DEV Community: Shan F

🤖 RapidRelief Disaster Recovery Assistant AI 2025: 5X Faster Damage Assessment & Rescue Guide ⚠️🛟

Shan F — Sun, 14 Sep 2025 11:32:27 +0000

This is a submission for the Google AI Studio Multimodal Challenge

The objective of RapidRelief - Disaster Recovery Emergency Assistant

As someone passionate about solving real-world problems with practical software, my goal with this submission is to explore the possibilities and demonstrate how Google AI Studio (and its multimodal Gemini/Imagen capabilities) can accelerate the development of an accessible, high-impact emergency tool — specifically RapidRelief Disaster Response Assistant, a multimodal disaster response assistant that combines image + text understanding, AI conversation, and cloud deployment to help people make faster, safer decisions during crises.

Disasters are chaotic and time-sensitive: people need clear, trustworthy guidance right now, not long technical reports. I wanted to build something that’s not just smart, but approachable — a lightweight, mobile-first assistant that lets users capture photos and short descriptions, receive an immediate severity assessment, and get a prioritized, actionable safety plan they can follow even under stress.

In exploring Google AI Studio and multimodal models, I found they can significantly reduce the effort required to:

📷 Analyze visual damage automatically (e.g., detect structural cracks, flooded areas, fire/smoke indicators) from user photos and produce concise labels and confidence scores.
🧠 Generate prioritized, context-aware action steps that translate technical risk into plain language (what to do first, who to call, what to avoid).
🖼️ Create quick “before / after” visualizations and annotated reports for victims, responders, and insurers.
💬 Power a conversational UX that guides non-experts through triage, follow-ups, and simple checklists using Gemini Chat APIs.
🌍 Localize recommendations and emergency contacts automatically (region, language, and common response phone numbers).
📤 Produce shareable outputs (short reports, SMS/WhatsApp messages, PDFs) so users can notify family or first responders instantly.
🎨 Speed up frontend and interaction design with AI-driven copy, microcopy, and flow suggestions so the app remains calming and easy to use under stress.
🏗️ Generate training and synthetic datasets for safer, more robust model behavior without long manual labeling cycles.

This submission aims to show that Google AI Studio is not just a toolkit for research labs but a practical accelerator for natural disaster victims, builders, NGOs, and first-response teams who want to move quickly from idea to deployed, useful software.

Through a clear, step-by-step demonstration, I hope to encourage developers — especially solo builders, students, and humanitarian technologists — to experiment with multimodal AI to create tools that genuinely improve safety and reduce panic when every second counts.

1️⃣ What I Built
2️⃣ Live Demo
3️⃣ How I Used Google AI Studio
4️⃣ Multimodal Features
5️⃣ Real-World Problem Solving
6️⃣ Application Features & Best Practices
7️⃣ Development & Deployment Details
8️⃣ Challenge Compliance
9️⃣ Future Enhancements
🔟 Lessons Learned
⚠️ Disclaimer
✅ Conclusion

1️⃣ What I Built

The Disaster Response Assistant is a web application designed to provide immediate, AI-powered support to individuals in disaster-affected areas. In the chaotic aftermath of an earthquake, flood, or fire, getting clear, actionable information is critical for safety. This applet addresses that need by allowing users to quickly capture and send images and text descriptions of damage to their surroundings.

It solves the crucial problem of rapid situational assessment. Instead of waiting for emergency services who may be overwhelmed, users can get an instant analysis of their situation, including:

A clear assessment of the structural damage.
The severity level of the situation (from Low to Critical).
A prioritized list of immediate, actionable safety steps.

The experience it creates is one of empowerment and reassurance during a highly stressful time. By transforming a user's phone into a powerful diagnostic tool, it helps reduce panic, provides a clear path forward, and enables users to take control and secure their immediate safety.

