I’m Himanshu. I build AI agents, intelligent applications, and the infrastructure that takes them from idea to production.
LangGraph connects reasoning, tools, and context into configurable agent workflows.
An illustrative workflow, inspired by my engineering work.
Your terminal sessions, remembered. A native macOS menu bar app that captures sessions and replays them into your preferred terminal.
A conversation with your CSV. Turn tabular data into searchable knowledge with vector embeddings and contextual, natural-language Q&A.
A system-design learning platform with guided modules, interactive simulations, quizzes, and real-world architecture case studies.
Make the unusual visible. A simulated data stream with predictive anomaly detection, interactive controls, and exportable results.
Coding agents that live in the cloud. A durable workflow drives an isolated sandbox VM through tools, so the agent and the machine it works on stay separate.
FORK Built on vercel-labs/open-agents (MIT). My fork adds a hardened MongoDB connector to the Python agent.
A document as a tree, not a blob. Vision calls infer section boundaries and describe every node, so an agent can walk the structure instead of re-reading the page.
INTERNAL Built at OnFinance AI. No public repository.
Showing all 6 projects.
Building AI agents for risk, audit, and compliance in financial services.
RLHF preference ranking and pairwise comparison of model responses across coding and reasoning tasks, with evidence-based justifications for every rating.
Evaluated and benchmarked multi-model LLM outputs across STEM and non-STEM domains for factual accuracy, reasoning, and response quality.
Built a GenAI knowledge bot for developers, using retrieval-augmented generation over internal documentation and codebases to return source-grounded answers and code references.
Research internship at IIT Kharagpur, alongside my M.Sc. in Economics.
I studied Economics at IIT Kharagpur. Today, I work at the intersection of business and AI: understanding the problem, designing the system, and getting it into production.
I enjoy the whole journey, from raw data and model behaviour to agent orchestration and the infrastructure underneath. The goal stays the same: build something useful that works in the real world.
Photography and filmmaking. Former Head of Photography and Advisor at IIT Kharagpur’s Technology Filmmaking and Photography Society.
Awarded by IIT Kharagpur’s Technology Students’ Gymkhana for distinguished contribution to social and cultural life on campus — the Institute-level tier, above Honourable Mention and Special Mention.
LLMs, agents & retrieval
Models, training & evaluation
From deployment to operations
Context, storage & communication
Interfaces & analysis
I’m open to conversations about AI engineering, intelligent products, and the systems behind them.