time, mobile-accessible interactions.

In this workshop, participants will work hands-on with a cutting-edge stack of tools and technologies tailored for building multimodal, production-ready agentic applications. LangGraph serves as the backbone for orchestrating agent workflows, with LangGraph Studio enabling easy debugging and visualization. SQLite powers short-term memory within the agent, while Qdrant, a high-performance vector database, handles long-term memory for contextual awareness. Fast and efficient responses are delivered using Groq LLMs, complemented by natural voice interactions through Whisper for speech-to-text and ElevenLabs for text-to-speech synthesis. For visual intelligence, Llama 3.2 Vision interprets image inputs, and diffusion models are used to generate high-quality visuals. Finally, the complete system is integrated with the Telegram Bot API, allowing users to interact with the agent in real time via chat, voice, or image directly from their mobile devices.

Prerequisites:

• Basic Python programming skills
• Familiarity with LangChain or LangGraph
• Basic understanding of multimodal AI concepts

*Note: These are tentative details and are subject to change.

This workshop is designed to provide a comprehensive overview of LLMs, right from foundational NLP concepts to the latest in this domain. This workshop is aimed at working professionals but covers the required details to help beginners get started. You will gain valuable insights and hands-on experience to learn & adapt concepts to your professional lives.

Key Takeaways:

• Understand the fundamentals of Language Models and Transformer architectures.
• Gain hands-on experience with LLMs and related concepts such as PEFT, Prompt Engineering, RAGs,  LLM frameworks like DSPY.
• Explore advanced topics such as Reinforcement Learning from Human Feedback (RLHF) and tool-calling through MCP

Prerequisites:

• Basics/hands-on experience of working with python
• Basic understanding of Deep Neural Networks (pytorch preferably)
• Access to google-colab or similar python environment with GPU access

*Note: These are tentative details and are subject to change.