2️⃣ Demo

Live Applet: Disaster Response Assistant

Video Demo:

Repository:

amfshan / disasterresponseassistant

RapidRelief AI 2025: 5X Faster Damage Assessment & Rescue Guide

Disaster Response Assistant

A multimodal AI applet built for the Google AI Studio Challenge - demonstrating the power of Gemini's multimodal content understanding and generation capabilities.

Challenge Compliance

This applet fully meets all requirements of the "Build and Deploy a Multimodal Applet" challenge:

✅ Built on Google AI Studio - Developed using Google AI Studio's development environment and APIs
✅ Deployed using Cloud Run - Production deployment on Google Cloud Run for scalability and reliability
✅ Multimodal Functionality - Implements multiple Gemini capabilities:

Gemini 2.5 Flash for multimodal image and text understanding
Imagen 4.0 for AI-generated "before disaster" visualizations
Gemini Chat API for context-aware conversational support

What I Built

The Disaster Response Assistant is a web application designed to provide immediate, AI-powered support to individuals in disaster-affected areas. In the chaotic aftermath of an earthquake, flood, or fire, getting clear, actionable information is critical for safety. This applet addresses that…

View on GitHub

Screenshots

1. Damage Reporting Interface: The clean, intuitive UI for uploading multiple images and adding a voice or text description.

2. Comprehensive Analysis Results: The main results screen displaying the severity, damage assessment, and actionable guidance.

3. Before & After Comparison: The powerful visual comparison showing the user's photo next to an AI-generated image of the location before the disaster.

4. Interactive Follow-up Chat: The conversational AI chatbot that helps users with specific follow-up questions.

3️⃣ How I Used Google AI Studio

Brainstorming and Initial Prompting

# 🌍 RapidRelief — Concept & Key Features

## 💡 Concept
**RapidRelief** is a multimodal applet designed to assist residents in **disaster-affected areas** — including earthquakes, floods, fires, and storms.  
By combining **image + audio understanding** with AI-generated guidance, the app helps people quickly **assess damage** and **take safe, informed action** during emergencies.

## 🔑 Key Features

- 📸 **Upload Photos or Videos**  
  Residents can capture and upload **damage images or videos** (houses, roads, infrastructure).  
  - Uses **Gemini 2.5 Pro / Flash** to detect **structural damage, flooding, fires, and blocked roads**.  
  - Identifies severity and flags areas that may be unsafe to enter.

- 🎤 **Voice & Audio Support**  
  Users can send **audio descriptions** or voice messages —  
  > “I see cracks in the wall, water rising up to knee height.”  
  The app automatically **transcribes** the message and **combines** it with visual analysis for a more accurate situation report.

- 🧭 **AI-Generated Actionable Guidance**  
  The app suggests **clear next steps**, such as:  
  - Identifying **safe exit routes** (based on images/videos)  
  - **Immediate actions** (covering broken glass, shutting off electricity, avoiding flooded areas)  
  - **Prioritized steps** when multiple hazards are detected

- 🗺️ **Before/After Map Comparisons**  
  Integrates with **map and satellite imagery** to:  
  - Detect **terrain changes** or **flooded areas**  
  - Show **before/after comparisons** to locate blocked roads, collapsed structures, or safe zones  

This concept turns a user’s **smartphone into a powerful emergency assistant** — helping them stay calm, act quickly, and communicate vital information to first responders when it matters most.

📹 Google AI Studio Demo

Deployment Infrastructure

Platform: Google Cloud Run (containerized deployment)
Scaling: Auto-scaling based on traffic with 0-to-N instances
Runtime: Node.js with Express.js backend
Frontend: React with TypeScript, served as static assets
Build Process: Docker containerization with multi-stage builds

Google AI API Integration

The entire application is orchestrated around the powerful multimodal capabilities of the Gemini API. I did not just use it for a single task, but created a chain of AI-driven operations to deliver a comprehensive user experience.

