AI for IT and Security
Cribl AI Research Lab
Researching, benchmarking, and building AI for the realities of IT, security, and telemetry
Overview
Cribl AI Research Lab explores how AI can better understand and work with IT and security telemetry. Our researchers and engineers develop purpose-built models, evaluate leading AI systems against real-world workflows, and research new approaches to AI-powered investigation, data protection, and agentic systems to make AI more accurate, efficient, and useful for technical teams.
Our work doesn’t stop at experimentation. We turn what we learn into AI capabilities used across the Cribl platform while also contributing research and benchmarks that help move the broader industry forward.
Develop purpose-built AI models and capabilities designed for telemetry.
Put leading AI systems to the test on real IT and security problems.
Research new approaches to AI-powered investigation, protection, and agentic telemetry.
LLM Evaluation
Generic AI benchmarks tell you how models perform on standardized tests. We want to know how they perform when the stakes are real and the telemetry is messy. Cribl develops benchmarks designed around real-world IT and security workflows, evaluating how leading AI models investigate incidents, reason across telemetry, handle uncertainty, and balance performance with cost.
We evaluated multiple AI models on real-world incident scenarios to understand not just whether they reached the right answer, but how they got there.
SecIT-bench evaluates areas including:
Investigation accuracy
Root cause analysis
Reasoning and tool use
Handling of incomplete or ambiguous telemetry
Token consumption and cost
Latest content
Learn more about our latest research approaches and reports, custom model development, and AI capabilities we’re building at Cribl.
Research Lab Members
Meet the researchers and engineers leading the way
Ledion is our CTO and Co-Founder. That means he’s the top goat in our engineering org, making sure we’re constantly shipping, always innovating, and never taking ourselves too seriously. He’s been at the forefront of launching our multi-product suite and brings an unwavering commitment to solving customer problems with a first principles approach (he might ask “Why?” five times, but that’s just to better understand the crux of the matter). Ledion has the cred(ion) as he has led the development of several enterprise products, including the introduction of Search-Time Schema and the design of Hunk and SmartStore while he was the Advanced Development Architect at Splunk.
Nikhil Mungel leads AI Engineering at Cribl, where he builds LLM-powered systems for IT and Security data transformation and analysis. Before Cribl, he spent over a decade developing distributed systems across the observability and consumer social tech landscape. His current focus is applying AI to make complex infrastructure more intuitive and explainable.
Chinmay is a Principal Engineer AI at Cribl, where he designs and builds AI native observability systems. His work spans building agentic systems, purpose-built models, real time streaming systems at the intersection of IT and Security. Prior to Cribl, Chinmay led AI/ML efforts at Splunk.
Sasikanth Vadlamudi is a product leader with more than 20 years of experience building the observability, telemetry, and digital-operations platforms that keep large-scale software reliable. Currently a Staff Product Manager focused on search and AI-assisted investigation at Cribl, he has led products across enterprise observability pipelines (Mezmo), endpoint digital-experience monitoring at global scale (Palo Alto Networks / Prisma SASE), and full-stack observability and AIOps for Fortune 500 e-commerce. His work spans real-user monitoring, alert correlation and noise reduction, incident response, and telemetry cost optimization.
Angela Governale, PhD leads AI Products at Cribl, translating advances in AI into practical, trustworthy experiences for IT, security, and telemetry teams. She brings over a decade of AI research experience and a track record of leading teams from early experimentation to production-ready products.
Rahul Ramakrishna leads AI Systems at Cribl, building inference and evals infrastructure, agentic frameworks and MCP systems. His work focuses on the foundational systems that move applied AI research into production, from inference and evaluation to the frameworks behind agentic products.
Latest
Discover more
get started
See demos by use case, by yourself or with one of our team.
Get hands-on with a Sandbox or guided Cloud Trial.
Process up to 1TB/day, no license required.
