By
@Hamerenoh
An AI climate assistant that turns real-time weather data into practical farming advice for Ethiopian farmers. Farmers can ask natural questions like "should I plant this week?" and get answers grounded in actual local weather conditions, not generic tips.
Built EthioFarm AI, a climate assistant that turns real-time weather data
into practical farming advice for Ethiopian farmers. It shows live weather
for any location (with a visual “horizon” that changes based on real sky
conditions), gives an instant plant/irrigate/hold-off recommendation, and
lets farmers ask questions like “should I plant this week?” through a
chat interface.
The most challenging part was the AI chat. I originally built it to call
an external AI API directly from the browser, but that approach doesn’t
actually work once hosted — it needs a securely-held API key and backend
server I don’t have access to. I rebuilt it as a self-contained rule-based
system instead: it detects what the farmer is asking about (planting,
irrigation, or rain) and generates a specific answer using real live
weather data — no external dependency, works the same whether local or
hosted.
I’m proud that I wrote the core logic myself — the keyword-detection and
answer-generation functions — working through the conditional logic step
by step instead of just pasting code. It’s a small thing, but it’s the
first time I really understood what I was building rather than just
shipping something that worked.
To test it: enter a real Ethiopian town (like Bahir Dar or Hawassa)or whatever city , click
“Check weather,” then ask a question like “will it rain tomorrow?” in the
Field Journal chat — the answer will reflect that location’s real current
weather data.
1h 2m 32s logged
Solved the AI backend problem in EthioFarm AI. The chat previously called
an external AI API directly from the browser, which isn’t realistic to
deploy without a backend server and paid API key. I rebuilt it as a
self-contained rule-based assistant instead: it detects what a farmer is
asking about (planting, irrigation, or rain) via keyword matching, then
combines that with real live weather data to generate a specific answer.
No external dependency — works identically whether local or hosted.
I wrote the core logic (detectIntent and generateAnswer functions) myself,
working through conditional statements step by step rather than just
pasting code. Tested it end-to-end — asked real questions and got correct
answers based on live weather data for a real location.
Also wrote a full README documenting the problem, solution, tech stack,
1h 44m logged
Built the dynamic weather horizon (updateHorizon) to switch sky gradients and cloud visuals in real time.Implemented the async loadWeather function to fetch forecasts and handle status updates.Coded event listeners for the AI chat so users can send messages via button clicks, the Enter key, or suggestion chips.Cleaned up script typos and DOM element references to make everything run smoothly.
1h 30m logged
Worked on the loadWeather(place) asynchronous function to manage fetching location data and updating current weather properties.Integrated fetchweather, updateHorizon, and recommendation building logic into the main loading sequence.Refined status message handling and location string formatting for the user interface.
1h 40m 16s logged
Worked inside index.html on the updateHorizon(mood) JavaScript function.Refined conditional checks for weather states like clear, partly cloudy, and overcast skies.Fixed a spelling typo in the mood condition check to ensure the dynamic sky gradients and SVG cloud elements render smoothly.
4h 0m 10s logged
Started EthioFarm AI — an AI climate assistant for Ethiopian farmers. So
far I’ve built the core structure: a weather-fetching system using real
location + forecast data, a visual “horizon” that changes based on actual
weather conditions, and the beginning of an AI chat feature. Still
debugging the weather display right now, and I’m working through.
