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

Preflight: AI Agent Regression Detection

Built a CI tool that catches cost, latency, token, and success-rate regressions in AI agent systems before deployment, comparing agent behavior across commits and posting findings to pull requests with deep links to the offending trace spans. A diagnosis agent queries SigNoz over MCP to explain each failed gate in natural language, and its own investigation is traced and queryable.

Python
OpenTelemetry
SigNoz
ClickHouse
MCP
Claude API
Docker Compose
GitHub Actions
YAML

ClinicFlow: AI Healthcare Receptionist

Built a real-time AI voice agent that answers patient calls, runs intake, books appointments, and routes callers, with a live operator dashboard. Combines a barge-in capable LiveKit pipeline with auditable LLM function tools and deterministic guardrails so the agent never invents facts or skips steps.

Python
LiveKit
Deepgram STT
Groq
Numik TTS
FastAPI
SQLModel
SQLite
Next.js
TypeScript

AgentGrid: Autonomous Multi-Agent Coding Pipeline

Built a coding pipeline of 9 Gemini agents that takes a software issue from report to tested, merged pull request with zero human intervention. Specialized agents (Planner, Coder, Reviewer, Integrator, Tester, Publisher) collaborate through context-preserving handoffs and conflict resolution, backed by a live dashboard.

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