Portfolio
About HandlerAI Production AI Architecture Experience Skills Contact handlerai.app
Available for opportunities Founder, HandlerAI Hamilton, Ontario 2019 — Present

Damanpreet Singh

Founder of HandlerAI — a 24/7 AI phone receptionist for local businesses. I design the product, the cloud, and the full stack, and I run the company alone with AI.

Scroll
HandlerAI· ElevenLabs· Twilio· AWS· Supabase· Claude Code· Bedrock RAG· ECS Fargate· Stripe· Terraform· Azure· Gemini CLI· HandlerAI· ElevenLabs· Twilio· AWS· Supabase· Claude Code· Bedrock RAG· ECS Fargate· Stripe· Terraform· Azure· Gemini CLI·
01

About

I founded HandlerAI and run it as a one-person company — product, infrastructure, voice, billing, and operations — with AI as the rest of the team.

Multi-disciplinary technologist with 5–8 years spanning systems architecture, infrastructure, full-stack development, and team leadership. I use that range every day to ship HandlerAI without a staff.

Azure-certified cloud architect. Production AI across realtime voice, RAG, and tool-calling agents. Proven ability to operate as a one-person technical department — now applied to a company I own.

0
Company Founded
HandlerAI — solo, AI-operated
0
Years Experience
Systems, AI, Development
0
Certifications
Azure, Fortinet, Cybersecurity
02

HandlerAI

Founded 2026 · Hamilton, Ontario · Solo founder

I started a company to answer the phone when the owner can’t.

HandlerAI is a 24/7 AI phone receptionist for local businesses. It answers in the owner’s name, knows their services, captures the lead, and can book the job — then texts them in seconds. I founded it. I still run every layer of it myself.

How it runs

There is no engineering team. Product, voice runtime, cloud, billing, marketing site, customer portal, and operations are one person plus AI agents — Claude Code and Gemini to build, production models to answer the calls.

The product

An AI that answers the business line. Not a phone tree. Callers interrupt, ramble, and change their minds. HandlerAI keeps up, grounded on that customer’s knowledge base.

Who it’s for

Trades, clinics, salons, restaurants, auto shops — businesses where the phone is the sales channel and the person who should answer is already doing the work.

The company

Multi-tenant SaaS. Isolated knowledge, numbers, and leads per customer. I designed the architecture so one operator can run many businesses without a call center.

03

Production AI

HandlerAI is not a single model behind a prompt. It is several AI systems with different jobs — conversation, retrieval, tools, and operations — wired so a missed call becomes a lead.

01

Realtime voice agents

Inbound audio streams from Twilio into a custom Voice Bridge on ECS Fargate. ElevenLabs Convai is the primary conversation model (persona Maya, voice Amber). xAI Grok Realtime is the reserve path. Opening greetings are pre-rendered TTS. Office ambience is mixed under the voice so it sounds like a desk, not a bot.

ElevenLabs ConvaixAI GrokMedia Streams
02

Per-customer RAG

Each tenant gets an isolated Amazon Bedrock Knowledge Base with Titan v2 embeddings. During a call the agent can lookup_knowledge — hours, services, pricing, FAQs — so answers come from that business, not a generic script. A shared guardrail sits on generation.

Bedrock KBTitan EmbeddingsNova-Lite
03

Tool-calling, not chat

The voice agent has tools: save a lead, look up a customer, book or cancel an appointment, end the call. Tools are gated by vertical and subscription tier. After the call, a fallback extractor still captures a lead if the model did not.

Lead captureBookingTier gates
04

AI that runs the company

Onboarding is an AI-assisted interview, not a settings dump. Provisioning is an orchestrated ledger: knowledge base, ElevenLabs agent, Twilio number. An AI-ops agent (Bedrock Nova) labels, diagnoses, and proposes fixes from structured logs — so I can operate production without a NOC.

Claude CodeGemini CLINova AI-ops
04

Architecture

Cloud, telephony, data, and product surfaces designed so one founder can ship and operate a multi-tenant voice platform.

  1. 01
    PSTN

    Caller dials a Twilio DID. Signature-validated webhook. Demo line has a press-1 robocall gate.

  2. 02
    Voice Bridge

    Lambda returns TwiML. Media Streams WebSocket to ECS Fargate. Bidirectional µ-law audio to ElevenLabs or Grok.

  3. 03
    Tools & RAG

    Knowledge lookup, lead save, booking — scoped to that customer, that tier.

  4. 04
    Systems of record

    Leads and bookings land in Supabase with org isolation. Owner gets SMS and email. Stripe meters the call.

Cloud

AWS us-east-1. Numbered Terraform stacks with separate state and IAM — stacks talk only through SSM, not remote state. Lambdas for telephony, leads, booking, Stripe, onboarding. Voice Bridge on ECS Fargate behind an NLB. Secrets Manager for keys. CloudWatch to Stripe for usage.

