No AI products today. This page is a public preview of what we're planning — a Webflow-native AI agent trained on our embed library and design patterns — plus the governance that covers all AI use on client work. Ships after Hublumen and Baselumen.
Read the AI guide → · A no-hype rundown of which AI tools we actually use, for what, and where each one falls short.
An AI co-builder is only as good as the patterns it's trained on. Hublumen and Baselumen are how we're encoding those patterns into a structured library — Stacklumen AI inherits everything they ship.
Component library application — the structured catalog of Webflow embeds and React patterns that the AI will be trained on.
Client portal application — feedback, approvals, and project state that gives the AI context about real-world use cases.
Webflow-native AI co-builder, trained on our patterns and the Baselumen library. Generation, debugging, translation — scoped to a stack we know works.
A short list of capabilities we're scoping for the first release. Some are concrete (we know how we'd build them); some are concepts (we want them, the approach is open). Status reflects that.
Translate a Figma frame or natural-language description into a Webflow embed that respects the 50KB limit. Output uses the Baselumen pattern library, so the code is consistent with our handcrafted work.
Describe a scroll-triggered sequence in plain English; get a working GSAP timeline back, scoped and minified. Built on our reference patterns from real client work.
Paste your Webflow custom code. Get back a list of class collisions with Tailwind utilities, Radix primitives, or third-party scripts — with rename suggestions.
Paste an embed that's over the 50KB limit. Get back a refactored version that fits — with a diff explaining every change.
Generate React + TypeScript components matching the Baselumen design system from a description. Approach is still open — we may use codegen, model fine-tuning, or both.
Generate Vitest or Playwright suites for components and embeds. Approach depends on how reliable model-generated tests prove to be in real codebases — we're researching.
The market doesn't need another general-purpose code AI. It needs tools that are honest about scope and excellent within it. Here's the approach.
The model is fine-tuned on Baselumen patterns and our agency codebase — not the entire internet. Narrower scope, sharper output.
Outputs are diffable, attributable to source patterns, and editable. You see why the model made each decision before you accept it.
Webflow custom code is a niche where most AI tools produce garbage. We've shipped 40+ sites in it — that's the asymmetric advantage.
First release covers two or three concrete use cases that work well, not ten that work poorly. We grow scope based on what people actually use.
AI is already part of how Stacklumen builds and maintains client work — and it runs under strict governance. Access is scoped to your project, every prompt must relate to your own site, and use outside that scope carries real consequences. The full policy follows.
One principle drives everything on this page: AI at Stacklumen exists to serve your project — and only your project.
Anything that moves your project forward. If it’s about your site, it belongs here.
Updates, fixes, new sections, and styling work on the site or app covered by your engagement.
Copy, structure, and content work destined for your own pages and properties.
How your site works, what’s possible within scope, and what a change would involve.
Roadmapping and prioritizing work on your project — upgrades, phases, and maintenance.
Out-of-scope use isn’t a gray area — it’s a contractual line. These are the categories that cross it.
We keep this policy short and the consequences unambiguous, because scoped AI access only works if the boundary holds.
Use AI for your site and everything works beautifully. Use it for anything else and the balance comes due and the project ends, with cause. If you’re unsure whether something is in scope — ask first. Asking is always free.
This policy works alongside the rest of our legal surface. Where documents overlap, the stricter protection applies.
If you’re ever unsure whether a request fits your project’s scope, ask before you prompt. We’ll tell you straight — and if it’s in scope, we’ll ship it.
