App Gen
Overview
App Gen was Webflow’s solution for generating interactive web apps (e.g., event calendars, location finders) from a natural language prompt. For App Gen’s public beta launch, Webflow rolled out a landing page splash screen where site visitors could type a prompt and get a functional app in Webflow.
I owned content design for the end-to-end experience: the landing page splash screen, the full FTUX, and eventually, the content strategy for deprecating App Gen and launching its successor, AI code components.
Goal
Ensure the App Gen landing page provided a frictionless entrypoint for any site visitor to generate an app. The constraint: Every app required an attached Webflow site, and deploying the app would also publish that site, regardless of whether the user had seen it.
Strategy
The site requirement couldn’t be abstracted away. I didn’t want users to discover a dependency they didn’t know to expect in the same moment they were ready to deploy — after they’d invested time generating and customizing their app. The most pressing question was how to introduce it early without it feeling like a catch or a cost.
The answer was to reframe it as a bonus, and to introduce it at the very first moment of the user experience. Then, the rest of the end-to-end FTUX had to deliver on the “bonus” expectation set by the splash screen.
The challenge was that users had to move through two distinct environments: the App Gen surface where they could iterate on their app, and the site surface where the companion site lived. Both needed to feel purposeful, and the transition between them needed to feel intuitive rather than jarring.
I designed the onboarding architecture around two sequential checklists — one for the app, one for the site — each preceded by its own modal to set the stage and reframe the site for where the user was in the flow. The site’s framing deepened as users progressed: first introduced as a free bonus on the splash screen, then an AI-powered asset in the App Gen welcome modal, and finally the app’s foundation when the user made it to their companion site.
User flows
The landing page entrypoint. “Bonus: your app will live inside a free Webflow site!” appeared immediately below the prompt box on the splash screen — up front, before the user submits their prompt. Each part of that string had its own impact:
- “Bonus” signaled an addition; the user got to feel like they’re getting something delightful on top of what they came for instead of being asked to accept a tradeoff.
- “Live inside” made the relationship between the app and site feel spatial and intentional, and subtly reinforced the hosting structure (the app would be deployed to a subpath on the site’s domain).
- “Free Webflow site” incentivized the user to try the product.
- The exclamation point set a celebratory tone — these are rare in Webflow’s voice, and it earned its place here.
After submitting a prompt and logging in or creating an account, the user would land here while the app was generating. The language here shifted from “free Webflow site” to “AI-powered site” — “free” mattered on the landing page where the user was deciding whether to try the product, but once the user was inside, the relevant frame was capability. What did the companion site actually unlock?
The welcome modal also oriented the user to the experience, setting up the two-environment structure the user was about to move through.
The FTUX checklist that followed continued this framing, treating the site as a destination the user would actually want to reach.
The theme customization tooltip copy — “Adjust colors, typography, and more across your app and included site” — was the first moment the site was described as something connected to the app. This planted the idea that changes made to the app carried through to both environments, again preparing the user to navigate the two.
The deployment and site publishing constraint was addressed at the moment the user encountered deployment. The language immediately reassures the user by anticipating and naming what they might be anxious about (i.e., going live with a site they haven’t seen or touched yet).
By this point in the flow, the user had been introduced to the site as an asset worth customizing. The tooltip reactivated that framing, which made the site publish just another expected and intentional step in the setup sequence — and gave the user enough context to receive it without alarm.
The headline here marked the handoff and transitional between the app and the site. “Strengthen your app’s foundation” reframed the site again — now as infrastructure the app depends on.
Each reframe built on the previous so that by the time the user reached this modal, the transition feels earned rather than surprising.
The site FTUX checklist mirrored the App Gen checklist for consistency — same pattern, new environment, which reduced friction at the moment the user encountered an unfamiliar surface.
The steps walked users through the site’s core capabilities in sequence, ending with publishing to close the loop on the dependency introduced on the splash screen and mentioned again when the app was deployed.
The “Published” status was the payoff for the flow that began with “your app will live inside a free Webflow site” — the user had built, customized, and shipped both.
Results
The result was a single connected flow that escalated the value of the site at each stage, from a free bonus to an AI-powered asset to the app’s foundation. The framing deepened as users progressed.
The internal feedback on this experience was that it felt intentional rather than accidental.
What changed
The beta feedback for App Gen told us that users didn’t want standalone apps. They wanted components they could reuse across their Webflow sites. In response, Webflow deprecated App Gen and launched AI code components as its successor.
To deprecate a product still in public beta after a major marketing push required a confident content strategy. I partnered with product marketing to develop the right narrative across three surfaces: an email sequence for existing App Gen beta users, in-product awareness messaging, and a blog post announcing AI code components.
The narrative I pushed for was one of listening and learning. App Gen showed us where users wanted to go. Webflow listened and answered with AI code components.
Challenges
Without user testing, the landing page copy was a judgment call. The “bonus” framing tested well internally, but I’d like to know whether it changed how users experienced the site requirement downstream or whether it just softened the introduction.
The two-checklist structure for the end-to-end flow assumed users would move through App Gen and then into the site in sequence. I’d like to see data on how many users progressed neatly through the happy path and how many abandoned at the app to site transition point. The drop-off rate would tell us whether the “Customize your included site” framing worked as a bridge or whether that was where the experience lost users.