🏆 View Winners 🌟 View Sponsors 👥 All Participants

Shubham Ashok Murar

Participant

Targetini - AI-Powered Recruiting Agents

Votes1

Score1

🧠Community0×5= 0

🌐Public1×1= 1

Individual

December 5, 2025 at 11:59 PM

Project Demo

Submission Details

hear-about-us: Linkedin

name: Shubham Ashok Murar

College / University Name: Gurunanak Institute of Technology 143

linkedIn-profile: https://www.linkedin.com/in/shubham-murar-95a472235/

Project Title: Targetini - AI-Powered Recruiting Agents

Describe what your project does?: Targetini is an AI-powered recruiting assistant that transforms professional search from keyword guessing to natural conversation. Built with LangChain and LangGraph, it features dual intelligent agents that understand what you're actually looking for when you say things like "Find me senior Python developers with startup experience in San Francisco." The system goes beyond basic search by implementing multi-agent reasoning: a Conversational Agent handles natural language interactions using LangChain's ReAct pattern with specialized tools, while a Learning Agent adapts to user preferences through Bayesian updating, getting smarter with each interaction. Powered by LangGraph's state machine orchestration, it executes 5-step reasoning workflows: intent understanding → strategy planning → search execution → result evaluation → response preparation. Why it matters: Traditional recruiting tools overwhelm users with irrelevant results. Targetini cuts hours of work down to minutes by understanding context, extracting skills from natural language, and learning your hiring style. It demonstrates real agentic behavior - not just responding, but reasoning, planning tool usage, and adapting over time. This showcases how LangChain/LangGraph can build production-ready AI systems that solve real-world problems through intelligent orchestration, memory, and adaptive learning.

Share a 3–5 minute HD demo video: https://drive.google.com/file/d/1KI2JM8Gs6lAjG8gB6UDjYCYgAf4kCqW-/view?usp=sharing

Hosted Project Link (if any): NO.

GitHub Repository (if any): https://github.com/Shubham-murar/Targetini

artifacts/ supporting material: https://drive.google.com/drive/folders/1SkZjGpcj4IbR8RLxIJUw6RumwYLYJPUb?usp=sharing

Is this project your original and proprietary work?: Yes

Does your project include any private, sensitive, or restricted code or content?: No

Do you give us (AI Demos & partners) permission to feature your work on our website and share it with our community (with full credit)?: Yes

Do you consent to us showcasing your name/profile on our social media platforms and YouTube: Yes

Are you open to freelance, internship, or collaborative opportunities based on this project?: Yes, I’m interested

Comments (0)

Explore More

All Participants Hackathon Details

Get In Touch

Connect with Shubham Ashok Murar to learn more about their project.

LinkedIn Profile

Featured

FutureSmart Agent

A complete AI Agent system for real use cases. RAG, NL2SQL, API actions, multi-agent logic — everything in one place.

Targetini is an AI-powered recruiting assistant that transforms professional search from keyword guessing to natural conversation. Built with LangChain and LangGraph, it features dual intelligent agents that understand what you're actually looking for when you say things like "Find me senior Python developers with startup experience in San Francisco." The system goes beyond basic search by implementing multi-agent reasoning: a Conversational Agent handles natural language interactions using LangChain's ReAct pattern with specialized tools, while a Learning Agent adapts to user preferences through Bayesian updating, getting smarter with each interaction. Powered by LangGraph's state machine orchestration, it executes 5-step reasoning workflows: intent understanding → strategy planning → search execution → result evaluation → response preparation. Why it matters: Traditional recruiting tools overwhelm users with irrelevant results. Targetini cuts hours of work down to minutes by understanding context, extracting skills from natural language, and learning your hiring style. It demonstrates real agentic behavior - not just responding, but reasoning, planning tool usage, and adapting over time. This showcases how LangChain/LangGraph can build production-ready AI systems that solve real-world problems through intelligent orchestration, memory, and adaptive learning.