Multimodal Analysis (gemini-2.5-flash): The core of the app uses gemini-2.5-flash to process a complex, multimodal input: multiple user-uploaded images and a text description. I configured the model to use JSON Mode with a strict responseSchema. This is a critical best practice that ensures the AI's output is always structured, reliable, and can be directly used to populate the UI without risky parsing of natural language. A systemInstruction primes the model to act as a disaster response expert, ensuring the tone and content are appropriate.
Text-to-Image Generation (imagen-4.0-generate-001): To provide a powerful visual context of the damage, one of the fields in the structured JSON response from Gemini is a beforeImagePrompt. This prompt, created by the analysis model, is then fed directly into the imagen-4.0-generate-001 model to generate a realistic photo of the location before the disaster. This creates a seamless AI workflow from analysis to visualization.
Conversational AI (Gemini Chat API): For personalized support, I used the Gemini Chat API (ai.chats.create). The chat session is initialized with the context from the initial damage assessment. This makes the chatbot instantly aware of the user's situation. All responses from the chatbot are streamed to the UI, creating a dynamic, real-time conversational experience and showing the user information as soon as it's available.

4️⃣ Multimodal Features

The app is built on a foundation of multimodality, which dramatically enhances its utility and user experience in a crisis scenario.

Image and Text Fusion for Superior Understanding: The app's primary input is multimodal. By analyzing images and text together, the AI gains a much deeper, more contextual understanding than it could from either modality alone. For example, the AI can correlate a user's text ("I hear cracking sounds") with a visual of a hairline fracture in a wall, leading to a more accurate severity assessment. This fusion is key to the app's effectiveness.
Analysis-to-Visualization Workflow: The app doesn't just understand multimodal input; it generates multimodal output. The "Before Disaster" visualization is a prime example. The AI first sees and reads about a damaged scene, then it imagines and creates an image of that same scene in an undamaged state. This powerful feature gives users an immediate and visceral understanding of the extent of the damage.
Visually-Grounded Conversation: The follow-up chatbot is more than a simple Q&A bot. Because its context is derived from the initial visual analysis, its answers are grounded in the user's actual environment. If a user asks, "Is that crack dangerous?", the AI's response is informed by the picture of the crack the user provided, making the guidance highly relevant and personal.

5️⃣ Real-World Problem Solving

This applet goes beyond basic AI demos to address a critical real-world challenge: immediate disaster response assessment. In emergency situations, traditional response systems are often overwhelmed, leaving individuals without crucial safety information. The Disaster Response Assistant fills this gap by:

Democratizing Expert Assessment: Transforms any smartphone into a structural damage assessment tool
Reducing Response Time: Provides instant analysis instead of waiting hours for professional assessment
Enabling Informed Decision-Making: Gives users concrete, prioritized actions based on their specific situation
Supporting Emergency Services: Generates structured damage reports that can be shared with first responders

Creative Multimodal Applications

Cross-Modal Analysis: Combines visual damage assessment with textual context (sounds, smells, environmental factors) for comprehensive understanding
Temporal Visualization: Uses AI to reconstruct "before disaster" scenes, helping users understand damage extent
Context-Aware Conversation: Chatbot responses are grounded in the user's actual visual environment
Progressive Disclosure: Information is revealed in stages (assessment → visualization → conversation) to prevent cognitive overload during crisis

6️⃣ Application Features & Best Practices

Key Features Checklist

Batch Image Upload: Users can upload multiple photos for a comprehensive review.
Textual Context: A textarea allows users to add crucial context to the visual data.
AI Damage Assessment: Structured JSON output provides a detailed assessment.
Severity Level Classification: Damage is categorized as Low, Medium, High, or Critical.
Actionable Safety Guidance: A clear, prioritized list of next steps for user safety.
AI "Before Disaster" Visualization: A generated image shows the scene pre-disaster.
Interactive Chatbot: A streaming, context-aware chat for follow-up questions.
Downloadable Reports: Users can save the analysis and "before" image for offline use.

