AI assistants and search decision
Dooken
A small, single-purpose static ad generator is realistic for one capable developer to build and maintain; there are no evident durable moats on the published page and the core features map to standard APIs and libraries.
Visit website↗Not priced
No pricing page we fetched carried a figure, so there is nothing to compare against. The build side is still real.
$100one-off32 h to build
$50/mo3 h/mo upkeep
No published price to break even against.
No open-source build does this yet
Nothing published replaces this one, so a replacement starts from an empty file. Here is what it would have to cover.
What a replacement has to do
- User enters campaign brief → AI generates ad copy and assets → assemble into static ad → export/save
What it still won’t have
- Design and UX polish of the hosted product
- Proprietary integrations or bundled API keys the vendor may provide
- Any server-side scale, monitoring, and enterprise features not implemented
What remains hard
- Product polish and ongoing maintenance
First-year cost
No published price
Dooken does not publish a price we could read, so there is nothing to compare against. What building costs is below.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build a minimal static ad generator web app using React (Vite), Node.js (Express), Postgres, and Docker. Core features in scope: prompt form for campaign brief, call an LLM API to generate multiple ad copy variants, call an image-generation API to create creative assets, server-side composition of text+image into downloadable PNG/JPEG, simple user session and Postgres-backed draft storage, and an exports history. Out of scope: training custom models, multi-tenant billing, analytics dashboards, and large-scale autoscaling. Include retry and error handling for API calls, input validation, and unit/integration tests for backend endpoints. Provide a Docker Compose dev setup and deployment instructions.
How we checked
How the score was reached
- Build verdict base78
- Evidence score78
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.
How scoring works →Cited sources · 1
Every page the run actually retrieved.
- official productKI Werbung erstellen | Static Ads Generator – Dooken
Integrity checks
What held up, and what did not.
