Agentic AI Observability and Control w/ TraceCtrl, anyone?
In this workshop, attendees will learn about the importance of having visibility and control over their agentic AI applications. Participants will start with a pre-built agentic AI application (using OpenClaw or AWS Strands) and learn to use TraceCtrl to instrument it, trace agent interactions, and surface security vulnerabilities. By the end, they'll have a full topology map of the app's agent communication and a concrete attack surface analysis with actionable hardening recommendations.
🧑💻 What You’ll Work On
Intro to Agentic AI & TraceCtrl (30 min): Overview of agentic AI and how TraceCtrl provides observability into agent behaviour, followed by a live product demo.
TraceCtrl Setup & OpenClaw Integration (60 min): Install and configure TraceCtrl to run alongside your agent, integrate it with your OpenClaw setup, and run a scan to generate an inventory of configured components, a static topology map, and a security assessment of your OpenClaw instance.
Remediation & Security Scenarios (30 min): Walk through how to fix identified issues, including auto-remediation, followed by a live demonstration of security scenarios on OpenClaw.
⚠️ Prerequisite
Laptop
Basic developer knowledge (comfortable with the terminal, Git, and running an app on localhost).
Environment Requirements:
Python 3.10 or higher
Node.js 20 or higher
Docker installed (Docker Compose is highly recommended)
Agent Setup:
A working installation of OpenClaw or a Strands agent with your API keys already configured.
You will get the best results and most valuable insights during the live topology mapping if you bring a sophisticated, well-configured agent or OpenClaw instance to the session.
*We'll share a setup guide a few days before the workshop so participants can have their environment ready before the session starts.
🗣️ Facilitated by The Cloudsine Team
Matthias is a recognised leader and tech entrepreneur in GenAI Security, serving as the Founder & CEO of CloudsineAI, a pioneering startup dedicated to protecting organisations from emerging generative AI threats. With over two decades of cybersecurity expertise, Matthias has built scalable security systems for government, healthcare, and financial institutions.
Rohit is a Software Engineer at CloudsineAI, where he leads the development of TraceCtrl, a security observability tool for agentic AI. A graduate from SUTD, Rohit has a knack for exploring — whether that's 14 countries and counting or tinkering with the latest AI tools and agents to solve everyday problems.
Sanat is a Technical Product Manager at CloudsineAI, focused on cybersecurity and AI. Being an alumnus of SUTD, design thinking and problem-solving are at the core of his work. In his free time, he dabbles in music, sports, and travel.
More About the Series
Fri-DIYs is Lorong AI's hands-on technical workshop series focused on learning by building. Sessions are structured around hands-on exercises and guided projects, giving participants time to experiment with AI technologies in a focused, collaborative environment.
Get involved: Learn more about Lorong AI | Speaker Sign-up | WhatsApp Community | LinkedIn | X