DEV Community: Abhijith Sreekumar

HIA — Health Insight Agent: Building an AI-Powered Medical Report Analysis System

Abhijith Sreekumar — Thu, 24 Sep 2026 10:12:46 +0000

Built by Abhijith Sreekumar

I built HIA (Health Insight Agent), an AI-powered application designed to help users understand information contained in medical reports through an interactive interface.

The idea behind HIA was to explore how AI, document processing, and conversational interfaces can be combined to make medical report information easier to understand.

The project is built with a separate React frontend and Node.js backend, with the frontend deployed through Vercel.

🩺 What is HIA?

Medical reports can contain a large amount of technical information that isn't always easy to interpret.

HIA provides an interface where users can interact with their medical report and obtain AI-generated insights based on the information provided.

The system is designed around three main ideas:

Medical report processing
AI-powered analysis
Interactive follow-up conversations

Instead of treating a medical report as a static document, HIA turns it into an interactive source of information that users can explore through an AI-powered interface.

🧠 How the System Works

The overall architecture is:

Medical Report
↓
React Frontend
↓
Node.js / Express Backend
↓
Report Processing
↓
AI Analysis
↓
Structured Health Insights
↓
Interactive User Experience

The frontend and backend are maintained as separate repositories, allowing the user interface and server-side functionality to be developed independently.

📄 Medical Report Processing

One of the main goals of HIA is to work with information contained in medical reports.

The system is designed around processing uploaded report information and using it as context for the AI analysis.

This allows the application to move from:

Static Medical Report

to:

Medical Report
↓
Extract Information
↓
AI Processing
↓
Health Insights
↓
Follow-up Questions

The backend repository is structured with dedicated routes, services, models, middleware, and configuration, providing a modular foundation for handling the application's server-side operations.

💬 Interactive AI Experience

A major part of HIA is the ability to interact with the generated insights.

Instead of receiving a single static response, the application is designed around an interactive experience where users can explore information and ask additional questions.

This makes the system more conversational and allows the report to become the starting point for further exploration.

⚛️ Frontend

The frontend is built using React with Vite.

The repository contains the application source under src, along with the public assets and standard Vite configuration.

The deployed application is available at:

https://healthinsightagent.vercel.app/

The frontend focuses on providing a clean interface for interacting with the report analysis workflow.

⚙️ Backend

The backend is built with JavaScript and is maintained separately from the frontend.

Its repository contains:

config/
middleware/
models/
routes/
services/
server.js

This structure separates different responsibilities within the backend and provides a foundation for extending the application's APIs and AI-related functionality.

🛠️ Tech Stack
Frontend
React
Vite
JavaScript
CSS
Tailwind CSS
Backend
Node.js
Express.js
JavaScript
AI & Document Processing
AI-powered medical report analysis
Medical report data processing
Conversational AI interaction
Deployment
Vercel
🔗 Project Repositories
Frontend

https://github.com/abhijithabhi01/HIA-Health-Insight-Agent--Frontend

Backend

https://github.com/abhijithabhi01/HIA-Health-Insight-Agent--backend

Live Application

https://healthinsightagent.vercel.app/

💡 Why I Built HIA

I wanted to explore how AI can be applied to a real-world information-heavy workflow.

Healthcare documents are a good example of information that can be difficult to understand because they often contain technical terminology, measurements, and structured medical data.

The goal wasn't to replace doctors or provide medical diagnoses.

Instead, the project explores how software can help users interact with and understand information contained in their reports through an AI-powered interface.

🔐 Important Note

HIA is a software project for exploring AI-assisted medical report understanding.

AI-generated information should not be treated as a medical diagnosis or a replacement for a qualified healthcare professional.

Users should consult an appropriate medical professional for diagnosis, treatment, and medical decisions.

🚀 What I Learned

Building HIA gave me hands-on experience with:

AI-powered application development
React frontend development
Node.js and Express backend development
API-based architecture
Medical document processing
AI integration
Frontend/backend separation
Building interactive AI experiences
Deploying web applications

One of the biggest lessons was that building an AI application is not only about the AI model.

The surrounding system matters just as much:

User Interface
↓
Backend
↓
Data Processing
↓
AI Layer
↓
Structured Response
↓
User Experience

The quality of the final application depends on how all these components work together.

🔮 What's Next?

Some areas I'd like to explore further include:

More advanced document understanding
Improved medical terminology explanations
Better conversational context
More structured report visualization
Additional document formats
Improved AI response validation
More robust security and privacy controls

HIA is part of my broader interest in building AI-powered applications that solve practical problems rather than simply demonstrating an AI model.

