Security leader working where security operations meets AI. I lead security engineering and operations, and I help companies adopt AI without taking on risk they can't see.
A 24/7 SOC run through an MDR partnership, made fast with detection engineering, SOAR automation, and AI agents in triage, not extra headcount.
15 years in IT and cybersecurity, 7 of them leading security teams at public and private companies.
Making it safe for a company to put agents into production.
A 24/7 SOC that is fast because it is engineered, not staffed up.
Taking passwords and standing access out of the attack chain.
I rebuilt that SOC around agentic AI. Production agents triage phishing, endpoint, and identity alerts, and an analyst reviews every incident with AI doing the enrichment and investigation legwork.
I sit on our AI Center of Excellence and architecture committee and lead safe AI adoption: use-case risk review, AI/MCP gateways, agent runtime guardrails, non-human identity controls, and OpenTelemetry tracing so the SOC can detect and investigate agent misuse.
Side projects where I test my ideas about agent security on real tooling.
An MCP server covering the full HackerOne REST API (Customer and Hacker, 174 tools), over stdio or hosted Streamable HTTP, wrapped in a gated bug bounty operations pipeline where nothing leaves the machine without a recorded human approval.
Read the write-upA Python orchestrator that lets a model drive a browser through provisioning and deprovisioning in applications with no API, with Teams approval cards before every write and a SHA-256 hashed screenshot audit trail.
Read the write-upA static Astro site where every page has a Markdown twin, plus llms.txt, JSON Resume, content negotiation, and a read-only MCP endpoint — built so an AI agent can read it as easily as a person.
Read the write-upMore and more, the first reader of a resume is an AI agent. So I built this site to be read by both people and agents — Markdown twins, llms.txt, JSON Resume, content negotiation, and a small read-only MCP server.
Most AI risk conversations start with the model. I think they should start with the credentials. An agent can only do what its identity allows — so govern the identity.
If you can't replay what an agent saw, decided, and did, you can't investigate it. OpenTelemetry already gives us the format. The SOC needs to treat it like EDR data.
Every identity program has a list of disconnected applications that someone provisions by hand. I built a proof of concept where a model drives the browser instead — with a human approving every write and a hashed screenshot behind every step.
I built an MCP server for HackerOne and a bug bounty pipeline around it. The interesting part isn't the 174 tools. It's the three places where the agent has to stop and wait for me.
Security leadership, AI risk, or agentic SOC work. I'm happy to compare notes.
Loading…