Run
One pass over your queries. A run usually asks every query that is being asked, of every assistant that is on, as many times as your repetitions setting says. Pages show the latest run that finished with an answer.
A run is one pass over your query bank. Fond asks every assistant turned on for your website every query that is being asked, as many times as your repetitions setting says.
A run started through the REST API with a list of queries asks only those queries. If it becomes the latest run, its figures cover only those queries.
When runs happen
On a plan with ongoing monitoring, Fond runs your queries on a schedule, at about the same hour each time. The free audit plan has one run, which Fond starts when you finish the website setup. You can also click Run Now on the Query Results page, within the run ceiling of your plan. A website can have one run in progress at a time.
Each run records the assistants, models and market that it used, so a change to a setting applies from the next run.
Failed requests
Fond leaves a failed request, such as a timeout, out of the rates that count answers. A run where every request failed is not in your analytics at all.
Which run is the latest
The overview and every analytics page choose the same latest run. It is the newest run that:
- finished, as Completed or Completed with errors
- has at least one answer that came back
- is not hidden
When two runs have the same date, the run that started later is newer. A page limited to a date range looks only in that range.
How it differs from a query
A query is one question. Its figures for a run come from the answers of that run to the query.
Related terms
Query
A question that Fond asks AI assistants for you, written the way a shopper asks it. Fond measures every visibility, share of voice and competitor figure over your queries.
Share of voice
How often AI answers mention your brand in each group of queries, by query tier or by your topic clusters. A query counts once if any answer to it mentioned you.