KisanVaani — किसानवाणी
AI agricultural intelligence for farmers — without requiring a smartphone.
An engineering and product case study detailing how KisanVaani evolved from an initial mobile web application into a multi-channel agricultural intelligence system powered by Indic Voice, SMS, WhatsApp, grounded soil telemetry, and district command center operations.
Project Snapshot
Core constraints, target persona, and product architecture at a glance
Small and marginal farmers lack localized guidance and often do not own smartphones, reliable mobile data, or digital apps.
Indian smallholder farmers (86% of 146M+ holdings), predominantly using basic feature phones with oral-first Indic dialects.
The farmer shouldn't adapt to technology. The technology must meet the farmer on the devices they already own.
AI advisory delivered via Voice Calls, SMS, WhatsApp, and Web Demo, backed by soil telemetry, weather data, and mandi prices.
Every farmer interaction aggregates into district-level signals for early pest outbreak alerts and agricultural officer triage.
Team Vishwakarma Devs • Built for Build with AI: Code for Communities (Track 4: Kisan Alert).
Why Traditional Agritech Fails Smallholder Farmers
Existing agritech platforms assume modern smartphones, high-speed 4G/5G connections, and English/text fluency. But rural Indian agriculture operates under completely different realities.
Most apps assume a 6-inch touchscreen and app store installation, excluding nearly half of rural households.
Heavy web applications fail over intermittent 2G/EDGE networks in deep agricultural hinterlands.
Navigating complex drop-down forms and typing crop diseases in Latin scripts creates immediate friction.
Agronomic science is published in English/Hindi, while farmers discuss soil symptoms in localized regional dialects.
Weather forecasts, mandi prices, soil cards, and pest guides exist as disjointed silos across different portals.
Farmer distress calls are treated as one-off support queries rather than aggregate early-warning outbreak signals.
Designing for The Smallholder Farmer
Rather than designing for an idealized tech-savvy user, we mapped the strict boundary constraints of real farmers across rural India.
Smallholder Farmer (Ramesh)
2 Acres Paddy & Cotton • Basic Keypad Phone • Bundelkhand / AP
Ramesh relies on seasonal rain and neighbor advice. When his paddy leaves show brown spots, he cannot search web forums or upload high-res files. He needs to dial a number, describe symptoms in his mother tongue, and receive an immediate actionable advisory.
- ✓Device: Basic 2G/GSM feature phone without browser capability.
- ✓Primary Input: Voice speech in vernacular Hindi/Telugu/Kannada.
- ✓Secondary Channel: SMS bulleted steps for reference while in the field.
- ✓Friction: Zero logins, zero app downloads, zero date inputs.
The Big Pivot: “Does the Farmer Need an App at All?”
“How do we build an agricultural mobile app with interactive forms?”
“The farmer shouldn't have to adapt to our technology. The technology must adapt to the farmer.”
Instead of forcing the farmer to buy a smartphone and learn application navigation, we moved the intelligence to the cloud and connected it to standard toll-free telephony and SMS.
How KisanVaani Was Discovered Through Iteration
The final platform was not designed on Day 1. It was discovered across four rapid iterations of user testing, prototype building, and challenging our own assumptions.
From Problem Statement to Visual Concept
Our initial attempt focused on defining the project vision and building a clean website showcase for satellite crop diagnostics and weather alerts.
Iteration 01 — Landing Page & Agricultural Website Concept
Click to load and play video evidence 🎬
An educational web portal where farmers could read weather advisories and check crop diseases online.
Landing page with agricultural alert cards, hero animations, and static weather/crop guidance.
Assumed farmers would browse the internet and read web articles during daily farming activities.
Farmers don't browse landing pages. They have urgent, specific, localized crop problems requiring direct action.
From Concept to Application
Transitioned from a static website to an application-oriented experience with interactive diagnostic modules and crop advisory forms.
Iteration 02 — Building The Web Application Experience
Click to load and play video evidence 🎬
If we build an interactive web app with forms and dropdowns, farmers can input soil stats and get tailored advice.
Mobile-first React application with interactive diagnostic inputs, soil charts, and weather cards.
Assumed farmers knew technical soil parameters (pH, NPK values) and could comfortably navigate multi-step form UIs.
