AI & Automation

There is nothing in AI
I can't handle.

I have dedicated years to going deep on AI — not as a user of tools, but as someone who builds the infrastructure, trains the models, gates the output, ships the products, and teaches others to do the same. Bring me your hardest AI problem.

6+ AI providers integrated
in production systems
3 Phasma products in
active deployment
SaaS Full billing, licensing &
client management built
FR+EN Bilingual AI — a Quebec
market differentiator

Most "AI for business" advice is shallow. This isn't.

The internet is full of people who figured out how to use ChatGPT last year and now sell AI consulting. That's not what this is.

I've spent years working directly with AI systems at every layer — calling APIs, routing requests through Cloudflare AI Gateway, building RAG pipelines from scratch, handling embeddings, managing token costs, training models on custom data, gating output so it stays on-brand and on-topic, and deploying self-hosted models for clients who can't send data to the cloud. I've built a full AI SaaS platform. I've written the billing system. I've automated the client onboarding with Claude. I've shipped it.

I can also teach you. If you're a senior person who wants to understand AI properly — not a course, not a demo, but a real hands-on conversation about what's actually worth building for your specific situation — that's something I do.

A chatbot that answers three questions then breaks
A properly trained chatbot with RAG knowledge base
Prompt templates from a course
Production prompt engineering from real use
One provider, one model, no fallback
Multi-provider routing with automatic failover
Your data going to OpenAI's servers
Self-hosted models when privacy matters
AI that says whatever it wants
Gated, controlled output — enterprise-safe
Someone who took an AI course
Someone who built the infrastructure from scratch

Things I've actually shipped.

Not demos. Not experiments. Production systems with real architecture.

SaaS Product — Production

Phasma — Managed AI Platform

A fully self-built, enterprise-ready AI SaaS platform I designed and built from scratch. Phasma is not a chatbot plugin — it is a complete managed AI infrastructure with its own hub-spoke architecture, billing system, license management, automated client onboarding, and a demo engine that generates personalized sales demos automatically. A startup to watch.

  • Phasma Hub — central WordPress plugin managing all AI clients, configs, logs, and routing. Serves as the AI gateway for all downstream deployments. v7.7 in active production.
  • Phasma Reach — lightweight client-side WordPress plugin. Downloads pre-configured from Hub with credentials embedded. Auto-connects on activation. Distributed to client sites via built-in update system.
  • Phasma Deep — membership-tier AI product with HMAC-signed per-member tokens, tiered access (basic/premium), per-member quotas, RAG knowledge base, SQLite vector search, and PDF ingestion.
  • Phasma Checkout — full Stripe billing, AI credit accounts (Ectos), plan management, automated welcome and cap-alert emails, client dashboard.
  • Multi-provider AI routing — Claude (Anthropic), GPT-4 (OpenAI), Llama, Mistral, DeepSeek, GLM via Cloudflare AI Gateway. Switchable per client. Unified billing. Auto-failover.
  • AI Client Prepper — native WordPress admin UI that scrapes a prospect's site (sitemap discovery, URL scoring, full subpage crawl), uses Claude to extract 40+ structured business fields, generates system prompt, greeting, FAQs, and starter questions, then pushes directly to a new client record in one click.
  • RAG pipeline — knowledge base chunking, OpenAI text-embedding-3, SQLite vector search, context injection. Per-client vector stores, PDF support, index health monitoring, similarity tuning, test query panel.
  • phasma-core — Python scraper, extraction, and demo pipeline. Brave pre-qualification, multi-phase scraping, master profile schema, output profile engine, declarative JSON templates per vertical (FitPro, Nonprofit, Restaurant, Real Estate, Service Business).
  • Demo Engine — auto-generates fully personalized demo websites per business from scraped data in under a minute. QR code PDF flyer system per vertical. Expiry countdown, floating cart, checkout integration.
  • Full bilingual widget EN/FR, voice input via Whisper, HMAC request signing, encrypted key storage, comprehensive file logging, client auto-update distribution system, lead capture and real-time push to Reach.
PHP / WordPress

Python

Cloudflare Gateway

Claude + GPT-4 + Llama

RAG / Embeddings

Stripe Billing

Whisper Voice

SQLite Vector Search
Personal Tool

AI Trading Dashboard

A personal Streamlit trading dashboard with AI-powered market analysis. Multi-tab interface with candlestick charts, catalyst scanning, backtesting, and an AI morning brief that summarizes market conditions before the open.

