Pantera
The wildfire AI platform I lead end to end at 1.5°C — detection, risk, response, impact.
Read the full story →Antonio Leblanc — Rio de Janeiro
Intern to CTO in ten months.
Today I lead the AI platform protecting 40 million hectares against wildfires.
Policy, community engagement, and ethics matter just as much as the model — that's where I want to keep spending my energy.
- Pantera
- 190 cameras, 40M+ hectares, 95% detection accuracy, including the Pantanal. I lead computer vision detection models, satellite imagery, fire spread, risk analysis and architecture at 1.5°C — co-founder and CTO since 2020 — with the engineering, ML, and environmental science team that builds it with me.
- Agents
- Eight AI agents run sales, support, and marketing on Hermes, open-source, on our own servers.
- ForeFire
- Contributor since 2022 to CNRS's open-source wildfire simulator, maintainer since 2025, and co-author on its JOSS paper — reviewing and merging PRs, cutting releases, Dockerization, CI/CD, documentation.
- Now
- Open to a technical second opinion for early-stage climate or govtech teams, a hand with technical leadership beyond 1.5°C, or just to hear what you're building in wildfire, deforestation, or agentic systems.
What I build
ForeFire
The open-source fire-spread simulator I maintain outside the day job, built by CNRS.
Read the full story →Where I focus
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.