# AI use cases for Geo Score (jianruntech/geo-score) Repo: [jianruntech/geo-score](https://github.com/jianruntech/geo-score) | Use cases: 4 | Page: https://dedupedai.com/use-cases/jianruntech-geo-score/ geo-score is an open-source Python tool that scores a website from 0 to 100 on whether AI answer engines can reach, parse, trust and cite it, and can check citations through your own API keys. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Score a website's readiness for AI answer engines: https://dedupedai.com/use-cases/jianruntech-geo-score/score-site-ai-readiness/ - Check whether AI engines cite your site for one question: https://dedupedai.com/use-cases/jianruntech-geo-score/check-if-ai-engines-cite-site/ - Track how often AI engines cite your site each week: https://dedupedai.com/use-cases/jianruntech-geo-score/track-weekly-ai-citations/ - Fail a build when a site's AI readiness regresses: https://dedupedai.com/use-cases/jianruntech-geo-score/block-site-regressions-in-ci/ ## How to score a website's readiness for AI answer engines with Geo Score Repo: [jianruntech/geo-score](https://github.com/jianruntech/geo-score) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Get a free 0 to 100 AI visibility score with the three gates and biggest gaps. **Who it is for:** A marketing or web lead who wants to know why AI engines might leave their site out, before spending on content or SEO changes. **The problem:** Standard SEO reports do not show whether AI retrieval crawlers can reach a page, parse its content, or find it trustworthy enough to quote. **The outcome:** A 0 to 100 score on the open rubric, the three gate checks, the gaps worth fixing first, and a result anyone can recompute. ### Steps 1. Install the pinned release: `pip install geo-score==1.8.3` (inferred, check the README) 2. Run the free score on your domain: `geo_score.py yourdomain.com` (inferred, check the README) 3. Read the three gate checks first; a gate at zero caps the result at 40. 4. Work through the biggest gaps listed, starting with the cheapest fixes such as robots.txt lines or missing JSON-LD. 5. Re-run the same command after each fix to confirm the change in the score. ### Prompt to paste into your agent ```text Using the geo-score repo at jianruntech/geo-score, run the free score on with geo_score.py, then list the three gate checks and the top three gaps by points. Expected output: the 0 to 100 score, band and gap list. Verify that the score is reported without any API key being used. ``` ### Caveat The score measures readiness against the rubric only; it does not measure whether any AI engine actually cites the site, which needs levels 2 and 3. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/jianruntech-geo-score/score-site-ai-readiness/ ## How to check whether AI engines cite your site for one question with Geo Score Repo: [jianruntech/geo-score](https://github.com/jianruntech/geo-score) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Ask one buyer question to AI engines and see whom the answers cite. **Who it is for:** A founder or content lead who wants to know, right now, whether ChatGPT, Perplexity, Gemini or Claude cite their company for a question a buyer would ask. **The problem:** A high readiness score does not show whether engines actually quote the site for the questions that matter to sales. **The outcome:** The engines' answers to your question and a list of the sources each one cites, including whether your site appears. ### Steps 1. Install the pinned release: `pip install geo-score==1.8.3` (inferred, check the README) 2. Export your own API key for at least one supported engine, such as OpenAI, Perplexity, Gemini, Anthropic or OpenRouter. 3. Ask one question about your site: `geo_score.py yourdomain.com --ask "your buyer question"` (inferred, check the README) 4. Check whether your domain appears among the cited sources and note which competitors or third-party pages are cited instead. ### Prompt to paste into your agent ```text Using the geo-score repo at jianruntech/geo-score, run geo_score.py on with --ask set to , using the API key already present in the environment. Expected output: each engine's answer and its cited sources. Verify that the report lists whether is cited. ``` ### Caveat The README says the sponsor relay has not been tested for citation measurements, and a relay may not pass web search and citations through unchanged, so check which key source you use. Risk, credentials: The ask command uses your own API keys for each engine, so store them as environment variables and keep them out of shared logs and repositories. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/jianruntech-geo-score/check-if-ai-engines-cite-site/ ## How to track how often AI engines cite your site each week with Geo Score Repo: [jianruntech/geo-score](https://github.com/jianruntech/geo-score) | Difficulty: Advanced | Time: 30 minutes | Basis: From the README Run a fixed question set weekly and compare cited rates and share of voice. **Who it is for:** A growth or SEO lead who needs to show whether changes to content or site structure move AI citations over time. **The problem:** A single query shows a moment in time, and it is hard to tell a real change in citations from noise. **The outcome:** A 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. ### Steps 1. Install the pinned release: `pip install geo-score==1.8.3` (inferred, check the README) 2. Write a fixed question list for your buyers and set your own API keys for the engines you use. 3. Run the watch command on the question set: `geo_score.py watch run` 4. Schedule the same command weekly with your scheduler of choice. 5. Compare reports with the diff function so you only act on changes the paired test supports. ### Prompt to paste into your agent ```text Using the geo-score repo at jianruntech/geo-score, run `geo_score.py watch run` against the question set for 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. Risk, credentials: Weekly runs spend your own API credits on each engine, so store keys securely and set a spending limit with each provider. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/jianruntech-geo-score/track-weekly-ai-citations/ ## How to fail a build when a site's AI readiness regresses with Geo Score Repo: [jianruntech/geo-score](https://github.com/jianruntech/geo-score) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Score the site on every push and fail the build on a regression or a zero gate. **Who it is for:** A web developer or DevOps engineer who wants AI readiness checked alongside other tests on each deploy. **The problem:** A robots.txt or rendering change can quietly remove a site from AI crawlers, and nobody notices until citations drop. **The outcome:** Each push is scored, and the build fails if the score regresses or a gate check drops to zero, with a job summary written for the run. ### Steps 1. Add the Geo Score GitHub Action to your workflow using the repository's action.yml, pointed at your site. 2. Set the target domain and any threshold the action accepts, as described in action.yml. 3. Push a change and open the job summary to read the score and check table. 4. Keep the check as a required status so a regression blocks the merge. ### Prompt to paste into your agent ```text Using the geo-score repo at jianruntech/geo-score, add its GitHub Action to a workflow that scores on each push. Expected output: a build that passes with the score in the job summary and fails on a regression or a gate at zero. Verify that a deliberately broken robots.txt line causes the build to fail. ``` ### Caveat The action checks public pages only and scores the site as crawlers see it, so changes that exist only behind a login will not appear in the score. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/jianruntech-geo-score/block-site-regressions-in-ci/