I bridge the gap between what you need and what gets built.
15 years understanding customers. Now I build for them.
AI Automation You Own. Production systems shipped fast.
Projects Built
Self-directed learning through hands-on building: Voice AI, Micro-SaaS, personal tools, and infrastructure
ClientFlow
No-code stack monitoring SaaS with predictive alerts
THE WORK
TECH STACK
AI Voice Agent
Multi-tenant voice AI platform with real-time conversations
THE WORK
- •Real-time voice AI with ~600-800ms response latency
- •WebSocket streaming: Deepgram STT → Groq LLM → Cartesia TTS
- •Auto-scaling on Fly.io (0→1 in <5 seconds)
- •AI provider auto-switching with Groq/Gemini fallback
- •Multi-tenant architecture with isolated data and webhooks
TECH STACK
IMPACT
Video Deepfake Detector
AI-powered deepfake detection with GPT-4 Vision
THE WORK
- •Multi-segment temporal sampling (3 segments at 25%, 50%, 75%)
- •Structured scoring with per-region analysis
- •GPT-4 Vision with forced JSON response for reliable detection
- •Client-side frame extraction with canvas API
- •Research-backed prompt engineering for 77-79% detection accuracy
TECH STACK
IMPACT
RAG Chatbot
Production RAG with vector search and GPT-4o
THE WORK
- •PostgreSQL pgvector with HNSW indexing for semantic search
- •OpenAI embeddings (text-embedding-3-small) + GPT-4o chat
- •Semantic chunking: 500 tokens with 50-token overlap
- •Digital Ocean upload service for 25MB file processing
- •Optimized for speed: 3-5 second responses, concise answers
TECH STACK
IMPACT
Anthropic Models Manager
Centralized AI model management serving 10+ production apps
THE WORK
- •Fully automated model detection via daily cron (zero-touch updates)
- •TypeScript-based API serving live model configs to production apps
- •A/B testing dashboard with usage analytics and cost monitoring
- •Vercel Edge Functions + Neon PostgreSQL architecture
- •Public demo with clean, documented codebase
TECH STACK
IMPACT
Agency Dashboard
Multi-client tracking dashboard for marketing agencies
THE WORK
- •Master agency view with client isolation for white-label access
- •Interactive SVG charts: performance trends, donut charts, leaderboards
- •Dark/light mode with CSS variables and smooth transitions
- •Paginated data tables with industry breakdown views
- •Client preview mode to demo isolated tenant experience
TECH STACK
IMPACT
Bland Flow
Community tool for visualizing Bland.ai voice agent pathways
THE WORK
- •Interactive flowchart visualization with React Flow
- •Shareable links with Vercel Blob storage (never expire)
- •Auto-parses Bland.ai JSON exports into visual node graphs
- •Color-coded node types: Start, End, Webhook, Route, Custom Tool
- •Click nodes to inspect prompts, conditions, and variable extraction
TECH STACK
IMPACT
n8n Workflow Demos
Production-ready n8n workflows for automation and AI integration
n8n RAG Chatbot
Document Q&A powered entirely by n8n workflows
THE WORK
- •No backend code - n8n handles all processing
- •Document ingestion: chunking, embeddings, PostgreSQL storage
- •Workflow: embed question → pgvector search → GPT-4o response
- •Same pgvector/HNSW architecture as Tier S RAG project
- •Frontend calls n8n webhooks directly (no API layer)
TECH STACK
IMPACT
AI Lead Qualification Chat Agent
AI chatbot with conversation memory and team notifications
THE WORK
- •Claude AI for natural lead qualification conversations
- •PostgreSQL conversation memory with session management
- •Email detection and automatic lead capture
- •AI-generated chat summaries for sales team
- •Streaming text effect frontend for realistic feel
TECH STACK
IMPACT
Telegram AI Lead Qualification Bot
AI chatbot with animated typing indicator workaround
THE WORK
- •Animated typing indicator (●○○ → ○●○ → ○○●) using message edits
- •Workaround for Telegram's broken sendChatAction API
- •Concurrent promise pattern in n8n Code nodes
- •Claude AI with PostgreSQL conversation memory
- •Email extraction with AI chat summaries for team
TECH STACK
IMPACT
Open Source & Explorations
Side projects exploring different domains and technologies
File Upload Microservice
S3-compatible upload handler for large files
THE WORK
- •Digital Ocean Spaces (S3-compatible) integration
- •Nginx reverse proxy with SSL termination
- •PM2 cluster with 2 instances and auto-restart
