E-commerce platform
Agento Wear
A production storefront built from nothing: catalogue, guest checkout, payments, order processing, automated email and an admin dashboard the owner runs without an engineer on call.
- Next.js
- React
- Supabase
- Payments
Montlify
One workspace holding 33+ AI tools for writing, research and chat, with the accounts, subscriptions and infrastructure needed to keep them all running.
Open montlify.com
Product design, full-stack build and deployment
33+
AI tools sharing one account, quota and interface
Live
Running in production at montlify.com
SaaS
Authentication, subscription tiers and usage metering
What made it hard
A single AI tool is a weekend project. Thirty-three of them behind one login is a platform problem: every tool needs the same account, the same quota, the same billing state and the same interface, or the product stops feeling like one product and starts feeling like thirty-three stapled together.
How it was built
- 01
One shell, many tools
A shared application frame so each tool inherits authentication, quota, history and layout rather than reimplementing them. Adding a tool became a configuration change instead of a release.
- 02
Model orchestration behind one interface
Prompt management, streaming responses and per-tool routing, so the model behind any given tool can change without the front end knowing about it.
- 03
Accounts, plans and metering
Authentication, subscription tiers and per-user usage limits. The metering had to exist before anything could be priced, so it was built first rather than retrofitted.
- 04
Deployed to take load
Cloud deployment with caching on repeated work. In an AI product the cost line and the architecture are the same conversation, so both were designed together.
What it does
- Writing tools
- Research tools
- AI chat
- Workflow automation
- User accounts
- Subscription plans
- Usage quotas
- Streaming responses
More work
Other things we've shipped.
AI research extension
Overtone
A published Chrome extension that turns an earnings call you are already listening to into research you can defend: answers cited back to a timestamp, slide capture in the player, hedging analysis, and no claim without a source.
- Chrome Extension MV3
- JavaScript
- Content scripts
- Transcript retrieval
Have something like this in mind?
A short call, then a written scope with a fixed price and a date. Scoping costs nothing and the document is yours either way.