I build AI agents that survive the real world.
I'm a Staff Developer Advocate at DigitalOcean. I build AI apps and agents, contribute to the open-source tools developers use to ship them, and write about what I learn.
The three projects I'd show an engineer first
Voice assistant for macOS
Nix lives in my Mac's menu bar. I say "Hey Nix", ask something, and it answers out loud. The thinking is done by whichever coding agent I'm signed in to (Claude Code, Codex or Antigravity), so it can read files, run commands and use my tools, within permissions I set. Speech recognition runs on the Mac with Whisper, five times faster than a hosted service (265ms against 1.3s), and the audio never leaves the machine.
Agent security
Watches every tool call an agent makes and checks it against eight rules based on the OWASP LLM Top 10, covering prompt injection, leaked secrets, data exfiltration, SSRF and dangerous shell commands. Any FastAPI or Express app connects with two lines of code.
Benchmark
I benchmarked four LangChain memory backends over a 50-turn conversation. Vector memory kept 82% recall at about a tenth of the cost of keeping the full history.
| Backend | Recall | Cost |
|---|---|---|
| Buffer | 90% | $4,303 |
| Qdrant (best value) | 82% | $418 |
| pgvector (best value) | 82% | $416 |
| Summary | 42% | $2,256 |
Start here. Each one is built on something I ran and measured.
I tested Jev, a model that answers typed questions with probabilities instead of text, as a safety check on my agents' shell commands. A few narrow questions per command give scores policy code can act on, cheaply enough to check every call.
I ran the same model three deployment ways on DigitalOcean and measured the real costs, latency, and gotchas to find exactly when self-hosting stops being cheaper than serverless.
What happens when an AI agent burns through your GitHub API rate limits and locks you out of your own repositories.
Skills are instruction carriers. Every skill description influences how the model reasons, and that creates a new attack surface.
Live apps and side projects, one line each
Talks, workshops and the occasional architecture review
I give talks and run hands-on workshops on AI agents and taking LLM apps to production. I also review agent architectures for a few teams.
I'm always up for a meetup, conference or workshop. The easiest way to reach out is below.
I'm always happy to talk about AI agents, developer tools, talks and workshops. Pick whichever channel suits you.
