The projects nobody had a product for kept landing on my desk.
Fourteen years at PwC across cybersecurity, digital forensics, risk, regulatory and financial services. Mostly deals and regulatory compliance, where the answer did not exist yet and somebody was waiting to audit the one you built.
I build enterprise systems for sensitive, regulated data.
Work out what is permissible, which means sitting with government regulators and legal teams. Work out what is technically possible. Then build it deterministically and repeatably, inside the window of a deal or a regulatory deadline, because it will face counterparty scrutiny and government audit.
This started with building skunk-works engineering teams from internal and external talent, to repeatedly solve problems that were too complex for existing tools to handle.
Scale was the other half. Hundreds of millions of files, spread across countries and the people who held them, inside the window before a deal closed or a deadline landed. Cloud was the only way to reach that, so we engineered the systems ourselves: architecture, data model, pipelines. Where the platforms could not carry what we put through them, I worked directly with Google and AWS engineers to change how their services behaved.
The U.S. Department of the Treasury asked for a live demonstration of one of them, a data risk mitigation program under a CFIUS National Security Agreement (NSA). Their feedback was that they had not seen technology layered together that way to address it so comprehensively.
I founded Octosight to build the tool my teams and clients always needed.I created Runtime to build it with agents.
Octosight protects large volumes of sensitive data with AI. I co-founded it in 2023 with one other person, and my former team left their jobs to come and build it. What changed was moving the work onto coding agents to go faster. By late 2025, with Claude Code and Codex, the speed was real and the results were not.
I started building the Runtime components so that my teams could go faster with agentic engineering. First the observer, to put the browser’s devtools and network traffic, the application logs and the cloud logs on one timeline, correlated by timestamp. It carries a graph and a branch view, for where code gets created and where it gets left.
Then the exchange, so sessions could talk to each other: across machines, across laptops, and across coding agents. They are coming together into a harness now.
I have learned a lot from attending hackathons and chatting with others in the agentic engineering community, and I am looking forward to releasing the Runtime Harness method as open source.
MeerkatOps is where I put the tools I build for my teams to work better with agents, whether that is running a startup or building for an enterprise. Three of them: building the product, the security operations around it, and the compliance evidence underneath.
I volunteer as a firefighter, and I do woodworking and mill lumber with a chainsaw with my kids. The rest of my life happens on a screen. This is where they learn the value of building things with their hands and being a useful human.