Our new website is still in development. Some pages and details are being finalised.

Real deployment.

Real environments.

Evidence from the field shows how Crane AI gets used in real-world environments by real-world people and communities it supports the most.

Deployed

Field demonstration

Technical delivery

Pilot / integration

Pilot preparation

What has worked, under what conditions, with what limits

EaseHealth

Location

Luweero District, Uganda

System

EaseHealth on Android, adapted MedGemma, offline inference

Scale

15+ public health facilities · 268+ consented frontline health workers

Research design

50-CHW cluster-randomised study with IDI Makerere

Approvals

Makerere REC MAKSHSREC-2026-41 · UNCST HS7408ES

Evidence type

Deployment, feasibility, adoption, usability, safety — not clinical effectiveness

The problem

In frontline care environments, clinical teams often need access to reliable decision support while working with limited connectivity and resources.

What the deployment taught us

Offline operation can make advanced model capability available where cloud access is unreliable. Clinical boundaries and refusal behaviour are product requirements. Device capability can become the binding constraint.

A documented moment

During a prolonged delivery, an enrolled midwife used the application to structure the case. The system helps the professional ask the right questions while authority remains with the professional.

Limitations

The deployment does not establish clinical effectiveness or universal accuracy. Evidence is specific to documented sites, participants, device configuration, model version and study design.

Available now on Android

Trawl

Find anything on your phone by what’s in it, with no internet.

Download Trawl

On-device pipeline

Google’s EmbeddingGemma 2 finds files by meaning. Microsoft’s TinyCLIP gives photos a quick first pass. NVIDIA’s Parakeet provides English speech-to-text. All run directly on the phone.

Local language coverage

Type searches in Luganda, Kinyarwanda, Swahili and other languages, with support continuing to improve.

Availability

Available now on Android.

Built by

Built by the Crane AI Labs team, led by Bronson Bakunga, using open models.

FIELD EVIDENCE & PIPELINE

Pathways in progress

Where Crane's work currently stands - from demonstrated field evidence through to institutional and commercial pathways still in preparation.

Field evidence

Offline agricultural AI in Kayebwe

Field demonstration

Foundational literacy and numeracy with Fab AI Foundation

Technical delivery and evaluation

Our educational model work targets Ganda-Gemma and Bridge model variants within a teacher-facing workflow. Rather than assessing hypothetical direct classroom impact, evaluation is focused on PCK (Pedagogical Content Knowledge) and ELL benchmarks.

Pipeline in progress

Agricultural advisory pathways

Pilot / integration work

In partnership with Shamba Records (MOU signed) and Hello Tractor (MOU signed), Crane is investigating integration paths with WeatherNext and Africa's Talking.

Voice AI Pathways in Africa

Institutional programme work

Programme

UNDP AI Hub for Sustainable Development - Voice AI Pathways, Italy-India-Kenya trilateral

Crane's role

Lead African technical partner

Announced

GITEX Kenya, May 2026

Partners

UNDP · EkStep/COSS (India) · Msingi AI (Kenya, Sauti ASR/TTS) · Kenyan government channels

Status

Institutional programme work - not a citizen-facing deployment

SME work notes and lender pathway

Pilot preparation

Crane is exploring local-language work-note and SME-finance workflows with a UMRA-regulated Ugandan lender. No outcomes claimed.

Device access partnership (Twist)

Pilot preparation

Device capability was identified in our early field trials as the binding limit on scale. Twist has expressed interest in providing refurbished Android devices for offline voice AI deployment. Signed at Bologna, June 2026. No outcomes claimed.