Form friction is catastrophic. Real farmers couldn't answer form fields and lacked touchscreen fluency.
The Accessibility-First Voice & SMS Pivot
The fundamental architecture pivot: Replaced complex UI forms with natural Indic Voice interaction and low-bandwidth SMS delivery for feature phones.
Iteration 03 — The Voice & SMS Accessibility Pivot
Click to load and play video evidence 🎬
Eliminate the app entirely for the farmer. Use natural spoken voice in regional languages over phone calls.
Telephony gateway connecting speech recognition to Gemini LLM with instant voice-back and automated SMS summary delivery.
Assumed pure AI conversational bots could answer 100% of cases autonomously without expert supervision.
Severe fungal blights and ambiguous symptoms need human expert escalation; and individual calls hold rich district-wide signal.
From Feature to Full Multi-Channel Ecosystem
The final complete platform: Integrating Voice, SMS, WhatsApp, Multimodal Leaf Diagnosis, Grounded Soil/Weather APIs, and District Command Center.
Iteration 04 — The Full Multi-Channel Agricultural Ecosystem
Click to load and play video evidence 🎬
Build a comprehensive two-sided platform: zero-friction access for farmers, and operational intelligence for agriculture officers.
Full KisanVaani platform with Voice, SMS, WhatsApp, photo diagnosis, grounded SoilGrids/Meteo data, and RSK Command Center.
Won Google Code for Community (Track 4: Kisan Alert) with end-to-end working telephony, AI pipelines, and operational suite.
Pilot blueprint designed to serve 2,000+ farmers across blocks at an operating cost of under ₹12 per farmer per season.
Early Assumptions vs Reality & Product Response
Farmer has a smartphone and will install an app.
Built complex React UI views and forms.
45%+ rural users carry feature phones on 2G networks.
App download is an insurmountable barrier.
Toll-Free Voice IVR + Automated SMS Prescriptions.
No app download or screen required.
The 3-Tier Multi-Channel Ecosystem
KisanVaani is a comprehensive three-tier system connecting edge farmer telephony, multi-source scientific intelligence, and district agricultural governance.
Voice Calls, SMS, WhatsApp & Web Simulator
Provides multi-channel entry points adapted to the farmer's available hardware: Toll-free IVR for basic phones, DLT SMS for offline bulleted steps, WhatsApp for photo leaf diagnosis, and browser demo simulation with Web Speech API for testing.
Gemini Multimodal + Grounded Agronomic Data Pipelines
Synthesizes real-time satellite meteorology, ISRIC SoilGrids texture/pH layers, Government of India data.gov.in mandi wholesale prices, and ICAR/SAU package of practices. All Gemini LLM answers are strictly grounded against empirical agricultural parameters.
RSK / KVK Agronomist Portal & Early Outbreak Signals
Provides government extension officers and Krishi Vigyan Kendra (KVK) scientists with a triage portal for uncertain/severe disease cases, pin-code targeted weather alerts, and geographic clustering heatmaps to spot emerging locust/fungal infestations before they spread.
Engineering Flowcharts & Visual Architecture
Clean, high-level visual diagrams showing the end-to-end communication pipelines, algorithmic decision loops, and operational triage flows.
1. High-Level End-to-End System Architecture
- • 📞 Inbound Voice (Toll-Free)
- • 💬 DLT SMS Messaging
- • 📲 WhatsApp Business Bot
- • 💻 Web Browser Simulator
- • Twilio Voice / SMS Webhooks
- •
/api/advisory&/api/mandi - •
/api/weather&/api/diagnose - •
/api/recommendCrop Engine
- • 🧠 Google Gemini 1.5 Pro / Flash
- • 🌍 ISRIC SoilGrids v2 (pH, Texture)
- • 🌧️ Open-Meteo & OpenWeather
- • 📊 data.gov.in & Agmarknet Mandi
- • 🎫 NeonDB Escalation Tickets
- • 🏛️ KVK / RSK Scientist Review
- • 📍 Outbreak Anomaly Heatmap
- • 📢 Pin-Code Broadcast SMS Alerts
2. Production Telephony vs Web Demo Separation
/api/telephony/voice/demo and speaks into laptop mic/api/advisory with grounded context3. Conversational Crop Advisory Flow (Max 2 Rounds)
“My cotton leaves are turning yellow with brown curling edges.”
