01Pantera
Pantera: a wildfire management platform — prevention, detection, response, impact.
It combines cameras with satellite feeds and fire risk modeling to catch wildfires early — and predicts where they're heading.
Some of that ground is the Pantanal and indigenous territories, where the nearest brigade can be hours away. The rest is pulp/paper, agriculture, and conservation — clients who measure us in hectares that didn't burn.
I own the architecture end to end — inference on the cameras themselves, the hybrid on-prem/cloud platform, the ML behind detection and risk. Pantera itself is built by engineers, ML specialists and environmental scientists, and most of what I know about fire, I learned from them.
02Approach
Three things I learned the hard way.
The model is the easy part. What breaks in the field is dust, lightning, heat, a lens nobody cleaned, 4G that drops for six hours. Ninety-nine percent of what's written about ML is about the model. Almost none of it is about what happens when inference runs on a pole in the middle of nowhere.
I don't judge a model on accuracy alone. The question is what it costs to miss a real fire, and what it costs to wake a brigade at 3 a.m. for nothing.
Research and operations are two different sports. I contribute to an academic fire simulator and I help run a system that, right now, is detecting a real fire somewhere.
03Elsewhere
The bar I hold Pantera to is the bar for anything I put out to run on its own, AI agents included.
Agents running our own operation. Eight of them cover sales, customer success, support and marketing at 1.5°C, orchestrated on Hermes, an open-source framework I deployed on our own servers. One of them alone has opened 400+ issues, about 25% closing without any real review, mine included.
ForeFire, since 2022. An open-source wildfire simulation engine in C++ built by CNRS at Université de Corse. Mostly plumbing: Dockerizing it, setting up CI/CD, and writing docs people can actually follow, to help other groups run ForeFire in their own projects.
04Now
Two directions I'm paying attention to.
Climate and public technology. Fire, deforestation, monitoring — systems that governments, NGOs and communities actually operate, rather than pilots that end with the press release.
Agentic systems outside of AI companies. The hard part isn't the model — it's putting it inside an operation where being wrong is expensive.
If you're building something in either direction, write to me — I'd like to hear about it.
Updated August 2026
05Off the clock
I run marathons (PR of 3:22), cycle, play sax in a carnival bloco, and spend as much time as I can with family and friends, traveling when it fits.