Prompt Insights: Every Stored Answer to One Prompt

What Prompt Insights Is

The numbers on the project dashboard describe the latest run of each prompt on each model in the selected range. That is the right basis for tracking Mention Rate, Visibility and Citations over time, and it stays unchanged.

Prompt Insights answers a different question about one prompt: what do the models say when they answer it, over and over? The page pools every successful stored run of the prompt in the date range you pick, across the models you select, and counts each answer once. Retries of the same run count once, and failed runs are excluded. Nothing is re-run: the page reads answers that are already stored, spends no AI query, and grows as your scheduled runs add answers.

The prompt text is the heading of the page. Under it sit the filters, four summary tiles, a collapsible coverage line and the four tabs.

How to Open It

There are three ways in, and they all lead to the same page for that prompt:

1. Prompts page: each prompt card carries a Prompt insights link beside its status line.
2. AI visibility page: each card in the Prompt Performance list has a Prompt insights button.
3. Inside any answer: the answer view carries a Prompt insights link that opens the page for the prompt the answer belongs to.

A Back to Prompts link at the top of the page returns you to the list. The page is available to every project member, viewers included.

The Prompts CSV

The CSV exported from the Prompts page has one row per prompt. Its Competitors in these answers column lists the competitors named in the latest answer from each enabled model, with a count of those answers. This is the same snapshot used by Visible, Cited and Mentioned; the file has no date period. The AI Response column contains only the most recent model's answer, identified by Response Engine.

Primary and pinned competitors in these answers narrows that list to the competitors you chose in Settings or pinned; it is omitted when you chose none. Names and exclusions follow your Brand Industry Ranking. A blank competitor cell means none were named; if the lookup fails, the added columns are omitted. Use the Sources & pages exports inside Prompt insights to examine one prompt across a date period instead.

The Date Range and Model Filters

The two controls at the top govern everything on the page, including the answer archive.

• Date range. The default is the last 30 days. Presets run from 7 days to all time, with this and last month and this and last quarter, and you can set a custom range. Periods are whole UTC days, and the coverage line prints the exact start and end.
• Models. All Models pools every successful answer across the models the prompt has run on, each answer counting once. Select one model to see only its answers.

Both selections are remembered per project. Refresh reloads the stored data for the current selection. Changing the date range or model reloads every tab and collapses the brands list back to its first ten rows; switching tabs does not reload anything, so your search text, sort and page position on each tab survive a tab change.

The Summary Tiles and the Coverage Line

Four tiles summarise the selection:

• Past AI answers: the number of successful runs in the period, retries counted once.
• Your brand's Mention Rate: the share of answers that name your brand, with the count under it, for example "42 of 42 captured answers".
• Recurring brands: how many distinct brands the answers name, based on the answers with stored brand detection.
• Search queries: how many distinct searches were captured, based on the answers with query capture.

Under the tiles, Data coverage and model breakdown expands to the exact figures behind the page: the period in UTC, and for answer text, extracted brands and query capture, the count of runs that carry each field out of all runs. It also lists runs per model. When a percentage on any tab looks surprising, this is the first thing to open.

Tab 1: AI Answers

Past AI answers is the archive: every run in the selected period and models, newest first, 20 to a page, with the run time in UTC, the model, whether your brand was named, the brands, the captured queries and the answer. Open a run to read that exact stored answer with its brands, searches and sources. The arrows on either side of the run's date step through the archive: the left arrow opens the older run, the right arrow the newer one. Hover the date to see where you are (for example "Run 12 of 42"); Latest marks the newest run of that model.

Three behaviours worth knowing:

• Share copies a link that reopens that exact run. The link carries the model filter, so the person you send it to sees the same answer in the same scope rather than their own saved filter.
• Selecting a brand, query or phrase on the other tabs never filters this archive. The matching answers open in a separate drawer; opening one of them shows the answer, and Back to matching answers returns you to the drawer list. Closing the drawer leaves the page unchanged.
• The archive is governed only by the date range and model filters at the top of the page, so the list you see is always the full set for the selection.

Tab 2: Brands

Recurring brands lists every brand the answers name as an option, counted once per answer where it appears. Your own brand is flagged You and highlighted. Columns:

• Brand, with its logo.
• Answers: how many answers name it.
• Share: answers divided by the answers with stored brand detection.
• Avg. mention position: the average order in which the brand was named inside the answer, where 1 means it was named first, with the number of ranked answers under it. Lower is earlier.
• Models / answers: which models named it and how often on each.