Verifies farming relevance; politely declines non-agricultural queries.
Asks concise numbered options: “Are leaves dry or sticky with white dust?”
Delivers verified organic & chemical remedies + auto SMS prescription.
4. Mandi Price Engine: 7-Day Auto Lookback
Extracts Commodity & District
E.g., “Tomato price in Guntur AP”. Auto-disambiguates duplicate city names.
Check Today's Arrivals
Queries Ministry of Agriculture daily APMC database for current date records.
Zero Date Friction
If today has no data (weekend/lag), scans back up to Day -7 on Agmarknet automatically.
Speaks Price Spread
Returns Min: ₹1,800, Modal: ₹2,200, Max: ₹2,500/Quintal + latest recording date.
5. Agro-Meteorological Weather & Spray Advisory
Open-Meteo & OpenWeather
Extracts pin code/district and fetches 7-day hourly temperature, precipitation, and wind speeds.
Safety & Spray Calculations
Evaluates heavy rain (>64.5mm), heatwave (>40°C), and high wind (>15km/h drift risk).
Optimal Window Recommendation
“Optimal spraying window: 7:00 AM – 10:00 AM. Rain expected in afternoon.”
6. Photo Disease Diagnosis & Human-in-the-Loop Triage
Automated Direct Prescription
Farmer immediately receives pathogen name (e.g. Early Blight), chemical dosage (Mancozeb 75% WP @ 2g/L), organic neem oil alternative, and safety interval.
Escalation to RSK / KVK Agronomist
Creates high-priority ticket in Command Center. Government agricultural officer reviews leaf photo, enters verified guidance, and triggers farmer callback.
7. Grounded Crop Recommendation Multi-Signal Convergence
pH, Sand/Clay %, Organic Carbon
NPK & Micronutrient Levels
Seasonal Rainfall & GDD
Historical Mandi Profitability
Crops, Water Fit, Profit Index
8. District Outbreak Anomaly Clustering (Early Warning)
Support Interactions
Farmers across neighboring villages report leaf spots and worm damage.
Spatial Telemetry
Queries are geocoded by pin code and anonymized in the telemetry database.
Spike Detection
System flags >15 cases of Fall Armyworm in 48 hours within Block 506001.
Targeted SMS Alert
District Agriculture Officer broadcasts preventive neem spray alert to all registered farmers.
Designing for Flaky Networks & Unreliable AI
In agricultural lifelines, returning a 500 error or hallucinated chemical dosage is unacceptable. KisanVaani implements two core resilience patterns:
Cached & Hindi Offline Fallback Strategy
Every live telephony and API call path includes a pre-compiled local cache and static Hindi audio/text fallback. If Gemini or data.gov.in is temporarily unreachable, the farmer is never hung up on; they receive verified baseline seasonal package-of-practices guidance immediately.
Farmer Call → External API Timeout → Cached Seasonal Guidance DeliveredWhen AI Shouldn't Be the Final Answer
AI handles scale; humans handle uncertainty and crop severity. If an image is blurry or symptoms suggest high-quarantine pests (like Pink Bollworm), the AI does not issue autonomous final advice. It creates a high-priority ticket in the RSK dashboard for verified agronomist review.
