eBPF tooling like Tetragon is excellent at seeing what a workload does. For sandboxing an agent, seeing is the wrong verb. Here is why the enforcement point has to sit in the syscall path itself.
July 5, 2026
Building agentic systems. Researching how they break.
I build AI-powered file ingestion systems at scale. I do research at William & Mary on agentic network protocols, and what happens to authorization when agents start delegating to each other.
Outside of that, I play rugby, spend a lot of time on guitar, and go back to Lisbon every chance I get.
I write about the work, the research, and travel.
eBPF tooling like Tetragon is excellent at seeing what a workload does. For sandboxing an agent, seeing is the wrong verb. Here is why the enforcement point has to sit in the syscall path itself.
July 5, 2026
I moved to Lisbon for a while and learned the language on the way. The language was not the point. The people were.
July 22, 2025
I spent a while assuming that being good at the work was the hard part of getting the work. The actual question people are asking is not whether you can build it.
November 6, 2024
Agents over the Network
In preparation · First author
Search-Based Evolutionary Data Pruning for Class-Level Code Summarization
ICSE 2026, JAWS Workshop · First author
Makes code-summarization models cheaper to train by finding the smallest useful training set.
Resource-Efficient and Effective Code Summarization
FORGE 2025 · Second author
Shows code summarization can be done accurately with far less compute.