Can Wholana be vibe coded?
TikTok research tool that ranks videos against each creator's own baseline and labels what they did
The core idea is simple arithmetic: a video's views divided by that creator's own median. An agent can build that for a watchlist of creators you pick, over a contained effort, on top of a paid scraper API. What it cannot hand you is the corpus, hundreds of thousands of videos already scraped, deduped, and labeled against a curated craft taxonomy, which is what makes search across creators useful instead of a list of your own bookmarks. So: yes for watching 25 creators you already know, no for finding the ones you don't.
Jump to the build brief ↓Checked Jul 2026
What you pay today, before any DIY hosting
medium editorial confidence
Buildability by layer
Screens, forms, and focused interactions
The repeatable job the product performs
Availability and legality of required data
Uptime, queues, support, and maintenance
Security, compliance, and user confidence
The achievable core
- Scrape a watchlist of creators nightly, compute each creator's rolling median views, and surface the videos that beat their own baseline.
- Draft, queue, and track content for the few networks you actually use.
- A responsive interface with real empty, loading, success, and error states.
The parts a prompt cannot buy
- the cross-creator corpus
- search across videos you never chose to watch
- a curated craft taxonomy instead of labels you invented
- semantic and hybrid search
- The useful dataset is owned, accumulated, or expensive to reproduce.
- Reliability at the vendor's scale is an operations problem, not a prompt.
Why people still pay
The arithmetic is free, the data is not. A personal build only ever knows about the creators you thought to add, and you pay the scraper bill every month to keep even that fresh. The subscription is renting a corpus that was already collected and labeled, plus the discovery that only exists once videos from creators you have never heard of are sitting in the same index.
The useful dataset is owned, accumulated, or expensive to reproduce.
Reliability at the vendor's scale is an operations problem, not a prompt.
The brief
Context, requirements, acceptance criteria, non-goals, and the full production standard — as Markdown, ready for any coding agent.
Build brief — a focused alternative to Wholana
Context
**Wholana** — TikTok research tool that ranks videos against each creator's own baseline and labels what they did. It currently costs $5/mo.
The core idea is simple arithmetic: a video's views divided by that creator's own median. An agent can build that for a watchlist of creators you pick, over a contained effort, on top of a paid scraper API. What it cannot hand you is the corpus, hundreds of thousands of videos already scraped, deduped, and labeled against a curated craft taxonomy, which is what makes search across creators useful instead of a list of your own bookmarks. So: yes for watching 25 creators you already know, no for finding the ones you don't.
This brief describes a focused, single-operator replacement for the part of Wholana that is genuinely reproducible. It is deliberately narrower than the product it replaces, and it says so in writing. Build the useful core; do not pretend to have rebuilt the rest.
What you are building
Scrape a watchlist of creators nightly, compute each creator's rolling median views, and surface the videos that beat their own baseline.
Draft, queue, and track content for the few networks you actually use.
A responsive interface with real empty, loading, success, and error states.
Requirements
Functional
SQLite.
A nightly cron job.
A scrape budget that recurs every month.
Data and integrations
TikTok scraper API (Apify or similar, paid per run).
LLM API key for hook labeling.
Each of these needs a real account, credential, or quota. Set them up before writing feature code.
Non-functional
Accessibility: semantic markup, labelled controls, visible focus, and reduced-motion support.
Security: server-side secrets, validated input, and no credentials in the client bundle.
Reliability: retries with backoff on external calls, and a clear failure state when a provider is down.
Portability: the operator can export their data and leave without losing it.
Implementation brief
Build me a personal TikTok outlier tracker to replace Wholana. Requirements:
A nightly Node script (node-cron) that pulls recent videos for up to 25 handles listed in
handles.txt, using a TikTok scraper actor on Apify, token in .env. Do not scrape TikTok
directly, you will be blocked inside a day.
Store videos in SQLite via better-sqlite3: handle, video id, url, caption, posted date,
views, likes, comments, shares, date first seen. Upsert on video id so a re-scrape
updates metrics instead of duplicating rows.
Per creator, keep a rolling median of views over their last 30 videos and score each
video as views divided by that median. 3x or higher is a breakout. Skip creators under
10 videos, the median is noise below that.
Label each breakout with one LLM call (Anthropic or OpenAI, key in .env): caption plus
the first 15 seconds of subtitles from yt-dlp, returning one hook type from a fixed list
of 12 in hooks.json. Fixed list, not free text, or nothing groups.
