AI Agents Security and Sandboxing Meetup

🌟 Join Us for the AI Agents Security and Sandboxing Meetup 🌟

As AI agents move from demos to production, a hard question takes center stage: how do we run autonomous agents without giving them the keys to the kingdom?

This community meetup brings together ASAPP, Nokia, Docker Benglauru, Collabnix community and AI practitioners, security engineers, and platform builders to tackle the emerging discipline of AI agent security. We will explore how to sandbox, govern, and ship AI agents safely — from microVM isolation and policy enforcement to MCP gateways, runtime observability, and real-world horror stories from production. Whether you are building multi-agent systems, deploying LLMs at the edge, or hardening your AI infrastructure, this meetup is designed to give you practical patterns, war stories, and the chance to meet the people solving these problems alongside you.

Target Audience

This meetup is crafted for:

• AI/ML Engineers & Researchers — Practitioners building and deploying autonomous agents and multi-agent systems
• Security Engineers — Professionals responsible for securing AI workloads, agent runtimes, and LLM-driven infrastructure
• DevOps, MLOps & Platform Engineers — Teams operationalizing AI agents in production environments
• Generative AI Developers — Developers shipping agentic applications (coding agents, cybersecurity triagers, autonomous workflows)
• CTOs, Architects & Tech Leads — Leaders shaping AI governance, runtime trust, and agent infrastructure strategy

Participants should have basic familiarity with containerized environments, AI/LLM concepts, and production deployment workflows.

Why Should Someone Attend it?

• Learn How to Sandbox AI Agents — Understand modern isolation techniques including microVMs, ephemeral environments, and container-based sandboxing. Explore how to contain blast radius when agents misbehave.
• Master Agent Governance & Policy — Learn how MCP gateways, policy enforcement points, and audit trails create a trust layer for autonomous systems. See real architectures used in production.
• Hear Real-World Horror Stories — From agents reading SSH keys to runaway loops burning compute budgets — learn from postmortems shared by practitioners who have shipped agents to production.
• Network with the Community — Connect with AI builders, security researchers, and platform engineers solving the same problems. Bengaluru's emerging AI agent security community gathers here.

Prerequisites

• Basic familiarity with containers, AI/LLM concepts, and production deployment

Agenda:

9:00 AM - 10:00 AM - Welcome and Registration 10:00 AM - 10:30 AM - AI-DLC using BMAD by Bhagavatula Chalapathi, Nokia 10:30 AM - 11:00 AM - Speaker #1, ASAPP 11:00 AM - 11:30 AM - Securing the AI Coding Agents by Raveendiran RR, Docker 11:30 AM - 12:00 PM - AI Modelling and Optimisation, Alagu Prakalya, ASAPP 12:00 PM - 12:30 PM - Don't Give Agents the Keys to the Kingdom: Threat Modeling Multi-Agent Systems with MAESTRO (framework ) by Shubhendu Shubham, Merative 12:30 PM - 1:00 PM - Engineering Workflows with Cursor AI: Secure Adoption of AI Coding Agents in Enterprise Environments by Harsimranjit Singh Kler, Nokia 1:00 PM - 2:00 PM - Lunch 2:00 PM - 2:30 PM - Agentic AI and Security, Koti Vellanki 2:30 PM - 3:00 PM - Safe and Secure AI Agents in Production, Arumugam Sakthiverlmari, Cognizant 3:00 PM - 3:30 PM - Networking and Wrap-Up

Register Now! https://forms.gle/9S8nZTCbgQ5sUaYb8 Interested to speak? Submit your talk here: https://forms.gle/7iDNAdbZJtf85ris5