< session />

Building Robust, Secure LLM and Agentic AI Workflows

If 2024 was the year of AI Chatbots & RAG, then 2025 is the year of AI agents. While you may interact with an AI agent in the same manner you interact with an AI chatbot, the differences between them are stark. AI agents can autonomously act to fulfill your requests.  You can even have multiple agents working in tandem. All they need is a task that you set them off with and they will go about completing that task.

There are multiple approaches and frameworks out there to help one get started with Agentic AI applications, but more often than not, this can get complex and expensive. Thus, in this demo lead session we will explore open-source agentic AI tooling like Langgraph, following a developer and workflow centric approach towards building AI Agents. We will also cover how one can enhance agent memory using vector databases.

The session will also addressing common security concerns when dealing with LLMs and how to overcome those issues especially when adopting agentic AI applications in production.

Key Takeaways

Participants will learn not only learn how to use open-source agentic AI tools like Langgraph, Controlflow which provide structured, developer-focused approach for defining agentic workflows and delegating work to LLMs while coupling them with vector databases.  But more importantly, how one can build applications in a secure manner.

Target Audience

This session is ideal for AI Builders and Engineers planning to build secure agentic AI applications. While at the same time, this session is equally applicable Software/Cloud Architects interested in simplifying agent deployment strategies and automating, scaling AI applications in cloud environments in a secure manner.