Ramya Ganesh
CyberSecurity XDR and AI Leader
Dallas, Texas, United States
Actions
Ramya Ganesh is a CyberSecurity Leader at Cisco with over 2 decades of experience in cybersecurity, product engineering and quality. She currently leads quality engineering efforts for Cisco’s XDR platform, specializing in backend automation, threat detection, cloud security, and GenAI integration.
Passionate about bridging the gap between AI and cybersecurity, she builds agentic AI prototypes using tools like Langgraph, n8n, OpenAI, AWS SageMaker, and MCP, enabling intelligent workflows for real-world use cases such as automated security testing and calendar orchestration.
An active advocate for Women in Tech, she also serves as a Board Director for an NGO for individuals with Cognitive disabilities and has mentored hundreds of you and mid career level professionals transitioning into AI and CyberSecurity roles. She has spoken at reputed institutions like Confederation of Indian Industry, Indian Institute of Technology, Microsoft Fabric Tour
Whether she’s building innovative AI-powered tools, mentoring rising talent, or driving security automation, she’s always focused on creating solutions with impact and inclusion at the core.
Area of Expertise
Topics
From Logs to Defense: Building AI-Enhanced XDR Pipelines for Application-Level Threats
Modern applications generate massive volumes of logs across microservices, APIs, identity systems, and cloud platforms but most organizations still struggle to convert this raw telemetry into meaningful security detections. Traditional rule-based alerting often misses subtle behavioral anomalies, while noisy signals overwhelm analysts and leave critical threats undetected.
This talk demonstrates how to build an AI Agent-enhanced XDR pipeline that transforms application logs into actionable defense signals. We will explore how machine learning, behavioral analytics, and LLM-based reasoning can uncover API abuse, authentication anomalies and other attacks that rarely surface in conventional AppSec testing.
Multi-Agent AI in Action: Detecting Anomalies in Datadog Logs with LangGraph
In modern cloud environments, log volumes are exploding, and with them, the challenge of spotting anomalies that matter. Traditional alerting often leads to fatigue, while real threats get buried. In this session, I’ll demonstrate how I built a multi-agent workflow using LangGraph to automatically detect, analyze, and respond to anomalies in Datadog logs.
The solution uses AI agents working together:
One agent extracts and parses log events.
Another applies anomaly detection (Isolation Forest) to identify outliers.
A third agent contextualizes the anomalies, grouping them by error patterns and impacted remote IDs.
A final agent pushes insights into downstream workflows (alerts via Webex, ticket creation in Jira).
By orchestrating these specialized agents, the system transforms Datadog from a passive log collector into an active anomaly detection and response engine.
Attendees will leave with practical insights into:
How to design and orchestrate multi-agent systems with LangGraph
Applying ML-based anomaly detection on real-world logs
Integrating detection with collaboration and ticketing workflows
This session is designed to be hands-on, showing how to combine AI, automation, and observability to move from reactive monitoring to proactive resilience.
Audience Takeaways
Understand multi-agent orchestration with LangGraph
Learn how to apply anomaly detection techniques to logs
See how AI can automate noisy monitoring workflows
Get inspired to extend existing observability platforms with AI
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top