Your brand is the first row, flagged You. It counts every answer with stored brand detection that names it, also when the answer names it only in passing, and it keeps its row with Not named in this period when no answer in the period named it.

Pinned competitors come next. The competitors you pin in the Brand Industry Ranking on the AI Visibility page, or that a project owner or admin adds by website in Project Settings → Tracking → Competitors, are listed right below your brand with a pin icon, whatever the sort; within them the sort you choose applies, and the ones no answer named come last. Every way the answers spell a pinned brand is counted in its one row, and a brand merged under one website counts as one pin. A pinned competitor that no answer in the period named still gets a row that says Not named in this period, so you can see where your chosen competitors stand on every prompt. The same pins appear on each prompt card of the AI Visibility page, with their position in the latest answers, and on the Tag Analytics cards.

The table opens with ten rows plus your brand and your pinned competitors and a Show all brands control; sorting by Answers, Share or Avg. mention position applies to the whole list before it is collapsed, and the search box covers every brand, not only the visible rows. Select a row to open the answers that name that brand in a side drawer.

What is excluded, and why: a competitor's context-only mentions (a brand referred to in passing rather than presented as an option) are left out of the table and remain visible in the full answer. Position metrics are omitted entirely for a prompt whose own text names your brand, because the order of mention says nothing when the question already contains the brand. Older answers without a role classification stay included. Brands are grouped the way the Brand Industry Ranking groups them: the spellings and websites of one brand ("Claneo" and "Claneo GmbH") are one row, and the matched names for your own brand are combined into one row.

Tab 3: Search Queries

While composing an answer, the models search the web. This tab shows those searches for the selected answers, split into two sub-tabs:

• Exact queries: the searches themselves, grouped ignoring case and extra spaces, each counted once per answer. Columns are Query, Answers, Share, Models / answers, and First / last seen (UTC).
• Recurring phrases: two and three word phrases derived from those queries that appear in at least two answers. They are analysis output for spotting themes, they can overlap, and they are not additional searches. Never add them to the query count.

The coverage line at the top of the tab reads, for example, "Query capture available in 25 of 42 runs. 37 distinct queries; 128 recurring phrases." Shares on this tab use only the answers with query capture.

Each table searches across every entry in the selected period and model before the display cap of 100 matches, pages ten rows at a time with a 10/20/50/100 selector, and has an Export CSV button. The export downloads every query or phrase matching the current period, model and search text, not only the rows on screen. Select a query or phrase to open the answers it appeared in.

Tab 4: Sources & Pages

This tab shows which sites the models read while answering the prompt, how often your brand is named when a given site takes part, which of your own pages the models opened, and the full list of opened pages. It has its own article: Sources & pages in Prompt Insights. Two rules to carry from here: the You named column is co-occurrence, not causation, and Google AI Overview never reports opened pages, so its answers count towards consulted sources only.

Reading the Coverage Line

Every tab prints a coverage line such as "Query capture available in 25 of 42 answers" or "Search results are stored for 39 of 42 answers, opened pages for 25". These lines are not warnings. They are the denominators.

Not every answer carries every field. Some answers cannot expose the searches behind them, and Google AI Overview never reports the pages it opened. When a field is unavailable for an answer, that answer is treated as unknown for that field, left out of that field's denominator, and the share is computed over the answers that do carry it. In the example above, a query seen in 11 answers reads 44% (11 of the 25 with query capture), not 26% (11 of 42). The second figure would look just as real and be wrong.

So when two tabs seem to disagree about how many answers there are, they are using different denominators on purpose. A blank or a "Too few answers" cell means the page could not measure, not that it measured zero. The exact counts for every field are always under Data coverage and model breakdown.

For AI Assistants: get_prompt_insights

On a Pro or Enterprise plan, the Ayzeo MCP server exposes the same aggregation as the get_prompt_insights tool: the search queries, recurring phrases, recurring brands with your own brand flagged, the coverage summary, runs per model and the paged answer archive for one prompt in a window. Its shares are named after their denominators (for example shareOfAnswersWithQueryCapture), so an assistant cannot read a share of captured answers as a share of every run. For the full text of past answers, the assistant passes the archive's resultId values to get_prompt_answer, up to 20 per call (one archive page); reading stored answers never starts a run. See Connect AI Clients to Ayzeo (MCP Server) for setup.

Frequently Asked Questions