AI assistants and search decision
Vernigo
A competent developer can reproduce a useful subset (search, outlier scoring, collections) using YouTube APIs in about a week, but the vendor's claimed large proprietary dataset and brand/scale advantages are not reproducible by a lone builder.
Visit website↗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
- Index YouTube videos, detect outliers per channel, enable faceted filtering, save collections, surface suggested titles/thumbnails.
What it still won’t have
- Proprietary, pre-indexed dataset and historical breadth/coverage
- Any curated tuning and UX polish from the original product
- Potentially integrated analytics or team features behind paid plans
- Brand recognition and existing user base
What remains hard
- Proprietary data
Vernigo is the world's largest library of outlier YouTube videos.
- Brand trust
Loved by 2,006 Creators
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 1 seat.
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 single-developer prototype (Node.js + Express backend, Postgres, Next.js frontend) that: 1) ingests video+channel metadata from the YouTube Data API into Postgres; 2) computes an outlier score per video (compare view count against a channel's recent videos) via a daily batch job; 3) exposes search/filter API endpoints (category, views, duration, outlier score); 4) implements a simple authenticated Next.js UI to browse results and save private collections; 5) integrates Stripe for a single paid plan (one seat). Out of scope: training ML models, building a large historical crawl beyond YouTube API, multi-seat team features. Include error handling, retries for API calls, and unit tests for core scoring/search logic.
How we checked
How the score was reached
- Partly verdict base52
- 3/3 assessment runs agreed+4
- Hard moats found in the evidence-3
- Evidence score53
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 →Integrity checks
What held up, and what did not.
