Apoorav Rao.
Available · AI Automation Founder

I build agents
that actually ship.

I'm Apoorav Rao. I build AI agents that find customers and book meetings — while you sleep. My systems cold-call and email local businesses, qualify them, and put meetings straight onto a calendar. Others answer a business's phone 24/7 and transfer to a human when it matters.

Running live for real businesses across the US, UK, and India, backed by a CRM I built and run on AWS that logs and transcribes every call. Also a CS grad — B.Tech Computer Science, 2026.

● Live in US · UK · India·AI Voice Agents · AWS · Self-built CRM·Open to remote
A
Talk to me — AI version ✦
Ask about my projects, skills, personality & availability
What's TrainFlow?What's your tech stack?Are you open to work?
Talk to my AI →View projectsDownload CV ↓Get in touch
scroll
01 ·

About

I build AI agents that find customers and book meetings — while you sleep. My systems cold-call and email local businesses, qualify interest, and put meetings straight onto a calendar. I also build AI phone receptionists that answer a business's calls 24/7 and hand off to a human exactly when it matters.

These run live for real businesses across the US, UK, and India — backed by a CRM I built and run on AWS that logs and transcribes every call. I'm also a CS graduate (B.Tech Computer Science, 8 CGPA, 2026).

Curious what that actually sounds like? Talk to Aria, my AI business advisor →

AI Sales Agents

Cold-calling and emailing local businesses, qualifying interest, and booking meetings straight onto the calendar — no human dialing required.

AI Phone Receptionists

Answering every call on a business's existing number, 24/7, and transferring to a human the moment it matters.

Cloud & CRM Infrastructure

A self-built CRM on AWS that logs and transcribes every call — the backbone every agent reports into.

iOS & Full-Stack Dev

Native SwiftUI apps and serverless AWS backends — the engineering foundation under all of it.

Timeline

2022

Started CS degree

Fell in love with algorithms

2023

First AWS projects

Lambda, DynamoDB, serverless

2024

LLM integrations

Agents, RAG, knowledge bases

2025

Internship @ Caterpillar

LangChain · Airflow · AWS

2026

Building AI agents for businesses

Live in US, UK & India · graduating June 2026

02 ·

Work

one role, real numbers
View case study ↗
Jun 2025 — Mar 2026Internship · 10 months
Gen & Agentic AI Intern→ Case study
Caterpillar Signs Pvt. Ltd. (Group Bayport) · Gurugram
  • ▸Built an LLM-powered data pipeline ingesting CRM data from Freshdesk and Salesforce APIs, running zero-shot classification and extractive QA on support tickets via LangChain, then transforming and loading into PostgreSQL (AWS RDS) via dbt.
  • ▸Orchestrated the entire pipeline with Apache Airflow — handling retries, backfill, and dependency management across daily and weekly jobs.
  • ▸Applied multi-label zero-shot classification to categorise tickets without a labelled training set, surfacing 20%+ more hidden issues buried in unstructured text.
  • ▸Reduced manual ticket review time by 400% by replacing a human-review workflow with an automated LLM audit pipeline with human-in-the-loop escalation.
LangChainApache AirflowdbtPostgreSQLAWS RDSFreshdesk APISalesforce APIPython
400%ticket auditing efficiency15%reduction in ticket volume20%+more issues surfaced
Education
🎓
BRCM College of Engineering and Technology
B.Tech in Computer Science · 8.0 CGPA
Bahal, Haryana · 2022 – 2026
📚
O.P. Jindal Modern School
12th CBSE
Hisar, Haryana · 2022
A couple of wins
🥈Problem-solving, coding, and innovation track.2nd Prize — Collegiate Hackathon
🏆National hackathon — selected in the top 10 teams out of hundreds of applicants.Top-10 Finalist — IIM Ahmedabad × Ashoka University
⚡Competitive programming — graphs, DP, greedy, combinatorics.550+ problems solved on Codeforces ↗
04 ·

Projects

code, not concepts
Client deployment · confidential
◎
☎
✓
📅
Find leadCall + emailQualifyBook meeting
✓ Meeting booked
Production

AI Sales & Booking Agent

An end-to-end AI sales system: it identifies local businesses that fit a client’s ideal customer profile, reaches out by AI voice call and email, qualifies who’s actually interested, and books the meeting directly onto the client’s calendar. No lead lists handed over — just meetings that show up. Every call is logged and transcribed through a CRM I built and run on AWS. Running live for real businesses across the US, UK, and India.