Engineering Best Practices

Structured AI Output: Used responseSchema (JSON Mode) for robust, predictable, and error-free communication between the AI and the frontend.
Clear State Management: Leveraged React's state management to handle loading, error, progress, and result states, providing immediate and clear UI feedback.
Component-Based Architecture: The UI is built with modular, reusable React components, promoting clean code and maintainability.
Asynchronous Flow Control: All API calls are handled with async/await and enclosed in try...catch blocks for graceful error handling.
User-Centric Loading: Loading spinners and dynamic progress messages are displayed during API calls to manage user expectations.
Streaming for UX: Chatbot responses are streamed to the UI to provide a responsive, real-time feel.
Accessibility: Key interactive elements include aria-label attributes to ensure usability for users with screen readers.
Responsive Design: The UI is fully responsive and accessible across devices, from mobile phones to desktops, using Tailwind CSS.
Code Organization: Logic is separated into services (geminiService), utilities (fileUtils, downloadUtils), components, and types for a clean and scalable codebase.

7️⃣ Development & Deployment Details

Technology Stack

Frontend: React 18 + TypeScript + Tailwind CSS
Backend: Node.js + Express.js
AI Services: Google AI Studio APIs (Gemini 2.5 Flash, Imagen 4.0, Chat API)
Deployment: Google Cloud Run with Docker containerization
Build Tools: Vite for frontend bundling, Docker for containerization

API Integration Patterns

// Multimodal analysis with structured output
const analysis = await gemini.generateContent({
  model: 'gemini-2.5-flash',
  contents: [{ parts: [imageData, textPrompt] }],
  generationConfig: {
    responseMimeType: 'application/json',
    responseSchema: damageAssessmentSchema
  }
});

// Streaming chat responses
const chatStream = await gemini.streamGenerateContent({
  model: 'gemini-2.5-flash',
  contents: conversationHistory
});

Cloud Run Configuration

Memory: 2GB for handling image processing
CPU: 2 vCPU for concurrent request handling
Concurrency: 100 requests per instance
Timeout: 300 seconds for complex AI operations
Environment Variables: Secure API key management

Performance Optimizations

Image Compression: Client-side image optimization before upload
Lazy Loading: Progressive component loading for faster initial render
Caching: Response caching for repeated analysis requests
Error Boundaries: Graceful degradation for API failures

8️⃣ Challenge Compliance

This applet fully meets all requirements of the "Build and Deploy a Multimodal Applet" challenge:

Gemini 2.5 Flash for multimodal image and text understanding
Imagen 4.0 for AI-generated "before disaster" visualizations
Gemini Chat API for context-aware conversational support

9️⃣ Future Enhancements

Audio Analysis: Integration with Gemini's audio understanding for sound-based damage assessment
Video Processing: Real-time video analysis for dynamic damage evaluation
Offline Capabilities: Progressive Web App features for areas with limited connectivity
Multi-language Support: Localization for global disaster response
Integration APIs: Webhooks for emergency services and insurance companies

🔟 📚 Lessons Learned

Building RapidRelief Disaster Response Assistant — Smart Emergency Response Assistant was a powerful learning experience that combined technical exploration, UX thinking, and real-world problem-solving. Here are the key takeaways from this project:

🤖 The Power of Multimodal AI: Combining text + image understanding through Google AI Studio enabled richer context-aware responses, proving how multimodal inputs can unlock more useful and actionable insights for users in high-stress situations.
⚡ Rapid Prototyping Matters: Using AI-assisted development drastically reduced build time — from generating frontend copy to suggesting API workflows — allowing me to iterate quickly and focus on user experience instead of boilerplate code.
🎨 Design for Calm, Not Just Functionality: Emergency apps must feel clear, calm, and reassuring. Small details like color choices, microcopy, and step-by-step instructions can lower user anxiety in a crisis.
🌍 Localization is Critical: Disasters are global — ensuring the app can adapt language, emergency contacts, and recommendations to the user’s region is crucial for real-world usability.
📊 Structured Guidance Over Raw Data: Users don’t need a technical report — they need actionable next steps. The biggest insight was to transform complex AI outputs into a prioritized checklist that users can follow under stress.
🔄 Iteration Improves Safety: Testing multiple prompts, refining risk categories, and validating AI responses taught me that iterative improvement is essential to build trust and reliability.
🤝 AI as a Companion, Not a Replacement: The project reinforced that AI is best used as a supportive guide — not a decision-maker — empowering users while still encouraging them to seek professional help when needed.

