An NDVI map shows that something is different. It does not say what, or whether it matters. The useful output is a short, ranked list of places an agronomist should look today.
All Agriculture & AgTech →
AI crop monitoring reads drone, satellite and phone imagery of a field, detects signals of water stress, nutrient deficiency, disease, pest damage, weeds and poor emergence, and turns them into a ranked scouting list with the evidence for each spot. An agronomist confirms what is actually there. It combines frequent, free Sentinel-2 satellite passes for the whole farm with higher-resolution drone or handheld images where detail matters.
Plant disease detection from images is real but narrower than demos suggest: many symptoms look alike, and a model trained on one variety, growth stage or climate can be wrong on another. That is why every system we build is labelled and validated on imagery from the region and crops it will serve.
satellite, drone, phone
against the field’s own history
likely cause with confidence
severity, spread, crop stage
confirms and records the cause
each confirmation improves the model
It analyses repeated imagery of a field, usually satellite for frequent whole-farm coverage and drone or phone images for detail, to find areas that differ from expected growth. Models then estimate the likely cause and rank areas for scouting. Accuracy depends heavily on local training data, so systems should be validated against field-checked observations from the same region.
For specific diseases in specific crops, with good training images, it can be a useful first screen. Many symptoms overlap with nutrient deficiency, herbicide damage or abiotic stress, and performance drops on varieties and conditions the model has not seen. We treat image classification as a pointer for an agronomist to confirm, never as a diagnosis.
Satellite imagery such as Sentinel-2 is free and frequent, and good for spotting change across a farm at field scale. It cannot resolve individual plants or small patches, and clouds interrupt it. Drones give centimetre detail on demand. Most systems use satellite to decide where to fly or walk, and drones or phones where detail matters.
What we built, what stage it is at, and a link to the live thing wherever there is one.
yourOS is an operating system with an AI at its heart. You talk to it like a person, out loud or typed. It makes your calls, plans your days and works on your projects with a crew of agents, on your own private server. Our own product, built from the first commit; the waitlist is open.
Website, backend and app assets for Sonora, a free AI sound-therapy app on iOS and Android published by Cognitive AI.
Brand, website, prototype, apps on five platforms, the AI backend and the algorithm-intelligence pipeline for Podswap, a social growth engine that runs without a human in the loop.
In closed beta: Roxy, a private AI assistant with permanent memory running on infrastructure the user owns. Brand, site, product, backend and conversational design.
Live at coherence.com: brand identity generated with AI agents we directed, the motion system and website for the group behind Sonora, AboutAI, WakeUp and MudShadows. Agent work remains in build.
Live at domainbooth.com for DomainBooth, a premium domain brokerage: a new animated mark, every page redesigned and rebuilt with designed mobile layouts, and a custom CMS for its sales record, featured names, press and enquiries.
Start with a season of imagery and the scouting notes that go with it.
30-minute technical call · no deck