Ambiguous Leaf Photo → AI Flags Low Confidence → RSK Scientist PrescribesTechnology Stack & Scientific Datasets
Production Tech Stack
Next.js 16 (App Router)
React 19, TypeScript, Tailwind 4
Google Gemini 1.5
@google/genai Pro & Flash
PostgreSQL
Neon Serverless Driver
Twilio Voice & SMS
TwiML, WhatsApp Business
Grounded Agricultural Data Sources
| SOURCE | DATA PROVIDED | ROLE IN PLATFORM |
|---|---|---|
| data.gov.in | Daily Mandi Wholesale Prices (Min, Modal, Max) | Real-time commodity price intelligence for APMC markets. |
| Agmarknet 2.0 | State Mandi Fallback Database | Secondary lookback fallback when primary daily arrivals lag. |
| ISRIC SoilGrids v2 | Soil pH, Sand/Clay %, Organic Carbon, WRB | Automated soil texture & chemical profile without manual test entry. |
| Open-Meteo & OpenWeather | Rainfall, Evapotranspiration (ET₀), Wind, Humidity | Dry-spell alerts, 72h downpour warnings, and spray windows. |
| Soil Health Card (SHC) | National NPK & Micronutrient Standards | Fertilizer recommendation calibration for nitrogen/phosphorus. |
| ICAR / SAU Guidelines | State Agricultural University Package of Practices | Ground truth agronomic treatment protocols and safety windows. |
| IMD Thresholds | Heavy Rain (>64.5mm), Heatwave (>40°C) | Automated trigger rules for district-wide emergency broadcasts. |
Core API Endpoints & Route Architecture
/api/advisory▲Conversational Agricultural Advisory
Receives voice/text transcriptions, validates farming relevance, queries Gemini with grounded context, limits clarifications to 2 rounds, and returns formatted Indic guidance.
/api/mandi▼Wholesale Mandi Price Resolution
/api/weather▼Agro-Meteorological Advisory
/api/diagnose▼Multimodal Leaf Disease Diagnosis
/api/recommend▼Soil-Climate Crop Match Engine
/api/telephony/*▼Inbound Telephony & DLT SMS Handlers
/command▼District Command Center Suite
/demo▼Interactive Web Simulator
Field Pilot Blueprint & Operating Economics
Outlining the operational deployment plan from single-block pilot to district-wide extension network.
2,000 Farmers in One Agricultural Block
- • Onboarding via Gram Panchayats and local Krishi Vigyan Kendras (KVK).
- • Missed-call registration to automatically register farm pin code.
- • Inbound toll-free voice advisory and mandi price lookups.
Full District Expansion & Officer Visibility
- • Rythu Seva Kendra (RSK) agronomist triage portal active.
- • Automated weather-zone SMS broadcasts for frost and downpour warnings.
- • District Agriculture Officer visibility into pest cluster heatmaps.
Under ₹12 per farmer per crop season
Achieved by concise AI speech prompts, localized token caching, and bulk government DLT SMS rates.
Engineering & Product Decision Log
Over 45% of Indian rural users own feature phones and face severe app-download friction.
The core product became universal — accessible on any 2G keypad phone in India without internet.
Farmers do not remember exact APMC reporting calendar dates, and mandi data has 2-7 day lag.
Implemented automatic 7-day lookback window. Farmer asks for commodity; system handles date matching.
LLMs frequently hallucinate generic advice (e.g. 'water daily') without empirical soil texture/climate context.
Advice is scientifically calibrated to specific sand/clay percentages and IMD precipitation forecasts.
Severe leaf blights risk real livelihood devastation if misclassified by computer vision models.
Low-confidence and high-severity cases become officer triage tickets in the Command Center.
Individual farmer distress calls contain latent geographic cluster signal about emerging pests.
Created the Command Center early-warning heatmap to alert block officers before infestations spread.
Key Product & Engineering Lessons
Don't build for the tech you want; build for the tech they have.
It is tempting as engineers to build rich WebGL dashboards. But true empathy means meeting users on their existing 2G basic keypad phones.
Accessibility dictates system architecture.
Choosing Voice + SMS wasn't just a UI tweak. It completely restructured the backend into event-driven telephony webhooks and DLT queues.
Voice is a primary product interface.
For oral-first communities, voice is not an auxiliary feature. It is the fastest, most natural, and most trusted interaction modality.
AI needs grounding to be actionable.
Generic LLM responses are dangerous in agriculture. Grounding against SoilGrids, Open-Meteo, and ICAR protocols turns text into reliable advice.
Safety requires explicit human escalation.
AI must know when to say 'I'm escalating this to Dr. Rao at Rythu Seva Kendra' instead of guessing on high-severity crop diseases.
Support systems are latent intelligence systems.
At scale, 1,000 farmers asking about leaf spots is no longer customer support — it is a real-time epidemiologic outbreak signal.
Explore KisanVaani Live
Experience the complete working prototype: Simulate toll-free voice calls with speech synthesis, diagnose leaf pests via camera uploads, test mandi spreads, and explore the District Command Center.