⚠️ Disclaimer

RapidRelief Disaster Response Assistant AI is an informational and support tool designed to assist users during emergency situations by providing AI-generated suggestions and general safety guidance.

🚨 Not a Substitute for Emergency Services: This app does not replace professional medical advice, official disaster management protocols, or emergency services.
📉 Accuracy Limitation: While the AI strives to provide relevant and helpful insights, it may not always accurately assess the severity of a situation or suggest the most appropriate action.
👤 User Responsibility: Users are responsible for making their own safety decisions and are encouraged to contact local authorities, emergency responders (such as 911), or qualified professionals when in danger.
❌ No Liability: The developers, contributors, and providers of this app are not liable for any injury, loss, or damage that may result from the use or misuse of the information provided.

✅ Conclusion

Building RapidRelief Disaster Response Assistant — Smart Emergency Response Assistant was more than a technical challenge; it was an opportunity to explore how AI can save lives by delivering clarity during chaos. This project demonstrated the power of Google AI Studio in enabling multimodal intelligence — taking images, text, and context to generate actionable guidance that anyone can follow, even in high-stress situations.

By focusing on speed, clarity, and accessibility, RapidRelief empowers individuals to make safer choices, share critical information with first responders, and reduce panic when every second matters.

This project proves that AI doesn’t just have to be futuristic or experimental — it can be practical, approachable, and human-centered. My hope is that this work inspires other developers, students, and humanitarian technologists to explore multimodal AI for real-world impact, building solutions that genuinely protect and empower communities in times of need.

References Used

🚀 Try RapidRelief AI Today!

Stay safe, stay informed, and take control during disasters.

👉 Launch the App Powered by Google AI Studio

I acknowledge my colleague and mentor for the voice over on the demo videos.

Built with ❤️ for Dev.to — powered by Google AI Studio

Runner H Exposed the Truth: Your 100K Salary Isn’t All What You Deserve by Law ⚖️

Shan F — Mon, 07 Jul 2025 05:20:16 +0000

This is a submission for the Runner H "AI Agent Prompting" Challenge

Demystifying PF & ETF deductions with RunnerH prompt engineering—no code, just powerful prompts.

Context – Using Runner H's Agent's Reasoning Power to Demystify Employee Benefits in Sri Lankan Legal Context

Legal calculations—especially those involving Sri Lankan employment law — can feel like wading through quicksand. 🤯

Understanding EPF/ETF contributions, take‑home salaries, and compliance requirements usually means parsing dense regulations and crunching numbers by hand.

This Runner H submission shows how AI agents can reason over legal documents and answer complex labor‑law questions with structured prompts—zero code required.

LegalReasonrAgent: a prompt‑based legal assistant that explains statutory salary deductions and employer contributions under Sri Lankan law in plain, actionable language with the power of Runner H AI Agent.

1️⃣ What I Built using Runner H

LegalReasonrAgent is a structured‑prompt AI built on Runner H.

It ingests legal documents (e.g., the Employee Provident Fund Act & Employee Trust Fund Act) as context and tackles a realistic scenario:

🧑‍💻 Employee: Software Engineer
🏢 Company: Private sector (Sri Lanka)
💰 Monthly Gross Salary: LKR 100,000

The agent then calculates:

Employee + Employer EPF/ETF contributions
Annual fund accumulation
Take‑home salary

No code, no spreadsheets—just **context + prompts + RunnerH magic

2️⃣ Demo - 13 Minutes Complete Step-by-Step Process [Must Watch}

3️⃣ How I Used Runner H

Building LegalReasonrAgent wasn’t about writing code — it was about engineering clarity through conversation.

