AI content pipelines
Multi-modal pipelines that generate copy, image, video, and voice through parallel agent tasks, running 740+ articles in production.
SERVICES
Production AI, and the tooling a team runs on.
I build content pipelines, agent systems, and the MCP tooling that ties them together.
WHAT I BUILD
07 TOTALAgents & MCP servers
MCP servers and agent tooling that give your team direct access to publishing, generation, and analytics from the tools they already use.
Publishing built for AI search
A publishing stack engineered for AI search, structured for citation across ChatGPT, Perplexity, and Gemini.
AI evals & guardrails
Automated evals and commit-time guardrails that catch drift and regressions before they ship, so an autonomous system stays trustworthy in production.
Motion & cinematic web
Scroll-driven WebGL and GSAP sites with real motion craft, the same builds further down this page.
LLM cost & observability
Cost and quality attribution for every AI generation, traced to its model, price, and outcome across every provider you run.
Getting a team AI-native
Hands-on help getting a team AI-native: the workflows, tooling, and habits that turn AI from a novelty into how the work gets done.
STACK
[SEE SELECTED WORK]- AI-Native Engineering
- Agents & MCP
- LLM Orchestration
- Durable Pipelines (Trigger.dev)
- Claude Opus 5
- Runway
- Seedance 2.5
- GPT Image 2
- React / Next.js
- TypeScript
- Python
- WebGL & Shaders (Three.js)
- Animation (GSAP)
- R3F
- Tailwind
- Postgres / Supabase
- Cloudflare Workers
- LLM Observability (Langfuse)
- UI / UX