Can ArtificialWatch be vibe coded?
Alerts you the minute a new frontier AI model goes live
The core loop is a genuine one-sitting build: poll the model-list endpoint of every provider you hold a key for, diff the ids against a local table, push the new ones to your phone. What does not one-shot is the three things a launch alert is actually judged on. Coverage · your script sees only the labs you have accounts with, while the watchlist here runs to 48 models including Chinese labs, restricted previews and things that have not shipped at all, which no API returns. Telephony · a call that rings until you answer means Twilio, a purchased number and US A2P 10DLC registration, which is days of paperwork before a line of code. And uptime, which is the whole product · a poller on a laptop that slept through the drop is worth nothing, and the second-sweep debounce that keeps preview aliases from crying wolf is the part you only tune after it has already cried wolf twice.
Jump to the build brief ↓Checked Jul 2026
What you pay today, before any DIY hosting
high 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
- Polls every provider's model-list endpoint on a one-minute cron, diffs new model ids against a local database, and pushes an alert to your phone.
- Build a focused single-user workflow with real persistence, search, and export.
- A responsive interface with real empty, loading, success, and error states.
The parts a prompt cannot buy
- coverage of labs you hold no key for · 48 tracked models including Chinese labs and restricted previews
- the phone call that rings until you answer, and SMS · Twilio plus US A2P 10DLC registration
- the pre-launch watchlist and live Polymarket odds on models that have not shipped, which no API can return
- debounce and alias filtering tuned so dated snapshots and -preview ids do not fire false alarms
- Reliability at the vendor's scale is an operations problem, not a prompt.
- The last 20 percent is sync, migration fidelity, speed, and edge cases.
Why people still pay
Because the failure mode is asymmetric. A launch alerter that works 95% of the time is not 95% as good, it is worthless on the one morning it matters, and that is exactly the morning your VPS got rate limited or your ntfy topic was muted. Paying moves the pager duty to someone else, buys the labs you have no account with, and buys a phone that rings instead of a notification that stacks under forty others. At $19.99 it is priced against the AI subscriptions it watches, which is the comparison buyers actually make.
Reliability at the vendor's scale is an operations problem, not a prompt.
The last 20 percent is sync, migration fidelity, speed, and edge cases.
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 ArtificialWatch
Context
**ArtificialWatch** — Alerts you the minute a new frontier AI model goes live. It currently costs $19.99/mo.
The core loop is a genuine one-sitting build: poll the model-list endpoint of every provider you hold a key for, diff the ids against a local table, push the new ones to your phone. What does not one-shot is the three things a launch alert is actually judged on. Coverage · your script sees only the labs you have accounts with, while the watchlist here runs to 48 models including Chinese labs, restricted previews and things that have not shipped at all, which no API returns. Telephony · a call that rings until you answer means Twilio, a purchased number and US A2P 10DLC registration, which is days of paperwork before a line of code. And uptime, which is the whole product · a poller on a laptop that slept through the drop is worth nothing, and the second-sweep debounce that keeps preview aliases from crying wolf is the part you only tune after it has already cried wolf twice.
This brief describes a focused, single-operator replacement for the part of ArtificialWatch 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
Polls every provider's model-list endpoint on a one-minute cron, diffs new model ids against a local database, and pushes an alert to your phone.
Build a focused single-user workflow with real persistence, search, and export.
A responsive interface with real empty, loading, success, and error states.
Requirements
Functional
An always-on box · a small VPS or a Pi, not a laptop.
An ntfy or Pushover topic for push.
Data and integrations
API keys for the providers you want covered (OpenAI, Anthropic, Google, OpenRouter).
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 new-AI-model launch alerter to replace ArtificialWatch. Requirements:
Node 22 + node-cron + better-sqlite3, one process on a small VPS under pm2 so
it never sleeps · a laptop that naps misses the launch.
Every 60 seconds, GET the model-list endpoints for the keys in .env: OpenAI
/v1/models, Anthropic /v1/models, Google generativelanguage /v1beta/models,
and OpenRouter /api/v1/models, which covers labs I have no account with.
Store every model id ever seen in SQLite. A launch is an id new to that table
· seed it on first run so the first sweep is silent.
Debounce: an id fires only after two consecutive sweeps, and ids matching a
regex list in config.json (dated snapshots, -preview, -latest) never fire.
Alert by POSTing to an ntfy.sh topic: model id as the title, provider plus
context window and per-token price as the body, link to the provider's docs.
Append each confirmed launch to launches.md as `YYYY-MM-DD · provider · id`.
One page on localhost:8080: last 50 launches, last good sweep per provider,
red banner when a provider has errored 10 minutes · a silent poller is worse
than none.
Out of scope: SMS and phone calls (Twilio plus US A2P 10DLC registration is
paperwork, not code) and any watchlist of unshipped models.
README with the four .env keys and the pm2 command.
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:
Coverage of labs you hold no key for · 48 tracked models including Chinese labs and restricted previews.
The phone call that rings until you answer, and SMS · Twilio plus US A2P 10DLC registration.
The pre-launch watchlist and live Polymarket odds on models that have not shipped, which no API can return.
Debounce and alias filtering tuned so dated snapshots and -preview ids do not fire false alarms.
Reliability at the vendor's scale is an operations problem, not a prompt.
The last 20 percent is sync, migration fidelity, speed, and edge cases.
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: high. No independent one-shot implementation is linked yet.
Prior art
Working open-source software you can read, fork, or borrow from before starting:
[models.dev](https://github.com/anomalyco/models.dev) — open-source database of AI models, providers and pricing · the data layer a DIY watcher can diff against
[changedetection.io](https://github.com/dgtlmoon/changedetection.io) — self-hosted page-change monitoring with notifications · covers the docs and pricing pages an API cannot
Generated by [Can It Be Vibe Coded?](https://www.canitbevibecoded.com) · Full report: https://www.canitbevibecoded.com/artificialwatch
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 ArtificialWatch be vibe coded?
Partly, if you narrow it. The core loop is a genuine one-sitting build: poll the model-list endpoint of every provider you hold a key for, diff the ids against a local table, push the new ones to your phone. What does not one-shot is the three things a launch alert is actually judged on. Coverage · your script sees only the labs you have accounts with, while the watchlist here runs to 48 models including Chinese labs, restricted previews and things that have not shipped at all, which no API returns. Telephony · a call that rings until you answer means Twilio, a purchased number and US A2P 10DLC registration, which is days of paperwork before a line of code. And uptime, which is the whole product · a poller on a laptop that slept through the drop is worth nothing, and the second-sweep debounce that keeps preview aliases from crying wolf is the part you only tune after it has already cried wolf twice.
What can an AI coding agent reproduce from ArtificialWatch?
Polls every provider's model-list endpoint on a one-minute cron, diffs new model ids against a local database, and pushes an alert to your phone. Build a focused single-user workflow with real persistence, search, and export. A responsive interface with real empty, loading, success, and error states.
What will a DIY ArtificialWatch replacement still be missing?
coverage of labs you hold no key for · 48 tracked models including Chinese labs and restricted previews; the phone call that rings until you answer, and SMS · Twilio plus US A2P 10DLC registration; the pre-launch watchlist and live Polymarket odds on models that have not shipped, which no API can return; debounce and alias filtering tuned so dated snapshots and -preview ids do not fire false alarms; Reliability at the vendor's scale is an operations problem, not a prompt.; The last 20 percent is sync, migration fidelity, speed, and edge cases.
What do I still own after building a ArtificialWatch 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.