Framewise
AI website builder — describe a business, get a finished site
In short: Framewise is an in-house DanixSoft product (SaaS / AI): AI website builder — describe a business, get a finished site. Daniyal Alam built it — product decisions, architecture and code.
An AI website builder. You describe your business, the model plans the sitemap, sections, copy and palette in one call, and you refine the result in a Figma-like editor before publishing to Vercel or exporting the Next.js source to GitHub.
- Industry
- SaaS / AI
- Scope
- Products we build and run in-house at DanixSoft
- Core stack
- Next.js 16 · React 19 · TypeScript · OpenAI
- Year
- 2026
The problem
Small businesses need a professional website without hiring a developer, but most builders hand them a template marketplace and leave structure, copy and design decisions to them.
The solution
One structured-output OpenAI call returns a blueprint — sitemap, sections, copy, palette and CTA strategy — never raw HTML. Rendering, editing, layout swaps, SEO, publishing and export are deterministic and cost no further model calls.
My role
I built it: the commit history of its repository is mine — product decisions, architecture and code.
DanixSoft team
An in-house DanixSoft product — built and operated by the studio, not for a client.
Technical challenges
The engineering problems this build had to get right.
- Exactly one AI call per site — enforced by tests that count model calls
- Ownership decided by row-level security, never by an id from the caller
- Every generated palette checked against WCAG AA in light and dark
Architecture
Implementation — what shipped
Engineering notes
Lesson for similar SaaS builds: design for exactly one AI call per site — enforced by tests that count model calls and ownership decided by row-level security, never by an id from the caller up front — these are the parts that are expensive to retrofit once the feature list grows.
Technologies
- Next.js 16
- React 19
- TypeScript
- OpenAI
- Supabase
- Tailwind
- Stripe
- Playwright
Building something similar?
A 30-minute discovery call is enough to scope the approach and a realistic budget.