  • ▸Finds and qualifies local business leads automatically
  • ▸AI voice calls + email outreach — no human dialing required
  • ▸Books qualified meetings directly onto the calendar
  • ▸Self-built CRM on AWS logs and transcribes every call
AI Voice AgentCold OutreachAWSCRMLead Qualification
Client deployment · confidential
24/7 · existing number
📞
🤖
Incoming call...
Production

AI Phone Receptionist

A voice AI that sits on a business’s real phone line and picks up every call, day or night. It handles routine questions on its own and transfers to a human the moment a call needs one — so no call goes unanswered and no simple question needs a human. Backed by the same AWS CRM that transcribes and logs every conversation. Running live for real businesses across the US, UK, and India.

  • ▸Answers every call, 24/7, on the business's existing phone number
  • ▸Handles routine questions and transfers to a human when needed
  • ▸Every call transcribed and logged automatically
  • ▸Running live for businesses across the US, UK, and India
AI Voice AgentPhone SystemsAWSCRM24/7 Support
Talk to Aria ↗
A
Aria
🎙️ voice💬 chat
business.apoorav.online
Live
business.apoorav.online

Aria — AI Business Advisor

A live, interactive site where any business owner can talk — by voice or chat — to Aria, an AI advisor that reasons about their business in real time. It’s not a scripted demo: it’s built on the same conversational AI stack that powers my client-facing sales agents and phone receptionists, running live at business.apoorav.online.

  • ▸Voice and chat interface — talk to Aria like a real advisor
  • ▸Live right now at business.apoorav.online
  • ▸Built on the same AI agent stack powering client deployments
  • ▸Real-time conversational reasoning, not a scripted demo
AI Voice AgentConversational AILive ProductAWS
View case study ↗
JavaScript
github.com/apoorav21/cash-tracking-app

Cashflow

An Android-first (Capacitor) personal finance app where you speak to log transactions. OpenAI gpt-4o-transcribe handles speech-to-text via Lambda; gpt-5.4-mini streams a structured JSON draft token-by-token into an editable preview you confirm before saving. Includes Munshi — a bilingual Hindi/English AI assistant that knows your full transaction history and computes interest the Indian way (रुपया सैकड़ा). Force-directed SVG money graph, asset tracking, and offline-first fallback via localStorage.

  • ▸OpenAI gpt-4o-transcribe for speech-to-text via a streaming Lambda Function URL
  • ▸gpt-5.4-mini streams structured JSON token-by-token into an editable transaction draft
  • ▸Munshi: bilingual AI assistant with full transaction context + Indian interest math (सैकड़ा convention)
  • ▸Force-directed SVG money graph, asset tracking, DynamoDB sync, and offline-first fallback
OpenAIgpt-4o-transcribeLambdaDynamoDBCapacitorAndroidCognito
Open on GitHub
423kcalCalories
5.2kmDistance
142bpmHeart Rate
Swift
github.com/apoorav21/trainflow

TrainFlow

A production-grade iOS application that ingests 20+ Apple HealthKit biometrics daily and serves them to an agentic AI coaching loop. A context builder pre-loads user health and training snapshots, a tool executor dispatches up to 5 OpenAI function-calling rounds per request, and a secondary model generates plain-English health summaries. User identities are extracted from Cognito JWT claims — never request bodies.

  • ▸24 Lambda functions + 6 DynamoDB tables deployed via CDK
  • ▸Agentic loop: up to 5 OpenAI function-calling rounds per coaching request
  • ▸Apple Watch companion syncing biometrics in real time via HealthKit
  • ▸Cognito JWT authentication — zero PII in request bodies
SwiftAWS LambdaDynamoDBCDKOpenAIHealthKitCognito
Open on GitHub
KBArticleArticleArticleArticleTagTag
Shell
github.com/apoorav21/llmkb

LLM Knowledge Base

A shell-powered pipeline inspired by Andrej Karpathy's knowledge management approach. It ingests raw articles, runs LLM summarisation and keyword tagging on each one, then stitches the outputs into an interconnected wiki with cross-linked entries. The result is a fully queryable, self-updating knowledge graph that grows every time you drop a new document in.

  • ▸Zero-configuration ingestion — drop any article into the watch folder
  • ▸LLM-powered summarisation, tagging, and cross-reference extraction
  • ▸Outputs a browsable static wiki with bidirectional links
  • ▸Inspired by Karpathy's personal knowledge management patterns
ShellPythonLLMKnowledge GraphKarpathy
Open on GitHub
api-agent — running tests
$ test-agent parse openapi.yaml_
Generating & running tests0%
Python
github.com/apoorav21/apitesting

API Testing AI Agent

An AI agent that reads OpenAPI/Swagger specifications and autonomously generates comprehensive test suites covering happy paths, edge cases, auth failures, and schema validation errors. It executes the generated tests against live endpoints and produces a structured report with per-endpoint pass rates and failure diagnostics — no manual test writing required.

