potato
Free Easy AI visibility check - measure how often a brand is mentioned & cited in Claude's web-search answers. Deterministic, reproducible, runs 100% locally, $
What is potato?
Free Easy AI visibility check - measure how often a brand is mentioned & cited in Claude's web-search answers. Deterministic, reproducible, runs 100% locally, $0 mock by default.
Overview of potato
What it is
Potato is a free, open-source tool that measures how visible a brand is inside AI web-search answers. It supports Claude, ChatGPT (OpenAI), Gemini, Perplexity, and Grok (xAI) — 27 models in total, any subset of which can be selected. The tool asks each chosen AI the same fixed set of frozen questions, collects every brand mention and source citation, then scores them with deterministic rules. No AI judge is used for scoring. The result is one reproducible, auditable report per engine, plus a side-by-side comparison page. Engines are never blended into one score. Every number carries a confidence interval.
Key features
- Deterministic scoring with no AI judge — every counted number comes from fixed rules, not a model's opinion.
- Three evidence tiers: mentioned → cited → verified. Only verified entries (where Potato fetched the cited page and confirmed it is reachable and mentions the brand) enter the core score.
- Independent citation check — Potato re-fetches third-party pages the AI cited and checks them itself for dead links and mismatches.
- Clean-room probes — every call is fresh with no history, no personalization; region, language, and temperature are pinned.
- Honest uncertainty — every ratio is shown with a Wilson 95% confidence interval. When two brands' intervals overlap, the tool says they are not distinguishable.
- Side-by-side comparison — each engine gets its own report, budget cap, and bill; no combined score or cross-engine ranking.
Use cases
Brands and marketing teams can use Potato to get a reproducible, auditable measurement of how often their brand is mentioned and cited in AI web-search answers. It is suitable for tracking brand visibility across multiple AI engines, comparing owned vs earned citations, and understanding share of voice in AI-generated responses. The tool is designed for deterministic, non-personalized, national-level measurements.
Getting started
On Windows, download AI-Visibility-Easy-Tool-windows.zip from the Releases page, unzip the whole folder, and double-click AI-Visibility-Easy-Tool.bat. A console window opens and the browser launches a wizard. Follow the 3 steps: enter brand info, draft and review the question set, then run the free mock preview ($0) or a real run. For developers, macOS, or Linux:pip install -e .[dev]aivis gui
License and pricing
Potato is open source under the MIT license. The free mock preview costs nothing and requires no API key. Real runs use the user's own API keys and incur actual API costs per engine, shown as a bill when the run finishes.
Based on the project's public README and repository metadata.