- •CORS handling for cross-origin uploads
- •Handles 500MB+ files efficiently
TECH STACK
IMPACT
Personal SMS & Voice Platform
AI-powered messaging and WebRTC calling for voip.ms
THE WORK
- •AI reply drafting with Claude (learns relationship context and tone)
- •WebRTC browser calling via FreeSWITCH SIP gateway
- •Voicemail transcription with audio playback
- •Privacy mode for masking sensitive data during screen sharing
- •TypeScript Edge Functions with CSRF and brute-force protection
TECH STACK
IMPACT
GIF Recorder (Chrome Extension)
MacOS screen capture with server-side conversion
THE WORK
- •Native Swift app using ScreenCaptureKit for accurate cursor on Retina
- •Chrome Native Message bridge for extension-to-native coms
- •Window-only capture with sourceRect cropping (no black space)
- •Express server with ffmpeg palette-optimized MP4→GIF conversion
- •Multi-browser support (Chrome, Vivaldi, Arc, Brave, Edge)
TECH STACK
IMPACT
BrightnessControl (macOS Native App)
Systems programming exploration: DDC/CI hardware control
THE WORK
- •Native Swift app for macOS status bar (AppKit, CoreGraphics, IOKit)
- •DDC/CI protocol build for external display control (M-series ARM64)
- •Gamma table manipulation for software-based brightness adjustment
- •Link Displays mode for simultaneous multi-monitor control
- •Keyboard shortcut system with cursor-based display targeting
TECH STACK
IMPACT
Hard Lessons
Challenges that shaped how I think about development
Security-First Development
Why security can't be an afterthought
- •19 API endpoints deployed without CSRF protection
- •Vulnerability discovered after production deployment
- •Every state-changing endpoint was at risk
- •Systematic audit across 4 subdomains
- •Built reusable withCsrf() middleware
- •Documented patterns in "Security Bible"
- •Zero vulnerabilities, zero-downtime rollout
- •Reusable security library for all projects
- •New rule: security designed in, not bolted on
AI-Assisted Development
Questioning TypeScript convention
- •Convention says TypeScript prevents bugs
- •Does that apply when AI writes the code?
- •Needed data, not dogma
- •Analyzed actual bugs: column renames, event bubbling, env vars
- •Pattern: none were type errors
- •All were logic/conceptual mistakes
- •Informed decision: JavaScript over TypeScript
- •Faster iteration without compile steps
- •AI bugs need investigation, not type checking
Tech Stack & Tools
Technologies I use to build, deploy, and manage production systems
Cloud & Infrastructure
APIs & Integrations
Databases & DevOps
AI & Development Tools
The Combination
Most technical roles need both customer communication and technical execution.
Most people only have one.
I have both.
Customer-Facing (15 Years)
Understanding What Customers NeedAI Specialist | Independent (2022-Present)
Building production voice AI and automation systems for clients
Co-Founder & CTO | PFM Media (2020-2023)
Built and operated digital marketing agency with real-time call center infrastructure serving real estate clients. Trained sales teams, managed client relationships end-to-end.
Behavioral Recognition | Pearson Airport (2012-2018)
High-stakes decision-making at Canada's busiest airport. Eye on Safety award for life-saving intervention.
Skills Developed:
- Explaining technical complexity to non-technical stakeholders
- Managing customer relationships through implementation challenges
- Troubleshooting under pressure with incomplete information
Technical Execution
Building What They NeedAI & LLM Integration:
Claude API integration and prompt engineering, conversational AI design, RAG-style architecture
Development:
JavaScript, React, Node.js, RESTful API integration, serverless architecture (Vercel), PostgreSQL (28-table schema)
Integration & Automation:
6-platform API architecture (Twilio, Cal.com, Stripe, Bland.ai, Make.com, Neon)
What This Proves:
- Production software while working full-time
- AI-native development from day one
- Focus on working solutions, not perfect code
- Tried multiple approaches until it worked
- Self-directed learning without hand-holding
- Real deployments, not tutorials
This combination is rare and valuable for customer-facing technical roles:
Let's Build Something
Interested in working together? Get in touch.
Built with modern tools and AI partnership
© 2025 Cameron O'Brien