  • Cloudflare AI Gateway unified billing — one API token across Anthropic, OpenAI, Google Gemini, Meta Llama, Mistral, DeepSeek
  • Model-agnostic routing layer — swap providers at runtime from the UI
  • Morning brief auto-generates at 6am ET from live RSS feeds + technical snapshots
  • Catalyst scanner scores full watchlist 0–100 across six signals
  • Extended hours data, support/resistance levels, Questrade API integration
Python / Streamlit

6 AI Providers

Cloudflare Gateway

Questrade API

I work directly with the APIs — not just the apps.

Most people use AI through ChatGPT or Claude.ai. I work with the underlying APIs directly — writing code that calls them, handling authentication, managing token limits, normalizing responses across different provider formats, and routing traffic intelligently.

Through Cloudflare AI Gateway, I've built systems that route to Anthropic, OpenAI, Google, Meta, Mistral, and DeepSeek from a single API token — with unified billing, automatic logging, and the ability to switch models or providers without touching client infrastructure.

What this means for you: You're not locked into one provider. If OpenAI goes down, the system routes to Claude. If costs spike, I can switch to a cheaper model. If your data is sensitive, I can point it at a self-hosted model. That flexibility is only possible when someone understands the full stack.

Commercial APIs — direct integration

Anthropic / Claude OpenAI / GPT-4 Google Gemini Cloudflare Workers AI

Via Cloudflare AI Gateway

Meta Llama Mistral DeepSeek Unified billing Auto-failover

Embeddings & RAG

OpenAI text-embedding-3 SQLite vector search Chunk + retrieve pipelines

Voice

OpenAI Whisper API Voice-to-text in production

Prompt engineering

System prompt design RAG context injection Structured output / JSON mode Multi-turn conversation management

When your data can't leave your building.

Healthcare providers, legal firms, HR departments, and anyone handling sensitive client data has a real problem with cloud AI — their information goes to someone else's server.

I run Ollama locally with open source models (Llama, Mistral, and others) and deploy OpenWebUI for clients who need a private, self-hosted AI interface. Same ChatGPT-style experience, zero data leaving your infrastructure.

This isn't a theoretical capability. I run it. I can set it up for you.

🦙

Ollama

Local LLM inference on your own hardware. Running Llama, Mistral, and other open source models. No API calls, no data leaving the machine.

🖥️

OpenWebUI

Self-hosted ChatGPT-style interface I deploy for clients. Your team gets a familiar AI chat experience on your own server, connected to your models.

🔒

Private deployment

Runs on your VPS or dedicated server. SSL secured, access controlled. No subscription to a third-party AI service required.

What I can do for you.

Concrete engagements, not vague "AI strategy."

💬

AI Chatbot — Managed Service

A properly configured, bilingual AI chatbot for your website — set up, trained on your content, and managed by me. You never touch the tech. Enquire for pricing.

📚

RAG & Knowledge Base Training

Give your AI actual knowledge about your business — products, policies, FAQs, procedures. I build RAG pipelines that chunk, embed, and retrieve your content so the AI answers from your data, not guesses.

🔌

AI API Integration

Adding AI capabilities to your existing systems — WordPress, WooCommerce, ActiveCampaign, custom apps. I write the integration code, not just configure a plugin.

🏠

Private AI Deployment

Ollama + OpenWebUI on your own server. Your team gets a ChatGPT-like tool, your data stays on-premises. Ideal for healthcare, legal, HR, or anyone with sensitive client information.

🛡️

Safe & Enterprise-Ready AI

AI that stays on-topic and on-brand. I implement stop words, output gating, topic restrictions, and guardrails so your AI doesn't go off-script, embarrass you, or answer things it shouldn't. Important for any client-facing deployment.

⚙️

AI Workflow Automation

Connecting AI to your existing business processes — content pipelines, lead qualification, customer communication, report generation. Real automation, not demos.

🎓

Executive AI Training

Not a course. A direct conversation with someone who has built real AI systems from scratch. I'll show you what's actually worth doing for your specific situation, what's noise, and how to stop being dependent on people who don't fully understand it either. For senior people who want to get genuinely good at this.

🧠

LLM Training & Prompt Engineering

Fine-tuning, system prompt design, context management, RAG knowledge base training, structured output, output gating and guardrails. I'll train your model, gate its responses, and make it behave exactly the way your use case requires — and stay there.

🇨🇦

Bilingual AI for Quebec

French and English AI systems that actually work in both languages — not translated, natively bilingual. A real differentiator if you serve the Quebec market.

Bring me your hardest AI problem.

I'll build it, train it, gate it, or teach you to do it yourself. There is nothing in AI I can't handle. Let's talk.