👨‍💻 About the Developer

Abhijith Sreekumar is an AI & Full-Stack Developer interested in building AI applications, agentic systems, automation, and modern web applications.

More projects and work:

Portfolio:
https://abhijithsreekumar.vercel.app/

GitHub:
https://github.com/abhijithabhi01

LinkedIn:
https://www.linkedin.com/in/abhijithsreekumar-dev/

HIA — Health Insight Agent
Exploring how AI can make complex medical report information easier to interact with and understand.

AbhijithSreekumar #HIA #HealthInsightAgent #ArtificialIntelligence #AI #GenerativeAI #React #NodeJS #ExpressJS #JavaScript #FullStackDevelopment #AIEngineering #HealthcareAI #WebDevelopment #MachineLearning

How I Built an Autonomous Account Research Agent Using Agentic AI

Abhijith Sreekumar — Sat, 08 Aug 2026 22:05:20 +0000

🚀 ARA — Account Research Agent

By Abhijith Sreekumar

I built ARA (Account Research Agent), an agentic AI system designed to automate B2B account research.

When researching a company, a lot of time can be spent manually checking its website, recent news, hiring activity, financial filings, LinkedIn signals, public registries, tender portals, and industry directories.

ARA brings this research into a single automated workflow.

🔍 What ARA does

The user provides:

Company Name
Website URL

ARA then runs 8 research tools across different data sources:

Company Website
News Coverage
Job Openings
Financial Filings
LinkedIn Signals
Company Registry
Tender Portals
Industry Directories

Each source has its own tool function, and the results are normalized into a common structure before being processed by the AI.

🧠 Architecture

Company Name + Website
          ↓
     Flask Backend
          ↓
    Google ADK Agent
          ↓
     8 Research Tools
          ↓
    Data Validation
          ↓
   Data Normalization
          ↓
    Gemini 2.5 Flash
          ↓
 Structured Research Brief

The project uses a single-agent orchestration pattern with Google ADK.

The idea is to separate the research process into clear stages:

Collect → Validate → Normalize → Synthesize

Instead of simply asking an LLM to generate information, the agent first gathers information through dedicated tools and then uses Gemini to synthesize the results.

📊 What the final report contains

ARA generates a structured account intelligence brief covering:

1. Company Summary

An overview of the researched company.

2. Current Initiatives

Signals about the company's current activities and initiatives.

3. Expansion Signals

Potential indicators of growth and expansion.

4. Hiring Signals

Hiring activity that can reveal areas of investment.

5. Digital Transformation Signals

Technology and digital transformation-related activity.

6. Possible Business Pain Points

Potential business challenges identified from the collected signals.

🛠️ Tech Stack

Backend

Python
Flask

AI & Agent

Google ADK
Gemini 2.5 Flash
Vertex AI

Data Collection

BeautifulSoup
External APIs
Web research tools

Frontend

HTML5
CSS3
Vanilla JavaScript

🌐 Data Sources

The implementation currently maps different research categories to different tools and APIs:

Research Area	Tool / API
Company Website	BeautifulSoup
News	Serper API + Tavily
Job Openings	Greenhouse + JSearch
Annual Reports	FMP + SEC
LinkedIn Signals	Serper API / Tavily
Public Registries	Scrapfly + Explorium
Tender Portals	Apify
Industry Directories	Scrapfly

💡 Why I built it

I wanted to explore how AI agents can be used for real workflows, rather than only building another chatbot.

The concept is:

Traditional AI

User → LLM → Answer

versus:

Agentic AI

User
 ↓
Agent
 ↓
Tools
 ↓
External Data
 ↓
Validation
 ↓
Structured Context
 ↓
LLM
 ↓
Actionable Intelligence

ARA is an experiment in turning fragmented public information into a structured research workflow that can help sales and go-to-market teams understand an account more efficiently.

🚀 What's next?

I'm looking at expanding ARA with:

Account scoring
Historical research tracking
Competitor intelligence
Decision-maker research
Source confidence scoring
Automated opportunity detection
More autonomous research workflows
Multi-agent research architecture

Building ARA has been a great learning experience around Agentic AI, Google ADK, LLM orchestration, web data collection, API integration, data normalization, and structured AI outputs.

The biggest takeaway:

An AI agent becomes much more useful when it can perform a workflow instead of simply answering a question.

🔗 Project

Portfolio:
https://abhijithsreekumar.vercel.app/

Built by:
Abhijith Sreekumar

AbhijithSreekumar #ARA #AccountResearchAgent #AgenticAI #AI #GoogleADK #Gemini #VertexAI #Python #FullStackDevelopment #AIEngineering #Automation #WebDevelopment #B2B #BuildInPublic