Productivity · News · 🇧🇷 Brazil
Embrapa app diagnoses soybean diseases from a photo
Researchers are testing with farmers an app that recognizes Asian soybean rust and downy mildew in phone images.
- Profession
- Farmer
- Tools
- App Embrapa (em testes)
- Source
- canalrural.com.br ↗
- Country
- 🇧🇷 Brazil
- Report date
- June 23, 2026
- Verified on
- October 24, 2026
What they did
The system was trained on thousands of images of healthy and diseased plants and returns an assessment of the possible problem.
How it went
It is in the testing phase. The stated goal is accuracy close to 100%, but no results have been published yet.
Good to know
Tool still in testing: use it as an alert, not as a diagnosis.
The prompt
List the visual signs that tell Asian soybean rust, downy mildew and [other disease] apart in soybeans, which part of the plant to look at, and which photos to take to send to the agronomist.
Replace what is in [brackets]. Prompt written by us from the account, not a literal copy of the source. Do not paste other people’s personal data (privacy laws such as LGPD and GDPR apply).
Summary in our own words. Results as stated in the original account; we have not tested or audited them. Read the source ↗ Found a mistake?
Similar cases
01Identify soybean and corn pests with your phone, even without signal
A tool built with IFMT researchers recognizes four pests from a photo and turns the records into maps.
02Ranch hand logs farm data by voice message on WhatsApp
A specialist shows AI converting field voice messages into inventory entries and answering the owner.
03Dairy Farms Log Their Routine on WhatsApp with AI
A startup from Minas Gerais brought dairy farm management to WhatsApp and accelerated adoption.
04Farmer Gets Management Questions Answered by a WhatsApp Chatbot
Embrapa's RAImundo answers by voice message and analyzes photos of pests and animals.
05A Chatbot as a Farmer's Technical Assistant
Globo Rural lists uses of AI in agriculture, such as a chatbot that answers questions about fertilizing and planting.
06Claude doubled the speed of a home Wi-Fi network
A user asked for help with slow internet; the agent ran tests, read the Mac's signal data and walked them through the router settings.
07Product manager turns scattered notes into a priority list
Ron Forbes dumps meeting notes into a folder and Claude Code returns summaries and tasks sorted by priority.
08A table at a hard-to-book restaurant without refreshing the website
The user asked the concierge to watch for an opening at Don Angie; the agent booked it as soon as one appeared.