Credentials. Weekly runs spend your own API credits on each engine, so store keys securely and set a spending limit with each provider.
Who it is forA growth or SEO lead who needs to show whether changes to content or site structure move AI citations over time.
The problemA single query shows a moment in time, and it is hard to tell a real change in citations from noise.
The outcomeA weekly report with cited rate and a 95% interval, share of voice against competitors and sources, and a diff that calls a change only when a paired test supports it.
What you need first
- Python with pip, to install geo-score==1.8.3 from PyPI (the release pinned in the README)
- A website domain to score; no key is needed for the free score
- For citation checks (levels 2 and 3): your own API key for at least one of OpenAI, Perplexity, Gemini, Anthropic or OpenRouter
Steps
- Install the pinned release:
pip install geo-score==1.8.3(inferred, check the README) - Write a fixed question list for your buyers and set your own API keys for the engines you use.
- Run the watch command on the question set:
geo_score.py watch run - Schedule the same command weekly with your scheduler of choice.
- Compare reports with the diff function so you only act on changes the paired test supports.
Prompt for your agent
Using the geo-score repo at jianruntech/geo-score, run `geo_score.py watch run` against the question set for <target-domain> using my own API keys. Expected output: a weekly report with cited rate, its 95% interval and share of voice. Verify that the diff between this week and last week is labelled as a real change only when the paired test supports it.
Caveat. Sponsors have not been tested for citation measurements, and levels 2 and 3 need each engine's own search-enabled API, so results depend on the keys you provide.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page