A stable panel, a useful comparison
Foliora derives buyer questions from what your business sells and the decisions your customers make. Keeping that panel stable lets you compare answers and cited sources across successive checks.
The panel is a measurement instrument, not a quota of work. Research and supported drafts cover opportunities within your site’s scope, including pages that do not map to a measured question.
Essential checks monthly. Pro checks weekly.
Each website has its own plan. Essential brings a monthly research and improvement cycle; Pro checks weekly for new opportunities, changed answers, and cited sources. Both include customer approval, publishing, and live verification.
Publishing a prepared change does not wait for the next research cycle. Once you approve, Foliora can publish and verify it. Follow-up observations remain separate from proof that the change is live.
Read the evidence behind the score
Question coverage and repeated sampling answer different questions. More distinct questions broaden the topics observed; repeated observations help reveal variability on a given question. Neither a small panel nor a single changed answer proves that a page edit caused an improvement.
A 25-question panel is a useful example: one question represents four percent of that panel. The reported denominator, sampled engines, and missing observations still matter. Read the individual answers and sources alongside any aggregate.
When a panel or measurement configuration changes, record the change and start a comparable baseline. A failed observation is unsampled, not evidence that the business was absent.
From questions to useful work
Foliora joins the questions with the site’s content, search demand, and findings to prioritize supported changes. Related issues become coherent page initiatives, rather than a bill for each generated fix.
You choose what to approve. Foliora can publish through Shopify, WordPress, Webflow, or a GitHub pull request; manual delivery and your own agent through MCP are also supported. Each site keeps its own cadence and plan.
Common questions
Does the measured panel limit the work Foliora proposes?
No. The panel is a stable set of buyer questions used to compare observations over time. Foliora researches supported opportunities throughout your site’s scope, whether or not a page maps to a measured question. Essential refreshes the cycle monthly; Pro refreshes it weekly.
Can I choose the questions myself?
You can read the panel and challenge anything in it, and a question that is wrong for your business is a signal worth acting on. What Foliora does not do is start from an empty box, because deciding what buyers ask and which of those questions your catalog can credibly answer is the research the service is supposed to perform, not a form for you to fill in before you have any data.
Wouldn't tracking more prompts give a more accurate score?
More distinct questions can broaden coverage, but they are not repeated observations of the same question. Interpret the panel’s scope, sample coverage, and answer variability together rather than treating a bigger prompt count as proof of accuracy.
How much does one citation move the score?
About four points on a twenty-five-question panel, two on fifty, one on a hundred. That is the arithmetic of the panel size and nothing more sophisticated is going on. It is stated here so you can check any movement we report against how many questions changed hands, rather than accepting a score with an undisclosed denominator.
What happens if the panel needs to change?
It gets changed, dated, and recorded, and the trend restarts from that point rather than being compared across the seam as though nothing happened. Silently amending the panel and continuing the same line is the most common way these numbers stop meaning anything.
How can I verify a score you report?
Every observation is stored with the engine, the question, the market, the date, the full response text, and the citation URLs. A score is recomputable from those records months later, and the individual responses are readable. If a vendor cannot show you the prompt, the date, the raw answer, and the citations behind a number, the number is decorative — that applies to us on exactly the same terms.