Technology

The AI and data stack behind Sodagro

How the platform works today, and the GPU-accelerated geospatial models we are building next.

  • Serverless and scalable
  • Private by design

Architecture today

How the app is built today

Four layers, all in use now.

Experience layer

Live

Responsive, server-rendered web app built with Next.js and React. Works in any phone or desktop browser with nothing to install.

Application & API layer

Live

Serverless API routes for chat, disease scans, fields and plans, with authentication, per-plan daily AI quotas and rate limiting.

Intelligence layer

Live

Frontier multimodal large language models for image diagnosis and agronomy advice, grounded in each field's details and forecast, plus a rule-based agronomic risk engine.

Data layer

Live

PostgreSQL with row-level security for every table, private object storage for crop photos, and live weather forecast data.

Inside a disease scan

From photo to treatment plan

The live Crop Disease Scan pipeline, step by step.

  1. 01

    Upload and validate

    JPEG, PNG or WebP up to 4 MB, checked and saved to private storage.

  2. 02

    Add field context

    Crop, sowing date, soil and irrigation from the selected field are attached.

  3. 03

    Multimodal inference

    A vision-capable model examines the photo together with that context.

  4. 04

    Structured output

    A schema-validated result: crop, diagnosis, severity, confidence, look-alikes and treatments.

  5. 05

    Deliver and record

    Shown to the user and saved to history. If anything fails, the daily quota is refunded.

Weather alerts run on a separate rules engine: each field's 7-day forecast is checked against thresholds for heat stress, frost, heavy rain, strong wind, dry spells (using evapotranspiration) and fungal-disease conditions.

Roadmap · Building next

Where GPU compute comes in

The next stage moves from general-purpose AI to models trained on Indian agricultural data. These workloads are planned and not live yet.

Roadmap

Satellite processing pipeline

Ingest multispectral satellite imagery, mask clouds, and compute NDVI and related vegetation-index time series for every registered field.

GPU-accelerated raster processing at scale

Roadmap

India-specific disease vision model

Fine-tune vision models on images of Indian crops, varieties and field conditions, collected with farmer consent through pilots.

GPU training and optimised low-latency inference

Roadmap

Yield and risk forecasting

Time-series models combining weather, crop stage and satellite signals to estimate yield and risk at field level.

GPU training on multi-season datasets

Roadmap

Agricultural foundation model

A multimodal model that understands imagery, weather and agronomy across crops, regions and seasons.

Large-scale distributed GPU training

Research & collaboration

Building better models together

Good agricultural AI needs field data and domain expertise. We are looking for partners to help build and validate the next generation of Sodagro models.

Agricultural universities and institutes

Field validation, crop and disease expertise, and evaluation of model outputs.

Research groups

Remote sensing, computer vision and climate-risk modelling for Indian agriculture.

Data partners

Responsibly sourced, consented datasets of crop images, field records and outcomes.

Any data used for research is collected with consent and handled under our Privacy Policy.

partnerships@sodagro.com

Get started

See the technology in action

Create a free account and try the disease scan and AI Advisor on your own crops.

  1. 1Upload a crop photoGet a structured diagnosis with severity, confidence and treatments.
  2. 2Ask the AI AdvisorAnswers use your field details and local forecast.
  3. 3Check your 7-day risksCrop-risk rules run on the forecast for every field.