48 AI agents scan NASA lidar data and spot a Maya complex in 72h

A software developer traveling in Peru drew inspiration from the story of Machu Picchu's discovery and decided to test the same approach with AI agents. After a brief brainstorm with several agents, he turned to lidar data, which reveals structures hidden beneath the forest canopy. According to the post, the Maya region is far better covered by public lidar than Peru, so the developer asked the agents to analyze the data overnight.

By morning, the agents had converted lidar strips covering roughly 1,200 square kilometers of jungle into images and gone through them one by one. As described in the article, 48 agents acted like patient archaeologists, looking for pyramids, platforms and plazas while filtering out natural hills, sinkholes and roads. No special model or classifier was involved; the agents simply looked at the pictures and followed a detailed guide.

The agents flagged a hilltop settlement that did not appear in official records. Sitting on the edge of a cliff under the jungle, it had straight edges and sharp corners, along with what looked like a leveled plaza, an oval pyramid at least 8-12 meters tall and a hollow that may have been a water reservoir. The developer wrote the findings up in Spanish and sent a report to Mexico's National Institute of Anthropology and History (INAH). The institute replied that it had no registered archaeological site at that location.

A correction followed, however. According to the update, the site had already been mapped in a 2025 paper by Estrada-Belli and colleagues. The agents missed it while going through the literature, so they rediscovered it rather than discovered it; it simply was not yet in INAH's register. Still, the episode shows how quickly lidar data can now be screened and how fast a formal reply from authorities can arrive.