  • ▸Parses OpenAPI 3.x and Swagger 2.0 specs automatically
  • ▸Generates tests for happy path, error codes, edge cases, and auth failures
  • ▸Executes tests against live endpoints and captures response diffs
  • ▸Produces structured pass/fail report with failure diagnostics
PythonOpenAIAPI TestingOpenAPIAutomation
Open on GitHub
ProfileAgentGitHubinLinkedIn↓Resume✓ Synced automatically
Python
github.com/apoorav21/profileagent

Profile Agent

An autonomous agent that monitors GitHub for new repositories, analyzes each project's README, languages, and screenshots, and generates a LinkedIn post, edits a LaTeX resume, and updates the GitHub profile README — all in a single GPT-4o call. The agent reads the full history of past posts before generating anything so tone rotates and content never repeats. Runs daily via macOS launchd; the resume compiles to a one-page PDF via Tectonic with automatic project rotation.

  • ▸Monitors GitHub via webhooks and daily polling — triggers on new repos
  • ▸Single GPT-4o call generates LinkedIn post + resume edit + README update
  • ▸Reads full post history before writing — ensures non-repeating, rotating tone
  • ▸Resume auto-compiles to PDF via Tectonic with one-page constraint enforced
PythonGPT-4oGitHub APILinkedIn APILaTeXSQLitelaunchd
Open on GitHub
Model AVSModel B
Model A
Model B
TypeScript
github.com/apoorav21/aiduel

AI-Duel

A model evaluation framework that fans the same prompt out to multiple LLMs in parallel, renders their outputs side-by-side with token counts and latency, and applies a configurable scoring rubric. Designed to make switching between model providers fast and evidence-based — see exactly where GPT-4o beats Claude or vice versa on your specific workload.

  • ▸Parallel inference — sends one prompt to N models simultaneously
  • ▸Side-by-side diff view with latency, token count, and cost estimates
  • ▸Configurable scoring rubric: factuality, tone, length, task completion
  • ▸Export results as JSON for downstream analysis or CI/CD integration
TypeScriptLLMEvaluationMulti-modelBenchmarking
Open on GitHub
✌️V
→
MediaPipe
Hello
ASL → English
Python
github.com/apoorav21/signlanguage

Sign Language Translator

A computer vision pipeline that captures hand landmarks in real time using MediaPipe, normalises the 21-point hand skeleton to a pose-invariant feature vector, and feeds it into a custom-trained neural network that classifies ASL gestures with high accuracy. The system runs at 30fps on a laptop CPU and outputs translated text with confidence scores displayed live on screen.

  • ▸21-keypoint hand skeleton extracted via MediaPipe at 30fps
  • ▸Custom neural network trained on a normalised ASL dataset
  • ▸Pose-invariant feature extraction — works regardless of hand size or distance
  • ▸Live on-screen overlay showing gesture class and confidence score
PythonMediaPipeDeep LearningOpenCVComputer Vision
Open on GitHub
AAPL+2.4%
$10,423.20
BUY
Python
github.com/apoorav21/papertrading

Paper Trading Web App

A full-stack paper trading platform that simulates real market conditions. Users start with a virtual portfolio and can place market/limit orders, track P&L over time, and review candlestick charts with technical indicators. The Django backend handles order matching, portfolio accounting, and historical data storage — making it a realistic environment for developing and backtesting trading strategies.

  • ▸Django REST backend with real-time order matching and portfolio accounting
  • ▸Candlestick charts with moving averages and volume indicators
  • ▸Supports market orders, limit orders, and stop-loss triggers
  • ▸Full trade history with P&L analysis per position
PythonDjangoMySQLREST APIBootstrap
03 ·

The stack

things I reach for

Agentic AI

AI Voice AgentsCold Outreach AutomationOpenAI Function CallingLangChainMulti-step Tool ExecutionAgentic LoopsKimi K2Prompt Engineering

Cloud & Backend

AWS LambdaDynamoDBAPI GatewayCDKCognitoRDSS3CRM SystemsPythonREST APIs

Data & Pipelines

ETL / ELTApache AirflowdbtPostgreSQLSQLitePandas

iOS & Mobile

SwiftUIHealthKitWatchKitCoreData

Languages

PythonSwiftTypeScriptSQLShell

Tools & APIs

GitGitHub APILinkedIn APINext.jsReactTailwind CSS
Exploring
AWS BedrockMulti-agent systemsRAG pipelinesHealthKit MLVector DBs
05 ·

Let's talk

i reply fast