GenAI + Agents with Elasticsearch

​Join the Ahmedabad Elastic User Group for an evening of talks and discussions on building GenAI applications and AI agents with Elasticsearch.

We'll explore how Elasticsearch powers agentic workflows and GenAI applications — from semantic search and vector databases to real-time monitoring of agent behavior. Our speakers will walk through actual implementations, share patterns that work (and some that don't), and discuss what's possible when you combine retrieval, reasoning, and execution.

​What we'll cover:

• ​How Elasticsearch's vector search and hybrid retrieval enable agent memory and context

• ​Observability for AI agents: tracking decisions, debugging failures, and measuring performance

• ​Real-world implementation examples and patterns

• ​Open discussions on building reliable agentic systems

​What to expect:

• ​Technical talks from Elastic team members and community developers

• ​Real-world use cases and implementation stories

• ​Hands-on insights into building production-ready agentic systems

• ​Networking with other developers working on AI and search

• ​Food and refreshments, Q&A and open discussions throughout the session

​Who should join:

​Developers working with or curious about AI agents, LLMs, and RAG systems. Whether you're just starting or already building in production, you'll find something useful here.

​Speakers

• ​Grounding LLMs at Scale: Enterprise RAG and Agentic Memory via Elastic by Amit Parmar (Bank of America)

• ​Application Performance Monitoring with Elastic O11y by Jigar Shah (Principal Support Engineer @Elastic)

• ​Building A Multilingual Voice Agent with Elastic Agent Builder and Sarvam AI by Ashish Tiwari (Principal SA - Search Specialist @Elastic)

​You don’t need to be an expert in GenAI. If you’re learning and experimenting, you’ll find the discussions useful.

​Everyone’s welcome — come to learn, explore, and connect with the community.