Ishan Avasthi

AI Engineer

I build LLM-powered systems, agentic workflows, and developer tools.

About

I'm a CS undergrad at BITS Pilani working on AI engineering. I build the layer between raw language models and working products: pipelines that retrieve the right context, agents that take actions, and tooling that makes the whole thing reliable. I care about testing things properly, making systems easy to work with, and shipping stuff that holds up in the real world.

Projects

AgentGrid: Autonomous Multi-Agent Coding Pipeline

Built a multi-agent coding pipeline powered by 9 Gemini agents that takes a software issue from report to tested, merged pull request with zero human intervention. Enables true agent collaboration, conflict resolution, and context-preserving handoffs across specialized agents (Planner, Coder, Reviewer, Integrator, Tester, Publisher) with a live dashboard and support for voice intake, adversarial testing, and computer-use visual verification.

  • Python
  • Gemini API
  • google-genai
  • stdlib http.server
  • SSE
  • subprocess/git
  • threading
  • concurrent.futures
  • argparse
  • Playwright
  • HTML/CSS/JS
  • WAV/PNG (stdlib)
AlphaDesk: Multi-Agent Equity Research System

Built a full-stack multi-agent research platform that automates Indian stock analysis with LangGraph, live NSE market data, RAG over financial filings, human approval checkpoints, and a real-time research dashboard.

  • LangGraph
  • Next.js
  • TypeScript
  • FastAPI
  • ChromaDB
  • ONNX
  • LangSmith
ChatWithPDF: AI Agentic PDF Chatbot

Developed a full-stack, AI-powered document assistant enabling users to upload PDFs and interactively query them using a RAG pipeline with an agentic reasoning loop, inspired by NotebookLM.

  • Python
  • LangChain
  • LangGraph
  • ChromaDB
  • Next.js
  • Tailwind CSS
RecruitEnv: RL Candidate Triage Environment

Built OpenEnv-compliant RL environment simulating AI-driven candidate screening across difficulty levels.

  • Python
  • FastAPI
  • NumPy
  • Docker
  • Pytest
Swiggy Claw: AI Ordering Agent

Built a full-stack AI ordering agent for food, groceries, and restaurant bookings using plain English, powered by Swiggy's MCP platform, Groq tool calling, resilient retries, and a streaming Next.js chat UI.

  • Next.js
  • TypeScript
  • Tailwind CSS
  • MCP
  • Groq
  • OpenAI Tool Format