Here’s exactly how I used **Runner H **to reason through Sri Lankan labor law with nothing but structured prompts and legal documents:

✍️ Step 1: Upload the Legal Context

I started by uploading publicly available legal documents related to Sri Lanka’s EPF (Employees’ Provident Fund Act) and ETF (Employees’ Trust Fund Act). This included official contribution rules, percentages, and statutory obligations for employers and employees.

✍️ Step 2: Design a Structured, Role-Playing Prompt

Instead of issuing vague instructions, I carefully crafted a persona-based prompt:

You are LegalReasonrAgent – a legal reasoning AI assistant trained on Sri Lankan labor laws and payroll regulations.

By referring to the attached legal documents and based on legal reasoning, please answer the following questions in a clear, step‑by‑step manner.

╔════════════ EMPLOYEE DETAILS ════════════╗
• Role: Software Engineer
• Company: ABC XYZ (Pvt) Ltd, Sri Lanka
• Monthly Gross Salary: LKR 100,000

╔════════════ QUESTIONS TO ANSWER ═════════╗
1) What is his monthly gross salary?
2) What is his monthly take‑home salary after EPF deduction?
3) What is the monthly EPF contribution by the employer?
4) What is the monthly ETF contribution by the employer?
5) How much fund will be added to his EPF account annually?
6) How much fund will be added to his ETF account annually?

Please include applicable contribution rates and use official Sri Lankan EPF/ETF contribution rules as reference.

⚠️ Disclaimer: AI‑generated outputs may not replace professional legal advice. Always verify with a legal practitioner or labor consultant before taking action.

This framing helped the AI act like a legal consultant, interpreting context and returning step-by-step answers based on factual obligations.

✍️ Step 3: Frame Questions Logically

I included real-world input variables—job title, salary amount, and company type—and asked targeted, logical questions around:

Take-home salary after EPF
Employer's EPF + ETF contribution
Annual fund growth for the employee

This made the prompt reusable and modular.

✍️ Step 4: Run the Prompt in Runner H

With context + questions in place, I launched the workflow in Runner H’s no-code environment. The multi-agent engine parsed the laws and applied arithmetic + reasoning to deliver precise outputs—including formulas, figures, and interpretations.

✍️ Step 5: Output by Runner H Agent

To calculate the requested information based on the provided legal documents, let's deduct the relevant percentages from the employee's monthly salary and determine both the Employee Provident Fund (EPF) and Employees' Trust Fund (ETF) contributions as well as their effect on the take-home salary:

His monthly salary:

LKR 100,000
His monthly take-home salary after EPF Deduction:

The employee contributes 8% of their salary to the EPF.
EPF employee contribution = ( 100,000 \times 0.08 = 8,000 ) LKR
Monthly take-home salary = ( 100,000 - 8,000 = 92,000 ) LKR
Amount of EPF Contribution by the Employer:

The employer contributes 12% of the employee's salary to the EPF.
EPF employer contribution = ( 100,000 \times 0.12 = 12,000 ) LKR
Amount of ETF Contribution by the Employer:

The employer contributes 3% of the employee's salary to the ETF.
ETF contribution = ( 100,000 \times 0.03 = 3,000 ) LKR
How much fund will be added to his EPF Account annually:

Total annual EPF contribution (employee + employer) = ( (8,000 + 12,000) \times 12 )
Annual EPF contribution = 240,000 LKR
How much fund will be added to his ETF Account annually:

Annual ETF contribution = ( 3,000 \times 12 )
Annual ETF contribution = 36,000 LKR
Disclaimer: This analysis is based on the current understanding of the legal documents and percentages mentioned within them. It is highly recommended to consult a legal practitioner or financial advisor for any actions based on these calculations, as an AI-based interpretation may not encompass all the complexities of legal requirements.

