All case studies
Design + Build · Ag-Tech · B2B Pilot Sep 2026 · 30-day Phase 0 · Discovery → Design → Ship

AgroHQ — a farm platform, built from the field up.

A B2B platform for mid-sized farms and agri-cooperatives — livestock, crops, workers, buyers and weather in one system. From twelve field visits to a Flutter app in production with an AI farm advisor, in 30 days.

The Challenge

Farm operators were juggling six tools — WhatsApp groups for workers, paper ledgers for livestock, spreadsheets for buyers, weather apps for planning, and no way to see the farm as one system. The founder wanted to modernise a $9B underserved market with a mobile-first product — and needed a shipping partner, not a strategy deck.

What we shipped

  • 12 farm visits · card-sort with 6 farm managers
  • Full design system (Figma) + Flutter component library
  • Field ops dashboard (web) + operator mobile app (Flutter)
  • AI farm advisor — Assistants v2 with farm-context memory
  • WhatsApp Cloud API bridge for low-literacy field workers
  • Buyer marketplace · price signals · pickup coordination

Stack

  • Flutter (iOS + Android) · Dart
  • Laravel · MySQL · Redis · Horizon queues
  • OpenAI Assistants v2 · GPT-4o
  • WhatsApp Cloud API · Twilio SMS fallback
  • DigitalOcean · Cloudflare R2 · Firebase FCM
30dDiscovery → shipped pilot
12Farms in Phase 0 pilot
84%Weekly-active operators
6→1Tools consolidated per farm

The brief: modernise an industry that's still on paper

AgroHQ's founder isn't a developer. He's an operator who grew up around farms and knew every fragmented tool the industry defaults to — WhatsApp for staff, ledgers for livestock, spreadsheets for buyers, weather apps for planning, and everyone's memory holding the rest together. He'd sat with two agencies who quoted 6–9 months for a discovery phase alone. He came to us with one question: can you get me a real pilot in production in a month?

"I didn't want a beautiful Figma file. I wanted farms actually using it, actually paying. Growvate went to the farms with me. That was the difference." — Founder, AgroHQ

Week 1: Discovery — 12 farm visits, one whiteboard

Before we opened a single tool, we spent five days on farms. Twelve visits across four regions. Watched morning stand-ups, sat in on buyer calls, followed workers with their phones. We surfaced three insights that reshaped the product:

We ran a card-sort exercise with 6 farm managers to build the information architecture. It killed our first draft of the top-level nav (six sections) and gave us the one that shipped — Farm, People, Buyers, AI Advisor.

AgroHQ · Farm-manager card-sort · FigJam 6 managers Farm People Buyers AI Advisor Livestock log ID · weight · health Crop calendar Sow · fertilise · harvest Weather + rain 7-day outlook Field map Plot · size · status Worker roster Roles · shifts Check-in log WhatsApp bridge Wages ledger Weekly / piece rate Price signals Market vs offered Buyer inbox Volume · pickup Escrow status Locked · released Logistics Truck arrival "When to sell?" Voice or type Pest diagnosis Photo upload Yield forecast 30-day view 6 candidate sections collapsed into 4. Nav decision unlocked.
Card-sort · 6 farm managers. We laid out 20+ candidate cards on a FigJam board and asked six farm managers to group them how they'd actually work. What we thought was six top-level sections collapsed into four — Farm, People, Buyers, AI Advisor — the exact nav that shipped.

Week 2: Design system + AI architecture

Two parallel sprints. The design team built a farm-friendly UI system — high-contrast, glove-friendly touch targets (48px minimum), large numerals for glance-reading in the sun, semantic colour for livestock status. Packaged as a Figma library and mirrored as a Flutter component library so mobile shipped from the same source of truth as the web dashboard.

The AI team built the farm advisor on OpenAI's Assistants v2 API — with a farm-context memory layer that keeps each operator's context (herd size, crop calendar, region-specific pest patterns) persistent across sessions. It doesn't hallucinate the farm's numbers; it looks them up.

Week 3: Build — the field ops dashboard + mobile app

The dashboard is the operator's cockpit — livestock health, worker check-ins, weather signals, buyer inbox, AI advisor thread — all one screen, all keyboard-navigable. The mobile app is the field partner — clock-in, photo logs, voice-note advisor queries, and offline-first sync (we lost data twice in early pilots when signal dropped — sync-first became a hard rule).

Laravel powers the backend — battle-tested, deployable anywhere, and reads/writes cleanly to MySQL with Redis for the AI advisor's memory layer. Boring stack. Deliberately.

agrohq.com/dashboard FARM Overview Livestock Crops Fields PEOPLE Workers Check-ins BUYERS Inbox Marketplace AI Advisor Green Ridge Farm Mon 21 Sep · 84 head · 4 crops · 6 workers on-site Livestock health 98% 2 flagged Workers on site 6 / 7 1 late Open buyer offers 4 2 above market 7-day rain 18mm Wed peak Buyer inbox ↑ 2 above market Sunrise Dairy · 500L · pickup Thu$0.72/L Kellogg Co. · 3T maize · pickup Fri$318/T Bwari Coop · 1T millet · TBD$240/T Al-Amin Butcher · 12 head$680/head AI Advisor Sunrise Dairy is 8% above last week's local median. Kellogg Co. is average, but pickup is same-day. Accept Sunrise offer Grounded in your last 30 days Field workers Via WhatsApp bridge · 6 active check-ins Sadiq Field 3 · 07:12 Bello Barn · 07:04 Musa Field 1 · 07:22 Rahmat Late · 07:34 Ibrahim Field 4 · 06:58 +2 9:41 FIELD APP Ask the advisor Voice note · 0:12 "Are the calves worth vaccinating this week?" AI Advisor Yes — 4 calves are 6-8 weeks past due. Local vet is on-route Wed. Book vet visit Quick actions 📷 Log photo Clock in Weather · next 24h 28° · rain 4pm Offline-first · syncs when signal returns
Field ops dashboard + mobile companion. The dashboard is the operator's Monday-morning cockpit — livestock health, worker check-ins, buyer inbox with AI price context. The mobile app is the field companion — voice-note advisor queries and offline-first sync for signal dead zones.

Week 4: Pilot — 12 farms live

We onboarded 12 farms in the first week of pilot, in-person for the first four (so we could watch onboarding fail in real time) and remote for the rest. By day 21 of the pilot, 84% of operators were logging in weekly. By day 30, we had our first paying farm.

The metric we obsessed over — tools consolidated per farm — landed at 6 → 1 across the pilot cohort. Operators who ran their farm on 6 disconnected tools now ran it on AgroHQ.

What we'd do differently

Two things. First, we'd have shipped offline-first sync from day one instead of retrofitting it week three — farms have signal dead zones we hadn't sat in yet. Second, we'd have built the WhatsApp bridge before the mobile app, not alongside it — it's the interface workers already trust, and the mobile app is a slower behaviour change than we assumed.

Both are now standard parts of our field-work playbook.

"Twelve farms live. Six tools down to one. Thirty days from a slide deck to real operators paying. That's not a discovery phase — that's a business."

— Founder, AgroHQ Ag-tech · B2B
Next case study →

Northline Health — modernising a UK clinic group with AI + a redesigned portal

Read next case