GenAI in Production (RAG + Agents)
We’re bringing together the Elastic and AWS Developer Communities in Mumbai for an in-person meetup focused on building GenAI systems in production.
The discussion will centre on Retrieval-Augmented Generation (RAG) and AI agents, and on how developers are connecting LLMs to search and real-world data. Rather than demos, the sessions will focus on practical implementation, architecture choices, and lessons from building real systems.
What to expect
Technical talks on RAG pipelines and AI agents
Real examples of connecting LLMs with search and data
Open Q&A and developer discussions
Time to meet other engineers and continue conversations over food
What you’ll learn
Some of the topics we plan to cover include:
How RAG architectures are designed in production systems
Ways to combine search, embeddings, and LLMs
Practical approaches for building AI agents
Managing data retrieval, context, and relevance
Lessons from real implementations and developer workflows
Venue and speakers
Beyond Vector Databases: Building Agentic RAG Systems with Elasticsearch by Dishant Gandhi
Abstracting Cross-Cutting Concerns: AuthN/Z and Observability at the Edge by Susmit V
Scaling AI Context: Implementing Elastic MCP on Bedrock’s Agent Runtime by Someshwaran M
Who should attend
This meetup is designed for developers and engineers who are:
Building or experimenting with GenAI applications
Working with LLMs, RAG pipelines, or vector search
Interested in search-driven AI systems
Exploring AI agents and automation workflows
Curious about how others are building AI systems in production
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.