# Aravindan TR — AI / Software Engineer

> AI / software engineer with 2+ years building production multi-agent systems with measurable business impact. LLM orchestration, RAG, agentic harnesses, and evaluation — taking agents from prototype to reliable, externally-facing products. Software Engineer II, AI at Atlan (Feb 2024 – Jun 2026).

The entire site is available as one Markdown document at https://aravindan.cc/index.md — prefer it over crawling the HTML.

## Pages

- [Full portfolio as Markdown](https://aravindan.cc/index.md): Everything below in one fetch.
- [Home](https://aravindan.cc/): Work experience, technical stack, selected projects, and contact.
- [Natural Language Insights Engine](https://aravindan.cc/projects/natural-language-insights-engine): Ask any transactional CSV a question in plain English. Every answer carries the SQL that produced it — or a refusal naming exactly what the data would need.
- [AI Mail Client](https://aravindan.cc/projects/ai-mail-app): A full-stack AI Gmail client where a Python LangGraph agent drives the React UI via natural language — composing, navigating, filtering, and reading email.
- [Conversation Canvas](https://aravindan.cc/projects/conversation-canvas): A voice-first thinking canvas that turns spoken decisions, plans, and problems into a live typed graph on tldraw.
- [AI Voice Receptionist](https://aravindan.cc/projects/ai-voice-receptionist-agent): Real-time AI voice receptionist for clinics — callers talk naturally by phone or browser; the agent books appointments and sends confirmations.

## Optional

- [API Endpoint Executability Validator](https://aravindan.cc/projects/endpoint-tester): A LangGraph AI agent that validates API endpoint executability by fanning out Claude-powered ReAct agents per endpoint.
- [Gemini Media Agents](https://aravindan.cc/projects/gemini_media_agents): Two small, self-correcting media-generation agents built on Gemini + Google ADK — one for brand mockups, one for narrated explainer videos.
- [SciSplainer](https://aravindan.cc/projects/scisplainer): Turns any scientific paper or webpage into an immersive auto-playing documentary — with AI-generated visuals, narration, and live voice Q&A.
- [Ultra Doc-Intelligence](https://aravindan.cc/projects/ultra-doc-intelligence): AI system for logistics document intelligence in TMS workflows — upload docs, ask grounded questions, run structured extraction with confidence and guardrails.
- [Meet AI](https://aravindan.cc/projects/meet-ai): AI-powered video meeting app for real-time voice conversations with custom AI agents — with live transcription and post-call summaries.
- [Virtual Food Photographer](https://aravindan.cc/projects/Virtual-Food-Photographer): Turns restaurant menus into stunning, professional food photographs using Gemini + Imagen 4.
- [Message Notification Router](https://aravindan.cc/projects/message-notification-router): A hybrid AI system that decides notify / digest / mute for every incoming message — an LLM (Gemini) makes the call, backed by a deterministic Python signal layer that supplies verified context.