Services
Work I take on
I build software that does real work: AI agents and automations that run unattended, MCP servers that give AI tools access to your systems, and the Next.js products around them. Each page below covers what I build, how I work and what you get.
AI agents and automation
AI agents and automation that run in production: LLM workflows on queues, agents that act on live data, human review where it matters.
DetailsMCP server development
Model Context Protocol servers that let Claude, ChatGPT, Cursor and VS Code use your product or internal tools, with OAuth, rate limits and tests.
DetailsWhatsApp and Shopify automation
A WhatsApp AI sales and support agent for Shopify stores: answers from live stock and prices, orders in the chat, payment matching and human handover.
DetailsNext.js development
Next.js and React products built end to end: App Router, APIs, auth, payments and admin, plus upgrades, performance work and self-hosted deployment.
Details
Also
Smaller pieces of work
APIs & System Design
Typed NestJS APIs with validation, rate limits, SSRF guards, webhooks, job queues and live progress over SSE, designed so the next feature has an obvious place to go.
Performance & Technical SEO
Core Web Vitals, rendering cost, semantic HTML, structured data, sitemaps and llms.txt, so a product loads quickly and search engines and AI assistants can read it.
Developer Tools & Web3
Open-source utilities, starter kits, desktop apps in Tauri and Electron, and wallet flows and on-chain reads when a product actually depends on them.
How it works
From first call to handover
A short call
You describe the problem, the systems you already have and the deadline. I ask the questions that decide the shape of the build.
A written scope
You get a plain document with what I'll build, what I won't, the milestones and the estimate, before any work starts.
Weekly progress
I build in small, working increments you can try, with a short update each week. Nothing disappears for a month.
Handover
Code in your repository, deployed on infrastructure you control, with documentation your team can run it from.
Not sure which fits?
Describe the problem in a few lines. I'll tell you how I'd approach it, or who would be a better fit.