TerraformLambdaECS FargateSSM

Full stack

Marketing site at handlerai.app. Authenticated customer portal and operator Mission Control as a separate app bundle on the same CloudFront distribution. Node APIs on Lambda Function URLs. Supabase (Postgres, Auth, RLS) as CRM. Stripe Checkout and metered overage. React/Vite on the web; the original mobile direction is Flutter.

ReactSupabaseStripeCloudFront
05

Experience

Currently: Founder of HandlerAI. Also operating at DIT.

System Administrator
DIT — Hamilton, Ontario
March 2019 – Present

Operating across five distinct roles: systems architect, system administrator, Flutter developer, front-end web developer, and IT team lead. Responsible for the full technology lifecycle from strategic architecture decisions through hands-on implementation and team management.

01

AI & LLM Integration

  • Leveraged Claude Code as a core development tool for accelerated coding, debugging, code review, and AI-assisted architecture planning
  • Utilized Gemini CLI for rapid prototyping, multi-modal analysis, and integrating Google's AI capabilities into internal workflows
  • Designed and implemented RAG database pipelines, connecting LLM models to internal knowledge bases for context-aware AI responses
  • Integrated multiple LLM models into production applications, evaluating performance, cost, and accuracy trade-offs
  • Built AI-powered automation tooling that reduced manual processes and improved team efficiency
02

Systems Architecture & Infrastructure

  • Designed application deployment architecture including CI/CD pipelines, containerization strategies, and cloud infrastructure on Azure and AWS
  • Managed full server infrastructure — networking, security hardening, patching, backups, disaster recovery, and uptime monitoring
  • Served as the senior technical escalation point for all infrastructure issues beyond tier 1 support
  • Made strategic decisions on cloud vs on-prem, tooling selection, and environment architecture
03

Software Development

  • Built and shipped cross-platform applications using Flutter/Dart targeting Android, iOS, and web from a single codebase
  • Owned the full mobile development lifecycle — UI/UX, API integration, state management, testing, and publishing
  • Designed and maintained company websites with responsive design, performance, and conversion optimization
  • Integrated Firebase for authentication, real-time databases, and cloud functions
04

Team Leadership

  • Managed and mentored the tier 1 IT support team, overseeing performance, workload distribution, and professional development
  • Established support processes and escalation paths that improved response times and end-user satisfaction
  • Served as the bridge between technical execution and business needs, translating complex requirements into actionable plans

Approach

I believe the best technology is invisible — it simply works. HandlerAI is that idea as a company: the phone gets answered, the lead is captured, and the owner keeps working. I built the systems so I could run it alone.
Damanpreet Singh
06

How I Build

Expert

Claude Code

Daily driver for HandlerAI — architecture, code generation, review, and documentation. The reason one person can ship a voice platform, a billing stack, and a company.

Code Generation Architecture Debugging Documentation
Expert

Gemini CLI

Expert-level use for rapid prototyping, multi-modal processing, and leveraging Google's AI ecosystem for analysis, content generation, and workflow automation.

Prototyping Multi-Modal Automation
Advanced

RAG Pipelines

Designed and built retrieval-augmented generation systems connecting LLMs to structured and unstructured internal data sources using vector databases and embedding models for context-aware AI responses.

Vector DBs Embeddings Knowledge Bases
Advanced

LLM Integration

Hands-on experience evaluating, integrating, and deploying multiple large language models in production environments. Skilled in prompt engineering, model selection, cost optimization, and building AI-powered features.

Prompt Engineering Model Selection Production Deploy
07

Core Competencies

AI & LLM Engineering

Claude Code ElevenLabs Convai Bedrock RAG RAG Pipelines LLM Integration Prompt Engineering AI Automation Vector Databases Embedding Models AI Security Reviews AI App Lifecycles

Architecture & Infrastructure

AWS Terraform Twilio Azure ECS Fargate Docker / Kubernetes Linux Windows Server Networking & Security Disaster Recovery

Software Development

React / Vite Supabase Stripe Firebase REST APIs Git / GitHub Cross-Platform Mobile Responsive Design App Publishing

Leadership & Operations

Solo Founder AI-Operated Company Vendor Management Stakeholder Comms Project Prioritization
08

Certifications & Education

Azure Administrator Associate

Microsoft · Issued Jun 2025 · Expires Jun 2026
Verified

FortiClient EMS 7.2 Administrator

Fortinet · Issued Sep 2024
Verified

Certified Associate Cybersecurity

Fortinet · Issued Oct 2023
Verified

Certified Fundamentals Cybersecurity

Fortinet · Issued Aug 2023
Verified

Computer Science / Information Technology

Mohawk College
09

Get In Touch

Building with AI, hiring for a systems role, or want HandlerAI on your line? Let’s talk.

sandhudaman0024@gmail.com