arrow_back Work
chevron_left ALL_WORK
Client Project / Backend Developer

AI Admission Counselor.

An AI-powered admission counseling platform that automates personalized engineering-stream recommendations — processing student academic data, generating adaptive assessment questions, and delivering stream recommendations as polished PDF reports.

FastAPI Python RAG Pipeline OpenAI GPT-4 MySQL Twig JWT (RSA256)
lock Code: Private (client IP)
RAG
Pipeline over student + academic context
Streaming
Real-time report generation UX
MD → PDF
Automated report pipeline
RSA256
JWT-secured versioned REST API

How It Works

Architecture & Key Decisions

Why It Matters

bolt

Production LLM integration in a real client product

This wasn't a demo — it was a shipped product replacing a manual counseling workflow. It required real prompt engineering, a retrieval pipeline to keep recommendations grounded in each student's data, streaming responses for UX, and structured report generation reliable enough to hand to families making a decision.

Trade-offs & What v2 Adds

Why synchronous OpenAI calls?

Simpler implementation with acceptable latency for the use case.

Why file-based key storage?

Acceptable for the MVP versus standing up a full KMS.

What v2 would add

Redis caching, an async queue (RabbitMQ/SQS) for OpenAI calls, S3 for uploads, and rate limiting.

Want the full walkthrough?

Happy to walk through the RAG pipeline, prompt design, and streaming report generation in detail.