A page on localhost:3000 (Express, server-rendered HTML, Chart.js): last 7 days of
breakouts sorted by score, filterable by handle, each row showing score, views, hook
type, and a link, plus a per-creator sparkline of views over time.
A save button per row that writes the video into a swipe collection and appends it to
swipe.md, so my picks survive the database.
Localhost only. No accounts, no telemetry, everything on my machine except the Apify and
LLM calls.
Out of scope: search across creators I am not already tracking, and a shared craft
taxonomy. Do not build auth, multi-user workspaces, or hosting config.
README: Apify token and actor id, the cron entry, and the cost per 1,000 videos scraped.
The scraper bill, not the code, is what makes people quit this build.
Delivery standard
Inspect the repository first, then write a short implementation plan before writing code.
Deliver the smallest complete end-to-end workflow first; every primary control must work against persisted data.
Use real validation and storage; never substitute fake dashboards, decorative controls, hard-coded success states, or mock integrations.
Include responsive layouts plus genuine empty, loading, success, validation, and failure states.
Keep secrets server-side in environment variables, provide .env.example, and never commit credentials or user data.
Add structured logs around every external call and return actionable errors without leaking sensitive details.
Write unit tests for the core logic and one automated test of the main user journey.
Finish with a README covering setup, architecture, data location, backups, tests, deployment, and known limitations.
Acceptance criteria
A clean install starts the app using only the README and .env.example.
The primary journey works from first visit through saved result, reload, edit, export, and deletion where applicable.
Invalid input, missing configuration, provider failure, and an empty database each have a usable state.
The interface works at 390px and 1440px, is keyboard navigable, and shows visible focus on every control.
Tests, type checking, linting, and a production build all pass with no ignored failures.
No part of the interface implies a live integration, security guarantee, or scale capability that was not actually built and verified.
Non-goals
Do not build these, and do not claim to have replaced them:
The cross-creator corpus.
Search across videos you never chose to watch.
A curated craft taxonomy instead of labels you invented.
Semantic and hybrid search.
The useful dataset is owned, accumulated, or expensive to reproduce.
Reliability at the vendor's scale is an operations problem, not a prompt.
What you still own after launch
Secure credentials, rotate secrets, and handle provider rate limits.
Run migrations, backups, restores, and dependency updates.
Test the critical journey after every model, API, or hosting change.
Monitor failures and fix the edge cases a first prompt will miss.
Risk
**Operational risk.** The code is achievable; dependable data, integrations, and ongoing operations are the real cost.
Editorial confidence in this assessment: medium. No independent one-shot implementation is linked yet.
Prior art
Working open-source software you can read, fork, or borrow from before starting:
[TikTokApi](https://github.com/davidteather/TikTok-Api) — Unofficial Python wrapper for TikTok's web endpoints; gets you raw metrics, not a corpus, and breaks when TikTok changes
Generated by [Can It Be Vibe Coded?](https://www.canitbevibecoded.com) · Full report: https://www.canitbevibecoded.com/wholana
You still own the product
- Secure credentials, rotate secrets, and handle provider rate limits.
- Run migrations, backups, restores, and dependency updates.
- Test the critical journey after every model, API, or hosting change.
- Monitor failures and fix the edge cases a first prompt will miss.
Open-source prior art
Before you start
Can Wholana be vibe coded?
Partly, if you narrow it. The core idea is simple arithmetic: a video's views divided by that creator's own median. An agent can build that for a watchlist of creators you pick, over a contained effort, on top of a paid scraper API. What it cannot hand you is the corpus, hundreds of thousands of videos already scraped, deduped, and labeled against a curated craft taxonomy, which is what makes search across creators useful instead of a list of your own bookmarks. So: yes for watching 25 creators you already know, no for finding the ones you don't.
What can an AI coding agent reproduce from Wholana?
Scrape a watchlist of creators nightly, compute each creator's rolling median views, and surface the videos that beat their own baseline. Draft, queue, and track content for the few networks you actually use. A responsive interface with real empty, loading, success, and error states.
What will a DIY Wholana replacement still be missing?
the cross-creator corpus; search across videos you never chose to watch; a curated craft taxonomy instead of labels you invented; semantic and hybrid search; The useful dataset is owned, accumulated, or expensive to reproduce.; Reliability at the vendor's scale is an operations problem, not a prompt.
What do I still own after building a Wholana alternative?
Secure credentials, rotate secrets, and handle provider rate limits. Run migrations, backups, restores, and dependency updates. Test the critical journey after every model, API, or hosting change. Monitor failures and fix the edge cases a first prompt will miss.