Vikramaditya Narayan
AI agents are beginning to write larger parts of applications, from individual features to complete services. But if agents can build software, they also need a reliable way to threat model what they build.
Precogly is an open-source (Apache 2.0) OWASP project for repeatable, human-reviewable threat modeling in the AI-coding era. It uses structured, community-curated library packs that connect components, threats, and countermeasures to sources such as CWE, CAPEC, and compliance frameworks.
This gives AI agents guardrails. Instead of inventing threat models freely, they work off installed libraries, producing outputs that are easier to review, reproduce, and audit.
In this demo, attendees will see Precogly’s DFD editor, library pack ecosystem, threat generation workflow, completion status dashboard, pack cross-checks for detecting untraced AI-generated items, and the OpenAPI REST API that agents can build on top of.
Vikramaditya Narayan
Creator of the Precogly Open-Source Threat Modeling Platform
Vikramaditya Narayan is the creator of OWASP Precogly, an open-source, enterprise-grade threat modeling platform designed for repeatable, AI-agent-ready threat modeling. Previously, he designed the prototype for a YC-funded AI governance platform. Vikramaditya leads the Bangalore chapter of Threat Modeling Connect and has spoken at ThreatModCon DC on emergent risks in multi-agentic systems and at OWASP on using AI in threat modeling. He holds an MS from Carnegie Mellon and is a Certified Threat Modeling Professional.