Actions
A ranked to-do list built from your own metrics, on a board whose cards close themselves when the data says the gap is fixed.
Actions is your ranked to-do list. MentionFlow reads your real metrics and hands you a board of the fixes worth doing first.
What it does
The recommendation engine scores every fix by how much it should help. Actions keeps that list as a board you work like any kanban: Suggested, then Planned, then In progress, then Done. A card you have started survives the next engine run. When the data shows the gap is fixed, the card closes itself and is marked "verified by data."
How to use it
Batch actions are on the way. Today the board supports per-card moves plus a bulk restore of dismissed cards. There is no multi-select bulk edit yet. We will update this page when batch actions ship.
Open Actions and work the board:
- Move a card by drag-and-drop or the per-card dropdown. Moves are optimistic. In demo mode they are local-only and not saved.
- Filter with the severity chips. They double as filters.
- Scope the view with deep links:
?prompt=and?source=open a filtered board. - Each card offers Brief, Evidence, Source, and Track.
Content briefs live at /actions/[promptId]/brief. A language model writes each brief from your real answers, citations, and knowledge base, and caches it once per prompt. Regenerating clears that cache and uses one of your monthly drafts. See Plans and quotas.
How it's computed
Fourteen pure rules score each recommendation. Priority = round(100 times impact times confidence). Severity follows from priority: high when at least 66, medium when at least 33, otherwise low. Confidence stops rising at five runs, so a recommendation can't out-rank the sample behind it.
The "verified by data" sync checks the board against each fresh engine run. It:
- inserts new recommendations,
- refreshes snapshots that changed,
- marks open cards resolved when the engine no longer emits them, and
- un-resolves a card if the gap comes back, unless you already closed it by hand.
Actions know what you published
The answer-gap and missing-page rules read your live articles from Content. When a prompt already has a live article with a published path, its card stops saying "publish a page". It names the page, shows how many citations that path has earned since tracking began, and turns the next step into a pickup problem: crawler access, a direct answer up top, internal links from pages engines already cite. A missing-page card for a prompt you have published closes on the next run, because the page now exists by MentionFlow's own record.
When the data closes an answer-gap or missing-page card and the prompt has a live article, the card keeps that article as its named cause: the "verified by data" badge reads "after your page", and the card detail shows the path and the citation trail it had when the gap closed, with a link to the article. Cards that close without a published page stay "verified by data" with no cause named. MentionFlow never claims credit for a gap it did not fill. The CSV export carries the same fact in a resolved_via column.
An open card is one whose status is not done or dismissed, and which is not resolved. Portfolio counts open actions the same way.
Limits
Actions is on every plan. Marketing presents it as a Growth feature, but it is not gated at runtime.