# AI use cases for Geolook (aigclink/geolook) Repo: [aigclink/geolook](https://github.com/aigclink/geolook) | Use cases: 4 | Page: https://dedupedai.com/use-cases/aigclink-geolook/ An open-source, self-hosted dashboard that runs GEO work for one brand: sampling AI engines, auditing the site, writing implementation tickets, and verifying the results. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Find out why AI engines never mention your brand: https://dedupedai.com/use-cases/aigclink-geolook/diagnose-ai-engine-absence/ - Turn GEO gaps into tickets and check that fixes worked: https://dedupedai.com/use-cases/aigclink-geolook/turn-geo-gaps-into-verified-tickets/ - Sample AI engines by hand with no API keys: https://dedupedai.com/use-cases/aigclink-geolook/manual-ai-sampling-without-api-keys/ - Build a GEO client package from one run: https://dedupedai.com/use-cases/aigclink-geolook/client-geo-delivery-package/ ## How to find out why AI engines never mention your brand with Geolook Repo: [aigclink/geolook](https://github.com/aigclink/geolook) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Sample AI answers, audit the site, and get a gap diagnosis for one brand in about 30 minutes. **Who it is for:** A marketing lead whose brand is missing from AI answers to category questions like best tools for X. **The problem:** AI engines leave the brand out of answers, and the team has no way to tell whether the cause is the site, the content, or the channels AI cites. **The outcome:** A dashboard showing mention rate, rank, and citation share per engine, plus a four-layer site audit and gap diagnosis that names what to fix first. ### Steps 1. Run `pip3 install requests beautifulsoup4 lxml` to install the three required packages. 2. Run `git clone https://github.com/aigclink/geolook.git` and then `cd geolook`. 3. Run `python3 scripts/geo.py new --url https://example.com --market` with your brand URL to start a full run. 4. Run `python3 scripts/geo.py ui` and open http://127.0.0.1:8765 to review the Status and Diagnosis pages. ### Prompt to paste into your agent ```text Use the geolook repo at to run a full GEO diagnosis for . Report the mention rate, the diagnosis type for each buyer question, and the first-fix order from the four-layer audit. Verify that the dashboard at http://127.0.0.1:8765 loads and that the diagnosis page lists the Access layer result. ``` ### Caveat This is a single-machine tool with no accounts or team collaboration, and the suspected-negative flags are leads for human review, not verdicts. 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/aigclink-geolook/diagnose-ai-engine-absence/ ## How to turn GEO gaps into tickets and check that fixes worked with Geolook Repo: [aigclink/geolook](https://github.com/aigclink/geolook) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Create implementation tickets with acceptance criteria and let re-crawls and sampling decide if each fix is done. **Who it is for:** An SEO or content lead who has a diagnosis but no one executing the recommendations. **The problem:** Advice piles up without an owner, and nobody can prove that a change helped AI engines. **The outcome:** Structured tickets with owner, effort, risk grade, and acceptance criteria, each with a progress bar from first-measured to target, and automatic reopening if a regression appears. ### Steps 1. Complete the setup and first run from the diagnosis use case, then run `python3 scripts/geo.py ui`. 2. Open the Action area and review the generated tickets, sorted by priority and risk grade. 3. Assign owners and work the tickets, using the content workbench for drafts and the deploy assets for llms.txt and JSON-LD. 4. Re-run sampling on a schedule, or run `./scripts/service.sh install` on macOS so scheduled re-runs keep firing. 5. Check the Results page for per-question before and after comparisons and the verification history. ### Prompt to paste into your agent ```text Using the geolook repo at , read the open implementation tickets for and draft the acceptance criteria check for each one. Output a list with ticket name, current measured value, target value, and pass or fail. Verify that the list matches the progress bars shown in the Action area. ``` ### Caveat Automatic verification depends on re-crawls and sampling rounds, so the progress reflects only the metrics the tool can measure. 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/aigclink-geolook/turn-geo-gaps-into-verified-tickets/ ## How to sample AI engines by hand with no API keys with Geolook Repo: [aigclink/geolook](https://github.com/aigclink/geolook) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Use a weekly buyer-intent sheet and the Chrome sampling assistant to collect AI answers without paying for API access. **Who it is for:** A small team that wants AI engine data but has no engine API budget, or that needs to sample engines without public APIs. **The problem:** Many important engines have no API, and sampling them by hand is slow and inconsistent. **The outcome:** A weekly buyer-intent queue that the Chrome extension fills in and submits back to the local dashboard as samples, cutting a weekly check from about 30 minutes to about 10. ### Steps 1. Run `git clone https://github.com/aigclink/geolook.git` and `pip3 install requests beautifulsoup4 lxml`, then skip the engine key step. 2. Run `python3 scripts/geo.py ui` to start the dashboard. 3. Run `python3 scripts/geo.py sample-sheet --intent buyer --limit 20` to export the weekly buyer-intent sheet. (inferred, check the README) 4. Load the extension/ folder as an unpacked Chrome extension and open its side panel to work through the queue. 5. Launch the disposable sandbox with `./extension/sandbox.sh` so each session starts clean. (inferred, check the README) ### Prompt to paste into your agent ```text Using the geolook repo at , export the buyer-intent sample sheet and list the 20 questions with their intent group. Confirm that the Chrome extension side panel shows the same queue, then report how many samples are still missing for this week. ``` ### Caveat Automated sampling is skipped without keys, and the auto-run mode carries ToS risks that the project documents in its own README. Risk, credentials: Persistent logged-in profiles for engines that need accounts keep login sessions on your machine, so protect the profile folder. 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/aigclink-geolook/manual-ai-sampling-without-api-keys/ ## How to build a GEO client package from one run with Geolook Repo: [aigclink/geolook](https://github.com/aigclink/geolook) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Produce a diagnosis report, strategy, execution plan, ticket CSV, and acceptance sheet for a client from one project. **Who it is for:** A GEO consultant or agency that bills clients for diagnosis and implementation work. **The problem:** Packaging GEO findings into client-ready files takes hours of manual work after each audit. **The outcome:** An HTML and CSV delivery package with a diagnosis report, strategy, execution plan, ticket CSV, and acceptance sheet, plus a one-page summary for leadership. ### Steps 1. Run `pip3 install requests beautifulsoup4 lxml` and `python3 scripts/geo.py ui`. 2. Create the client brand project with `python3 scripts/geo.py new --url https://example.com --market`. 3. Wait for the full cycle to finish, then open the Results page. 4. Export the complete client delivery package, which includes the HTML report and the CSV files. ### Prompt to paste into your agent ```text Using the geolook repo at , generate the full client delivery package for . List each file produced, confirm the ticket CSV row count matches the open tickets on the Action page, and report any section that came out empty. ``` ### Caveat The package reflects only the data the tool could measure, so an unsampled engine appears as unmeasured rather than with a 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/aigclink-geolook/client-geo-delivery-package/