Case Study

Mobile

AmbutechPro

AmbutechPro is a professional AI-powered application built for SMUR/SAMU ambulance personnel in France, designed to streamline patient management, automate reporting, and improve communication during emergency handovers.

Flutterflow

Firebase

Challenges & solutions

The technical problems our team solved to ship a reliable, unified mobile experience.

Design an AI agent within FlutterFlow's Agent Builder capable of understanding complex medical data — vitals, symptoms, and patient history — and delivering clinically reliable interpretations, where generic AI responses were not acceptable for emergency

Created a custom AI agent in FlutterFlow with carefully engineered system prompts, medical terminology rules, and validated example conversations, enabling accurate and consistent analysis of SAMU patient records directly inside the app.

Force the AI agent to always respond in a strict, structured format — free-form AI text could not be used for clinical handoffs, where a missing field could compromise patient safety.

Configured the FlutterFlow AI agent with JSON response mode and a locked SBAR schema (Situation, Background, Assessment, Recommendation), ensuring every generated report is complete, consistent, and ready for emergency department handoff.

Handle AI agent calls, vital sign monitoring, and live data updates simultaneously without freezing the interface — paramedics cannot wait on a loading screen during an emergency.

Implemented asynchronous AI agent actions in FlutterFlow with loading states, response caching, and optimized action flows, keeping the app fully responsive while AI analysis runs in the background.

Pass dynamic context — current vitals, mission details, and patient history stored in the backend — into the AI agent's prompts at runtime so every analysis is personalized to the active case.

Built dynamic prompt injection in FlutterFlow that merges real-time patient data and mission logs into the agent's context on every call, producing case-specific analysis and alerts instead of generic responses.

Transform the AI agent's structured responses, mission logs, and vitals data into professionally formatted PDF reports that meet medical record-keeping requirements.

Developed a PDF export pipeline that parses the agent's JSON output and compiles it with mission data into standardized, shareable reports — completing the workflow from AI analysis to official documentation.

Prevent hallucinated or clinically irrelevant AI suggestions by constraining the agent to real-world SAMU emergency protocols and field terminology.

Refined the FlutterFlow AI agent's system prompts and example conversations in collaboration with an experienced SAMU paramedic, aligning every output with real emergency response workflows and the high-pressure environment of field medicine.

Key features

What users get in the finished, shipped product.

AI-Powered Patient Record Analysis :

Overview : Automates the analysis of SAMU patient records
Function : Helps paramedics quickly interpret critical data
Efficiency : Enables faster action on vital information

SBAR Report Generation :

Overview : Generates structured Situation, Background, Assessment, Recommendation reports
Purpose : Ensures clear communication with emergency departments
Impact : Streamlines the handoff process between medical teams

Vital Signs Monitoring with Alerts :

Tracking : Real-time monitoring of patient vital signs
Alerts : Instant notifications for abnormal readings
Response : Enables timely and life-saving medical interventions

Mission Log Management :

Overview : Efficient recording of mission-specific details
Tracking : Comprehensive management of emergency case history
Accuracy : Ensures precise documentation for every call

PDF Report Export :

Function : Enables easy export of medical reports in PDF format
Usage : Supports seamless sharing and documentation
Compliance : Meets regulatory standards for record-keeping

Built by Medical Professionals :

Expertise : Designed by an experienced SAMU paramedic
Relevance : Tailored to real-world emergency response needs
Workflow : Optimized for the high-pressure environment of field medicine

Tech integrations

Third-party SDKs & libraries

2 core integrations powered

RevenueCat

Core system integration

Google Ads

Core system integration

More Case Studies

Related Work

Similar Projects We've Built

TrueGlow AI – AI-Powered Skincare App

TrueGlow AI is an advanced AI-powered skincare application designed to analyze skin conditions directly from a user’s photo and provide personalized skincare insights in seconds. Using intelligent image analysis, the app detects concerns such as acne, pigmentation, dryness, oiliness, pores, dark circles, and uneven skin tone, helping users build smarter and more effective skincare routines. […]

Next.jsTailwind CSS+3

View Case Study

CareBot AI – AI-Powered Doctor Appointment Booking

CareBot AI is an intelligent conversational healthcare platform designed to simplify and automate doctor appointment booking through AI-driven chat interactions. Users can describe their symptoms in natural language, and the system instantly identifies the appropriate medical specialist, checks real-time appointment availability, and completes the booking process within a single conversational interface. The platform eliminates traditional […]

Next.jsTailwind CSS+2

View Case Study

Ashmi Health

Ashmi Health is a digital healthcare and wellness platform designed to provide users with access to personalized health services, consultations, and wellness tracking tools. The platform integrates modern digital health practices with user-centric design to support preventive care, lifestyle management, and ongoing health monitoring. It appears to focus on delivering accessible healthcare solutions, potentially including […]

React NativeNode.js+3

View Case Study

EatTrainTrack: Calorie Counter

EatTrainTrack is an AI-powered health and fitness tracking application designed to simplify nutrition logging, meal planning, and workout monitoring. The app enables users to track their daily food intake, calories, and physical activities using intelligent automation such as photo recognition, voice input, and AI-based analysis. It is built to support users aiming for weight loss, […]

React NativeNode.js+2

View Case Study

View All Work

Have a similar idea? Let's build it together.

From concept to launch, we turn your vision into a world-class product.

Get a free consultation Back to portfolio