Shadab Jamadar Logo
PRODUCTS

Things I've Built.

AI products, systems, and experiments designed to solve real-world problems.

View Journey
EDUCATIONAL AILive

Curio.

AI Co-Teacher for Modern Classrooms

An autonomous AI teaching assistant that listens, understands, and generates educational aids in real-time during lectures. It captures audio input, extracts semantic structures, and dynamically serves visual maps, quizzes, and summaries to students.

LangGraphGeminiRAGFastAPIReactPostgreSQL
curio-co-teacher.ai/dashboard
Voicestream Live
AI

Your AI Co-Teacher, in Every Lesson.

Listening to: "Machine Learning Basics - Decision Trees and Entropy..."

Mind Map

Visual concept map linking Entropy with Information Gain.

H
E
IG
Quiz

1. What is entropy used to measure in decision trees?

A. Calculation speed
B. Impurity of data
Summary
  • Information gain splits data
  • Leaf nodes hold outputs
  • Pruning prevents overfit
Updated 3s ago
HEALTHCARE AILive

AI-First CRM HCP Module.

Intelligent CRM for Healthcare Professionals

An intelligent customer relationship management system designed for medical representatives. It leverages Generative AI to streamline logging, summarizing, and tracking HCP interactions.

FastAPIReactPostgreSQLGroqRedux
AI-First CRM HCP Module Mockup
HIRING AIBeta

AI Interviewer.

Intelligent Interviews. Better Hiring.

An AI-powered interviewer that conducts structured, adaptive, and unbiased interviews at scale. It responds to candidate answers dynamically, asks intelligent follow-ups, profiles coding competencies, and grades responses based on rubric constraints.

LangChainOpenAIPostgreSQLFastAPINext.js
interviewer.io/session/39f0a2
24:36
Question 3 of 5DSA / Data Structures

Explain how a binary search tree works? Implement a node struct and search algorithm.

// TypeScript Binary Search Tree
class BSTNode {
  value: number;
  left: BSTNode | null = null;
  right: BSTNode | null = null;
}
Type your explanation here and explain edge cases...
AI Engineering & ObservabilityProduction

LLM Evaluation Pipeline.

Deterministic LLM Observability & Evaluation

A deterministic evaluation pipeline measuring relevance, completeness, hallucination, and latency on 150+ queries. Features modular loader-metrics-aggregator workflows, embedding caching, and local inference for 25% faster batch executions.

PythonSentence TransformersRedisDockerFastAPI
Mockup unavailable
TRADING SYSTEMSProduction

Filoos - Unified Python SDK.

Unified Python SDK for Programmatic Trading

A unified, type-safe Python SDK for programmatic trading on Indian stock exchanges. It abstracts broker-specific APIs behind a clean, domain-driven interface.

PythonSQLiteDataclassesType Hints
main.py - filoos
from filoos.brokers import Zerodha
from filoos.instruments import Equity
from filoos.constants import TransactionType

# Initialize broker safely without leaking API strings
broker = Zerodha(api_key, access_token)

# Place order using strict Domain Objects
order_res = broker.place_order(
Equity("RELIANCE"),
TransactionType.BUY,
quantity=10
)

print(f"Order placed: {order_res.order_id}")
TERMINAL
$ python main.py
[INFO] SQLite Resolver: Loaded 112,450 instruments
[INFO] Resolving token for Equity(symbol='RELIANCE') -> 738561
Order placed: 24012500194833
HEALTHCARE AIResearch

Healthcare RAG.

Ask. Retrieve. Understand.

A domain-specific RAG system for healthcare professionals to query medical databases and get accurate, annotated, and fully cited answers from complex clinical documentation.

Llama 3RAGQdrantFastAPINext.js
HHealthcare RAG Dashboard
HIPAA Compliant

How can I help you today?

Ask about diagnosis metrics, clinical guidelines or paper references.

Drug Interactions with AspirinICD-10 code for diabetesTreatment for hypertension
TRADING SYSTEMSProduction

MT5 Infrastructure.

High-Frequency Bridge for Quantitative Trading

A low-latency infrastructure connecting quantitative Python trading pipelines to MetaTrader 5 terminals, featuring memory-mapped IPC, automatic order routing, and failover management.

C++PythonMT5 APIRedisDocker
MT5 Core Bridge Daemon
IPC Mapped: OK
LATENCY800μs
SLIPPAGE0.01%
UPTIME99.99%
TICK STATS10M+
// Execution Logs - Tick Buffer Stream
[08:00:00.001] [IPC] Shared memory connected.
[08:00:00.800] [MT5] EURUSD tick: Buy 1.08450 (Latency 800μs)
[08:00:01.200] [MT5] GBPUSD tick: Sell 1.26840 (Latency 780μs)
[08:00:02.110] [EXEC] Order filled: 0.1 lots Buy EURUSD
[08:00:02.112] [EXEC] Slippage calculation: 0.00001 (0.01%)

Every product is built with a focus on solving real problems.

Interested in engineering collaboration, specialized quantitative models, or custom educational AI solutions? Let's connect.

Let's Connect