Amit Kumar
Senior Platform and DevOps Engineer
Chandigarh, India
Actions
I am a Senior Platform and DevOps Engineer with 5+ years of experience, specializing in Kubernetes, cloud-native architectures, and AI/ML infrastructure. I have implemented scalable, automated, and resilient systems using Terraform, ArgoCD, Crossplane, and Kubernetes. My expertise includes GitOps, CI/CD, AI/ML pipelines, and security best practices. Passionate about automation and cloud-native solutions, I focus on disaster recovery and AI/ML platform engineering.
Links
Area of Expertise
Topics
Blast Radius: How We Built a Scanner to Quantify AI Agent Risk
Most teams shipping AI agents spend a lot of time making them capable and very little time asking what happens if they are manipulated. A LangChain agent with a delete tool and no input constraints, a CrewAI agent that can delegate to sub-agents without limits, an MCP server that can read your database and post to Slack are not hypothetical risks. They are the default configurations most developers ship without realising.
We built Kaaval, to be an open source AI agent security scanner that takes an agent definition or MCP server config and tells you exactly what it can do, what it should not be able to do, and what the damage looks like if something goes wrong. We call that number the Blast Radius, a score from 0 to 10 that reflects the real-world impact of a compromised agent.
Kaaval works in three detection layers. The first layer runs deterministic rule checks mapped to the OWASP LLM Top 10, covering things like missing system prompt boundaries, tools with delete or execute access and no scope constraints, and sensitive credentials exposed in agent context. The second layer runs vector similarity search against a corpus of known attack patterns from MITRE ATLAS and Garak, so every finding is grounded in a documented threat rather than an LLM guess. The third layer runs an optional deep analysis that catches semantic risks the rules miss, such as two tools that look safe individually but together create a data exfiltration path.
Kaaval has two modules built and presented together in this session. The first module audits agent definitions across LangChain, CrewAI, and AutoGen. The second module audits MCP server configurations for trust boundary violations, supply chain risks, and dangerous capability combinations across servers. Both modules produce findings with severity scores, remediation guidance, and a combined blast radius when run together.
In the demo, we scan a realistic agent configuration that resembles what most teams are shipping today, an agent with several tools, a minimal system prompt, and no explicit permission boundaries. We run Kaaval against it and walk through the findings layer by layer.
Kaaval runs as a CLI tool, and is designed to integrate into deployment pipelines with a single flag that fails the build on critical findings.
OpsAI: Incident Investigation, Reimagined with AI Agents
Every incident follows the same pattern. Alerts fire, you open four terminals, correlate logs with recent deployments, check cluster state, dig through git history, and slowly piece together what went wrong. The tools are good. The process is exhausting.
OpsAI is a multi-agent AI system we built to tackle this. It investigates incidents by pulling evidence from logs, Kubernetes state, and git repositories, then produces answers where every claim is tied to a real source. No hallucinated pod names. No invented timelines. Every assertion points back to a log line, a commit, or a cluster object.
This talk covers what we learned building it in production: why evidence citation has to be an architectural constraint and not an afterthought, how we structured git, Loki, and Kubernetes snapshots as complementary evidence layers, how multi-agent coordination works when sub-questions need different specialists, and why running AI inference workloads on Kubernetes is a different class of operational problem than most teams expect.
The goal is to share a concrete architecture pattern that others can apply, and be honest about where it breaks down.
CNCG Chandigarh Meetup User group Sessionize Event
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