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
CI gate that catches AI agent regressions before they ship.
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
- MCP
- Claude
- Docker
- Multi-Agent
- Evals
- DevTools
Real-time AI voice receptionist for clinics, with a live operator dashboard.
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
- TypeScript
- Next.js
- FastAPI
- LiveKit
- Groq
- Voice AI
- Full-Stack
Nine Gemini agents take an issue from bug report to merged PR, unattended.
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
- Multi-Agent
- DevTools
Multi-agent Indian equity research desk with human approval checkpoints.
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.
- Python
- TypeScript
- Next.js
- FastAPI
- LangGraph
- Multi-Agent
- RAG
- Full-Stack
Order food, groceries, and tables in plain English over Swiggy's MCP platform.
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.
- TypeScript
- Next.js
- MCP
- Groq
- Multi-Agent
- Full-Stack
Agent-callable code review skill returning a deterministic verdict.
Built a backend code-review skill any agent can call: POST a raw diff or a PR URL and get back a deterministic pass / needs_changes / fail verdict with line-anchored issues. Runs as a Deno service on Base44 with static analysis behind the verdict, so the same diff always grades the same way.
- TypeScript
- Claude
- Deno
- Evals
- DevTools