✅ Step 6: Review and Verify

I double-checked the generated output against trusted HR resources and official EPF/ETF guidelines to ensure accuracy and compliance.

Shockingly...

the Output is perfectly align with the Manual Finding and the Legal Provisions

⚠️ Note: Check the above Demo video to understand how the provisions apply and then the output generated by Runner H's reasoning

By combining intent-driven prompt design with Runner H’s structured agent execution, I transformed a traditionally manual, error-prone task into an automated legal reasoning assistant.

No API calls. No spreadsheets. No legal team.

Just Runner H + one powerful prompt = Instant legal insight ⚖️✨

4️⃣ Use Case & Real-World Impact – Who Benefits

When building LegalReasoningAgent with Runner H, my goal wasn’t just to create another AI prompt. It was to solve a real, recurring problem faced by millions of working professionals across the World.

Here’s how and who this AI Agent can actually serve in the real world

🧑‍💼 1. Employees

Most employees receive a salary slip, but don’t fully understand where their money goes—especially when it comes to EPF/ETF deductions and fund contributions.

With LegalReasonAgent, they can:

Understand exactly how much goes to EPF and ETF monthly and annually
Know their actual take-home pay after mandatory deductions
Be financially literate and plan for retirement or future withdrawals
Verify if their employer is compliant with labor law obligations

📊 2. HR Managers & Payroll Officers

For HR teams, especially in SMEs and startups, salary structuring and compliance can be overwhelming. Many don’t have internal legal staff or automated tools.

This tool helps them

Cross-check payroll outputs with legal expectations
Simplify salary breakdowns for onboarding and offer letters
Ensure full EPF/ETF compliance and avoid regulatory penalties
Create better transparency with employees during salary reviews

🧠 3. AI Builders & Prompt Engineers

LegalReasonAgent is a showcase of how structured prompt engineering can simulate legal reasoning — a field often seen as too nuanced for LLMs but as per the experiment Runner H outperforms.

For AI builders, this use case highlights:

The power of document-anchored, persona-driven prompts
How to handle domain-specific logic without APIs or custom code
A reusable prompt design that can be applied to other jurisdictions or legal systems
The opportunity to build no-code compliance tools using RunnerH

⚖️ 4. Legal Educators & Law Students

Understanding how laws are applied in practice can be difficult for students and early-career lawyers.

This use case provides:

A practical, AI-assisted teaching tool
A method for interactive legal case simulations
A way to automate routine legal logic and focus on higher-order interpretation
An intro into how AI can support legal analysis, not replace it

🏢 5. Startups, Freelancers & SME Founders

Founders and freelancers often don’t have HR consultants or payroll software. Yet they are legally bound to pay EPF/ETF for their employees.

This AI agent gives them:

A quick, trustworthy breakdown of what they owe
An automated advisory that replaces hours of manual research
Peace of mind that their company is staying within legal limits

🚀 The Broader Impact

Ultimately, LegalReasonAgent isn’t just about calculations.
It’s about democratizing legal knowledge, empowering employees, and enabling businesses to be smarter, faster, and fairer—using nothing but structured prompts and AI reasoning.

From 100K salary confusion to transparent, AI-backed clarity - this is legal tech made practical for everyday users.

Social Love

👉 On Platform X
// Detect dark theme var iframe = document.getElementById('tweet-1942091460490506273-767'); if (document.body.className.includes('dark-theme')) { iframe.src = "https://platform.twitter.com/embed/Tweet.html?id=1942091460490506273&theme=dark" }

👉 On Youtube

Credits: I owe credits to my team members @oliviaaaron and external legal practitioner in proofreading our understanding with regard to the application of law and for the voice by my team member.

💬 Have a salary breakdown you want verified? Drop a comment or remix the prompt for your country. Let’s make labor law understandable—one prompt at a time.

⚠️⚠️⚠️ Disclaimer: AI‑generated outputs may not replace professional legal advice. Always verify with a legal practitioner or labor consultant before taking action.