Prompts reference

Prompt fields

Field	Meaning	Values
Prompt text	The question sent to the AI assistants	Up to 1000 characters
Status	Whether the prompt is asked	Active, Suggested, Archived
Source	How the prompt was created	Manual, Suggested, Imported, Onboarding (created from your onboarding request)
Region	Market the prompt is answered for	See regions below; set to the project market when the prompt is created
Tags	Project tags for grouping and filtering	Any project tag
Brand status	Whether the prompt names one of your own brands, set by GripIQ’s automatic classification	Branded, Non-branded
Personas	Personas linked to the prompt	Any project persona; the row shows two, then “+N”

Only Active prompts are asked. You can edit a prompt’s text and status, and assign tags, in the app. Personas are linked for you by your account manager.

Regions

France, Germany, Belgium, Luxembourg, The Netherlands, United Kingdom, United States, Spain, Italy, Poland, Sweden, Austria, Switzerland, Ireland, Portugal, Denmark, Norway, Finland, Czechia, Flanders, Wallonia (Wallonie), Brussels.

Every prompt has a region. A new prompt gets the project market, and a prompt whose region is cleared falls back to it. When the project market changes, prompts on the old market move to the new one; a prompt set to another market keeps it. Each answer records the region it was generated for, and the answer detail shows that region as a badge.

Filters per tab

Tab	Filters
Overview	Date range, Brand (Branded, Non-branded), Tags, Models
Prompts	Search prompts, Status, Region, Tags, Personas
Answers	Date range, Tags, Models, region, sentiment, Only

Date-range options: week, month, 3 months, 6 months, year, all, custom. The default is month.

The Brand filter uses each prompt’s brand status. A prompt is classified again after you edit its text; until then it has no status and any Brand selection leaves it out.

The Overview and Answers filter rows end with a data-freshness line: Data as of the last scan · next scan the time until the next one. Before the first scan it reads Awaiting first scan.

Metric definitions

Metric	Definition
Visibility (KPI)	Percentage of answers in the date range that mention any of your own brands
Visibility (Rankings)	Each brand’s share of all brand mentions in the period; the column sums to 100%
AI share of voice	Your brand’s slice of the total brand-mention pool across all monitored brands; each answer counts at most once per brand
Position	Average ordinal place of the brand in the answers that mention it; 1 = mentioned first
Average sentiment	Average sentiment score of the answers in the range, from −1 to +1
Sentiment label	Above 0.3 = Positive; below −0.3 = Negative; otherwise Neutral
Top domains	Domains cited in answers; the count is the number of distinct answers referencing the domain, the percentage its share of all answers in the range
Trend badge	Comparison with the previous range of the same length

Brand mentions come from the automatic analysis of each answer, not from raw text matching.

AI assistants and models

Every scan asks each active prompt once per monitored assistant. Each assistant answers as if the person asking is in the prompt’s region and speaks the project language. For ChatGPT, Gemini, and Claude, GripIQ uses one model per assistant, chosen to match what that assistant serves its own users by default. Google AI Mode is the answer Google shows in AI Mode for the prompt.

Assistant	Provider	Answer collected
ChatGPT	OpenAI	Answer from the model ChatGPT serves by default
Gemini	Google	Answer from the model Gemini serves by default
Claude	Anthropic	Answer from the model Claude serves by default
Google AI Mode	Google	Google’s AI Mode answer for the prompt’s region, in the project language; no answer is stored when Google shows none

Google AI Mode is counted as its own assistant, separate from Gemini. The Models filter and the model badge on each answer show the assistant name (ChatGPT, Gemini, Claude, Google AI Mode), not the provider.

GripIQ keeps this in step with the assistants themselves: when an assistant changes the model it serves its users by default, GripIQ moves to that model with it. Answers are grouped per assistant, so a model update never splits your filters or metrics — you may only notice a shift in an assistant’s answers or trend line around the date it changed.

The Models filter lists only assistants that actually have answers in your project, and appears only when there is more than one.

Schedule

Interval	Prompts are asked
Daily	Once a day
Weekly	Once a week
Monthly	Once a month
Disabled	Never

The interval is a project setting that your account manager sets; you can see it on the Settings page under Scan schedule. There is no button to run a prompt on demand.

Web search and sources

When answering, the assistant may search the web, biased to the prompt’s region. The pages it consulted are stored per answer and shown under Sources. For Google AI Mode, Sources lists the pages Google cites in the AI Mode answer. The Top domains card is built from those citations.

Exports

Export	Where	Columns
Answers (filtered set)	Answers tab → Export CSV	Prompt, Answer, Model, Brands Mentioned, Sentiment, Date
Answers for one prompt	Prompt detail → Export CSV	Prompt, Model, Answer, Sentiment, Sentiment Score, Date

The filtered export is named ai-monitor-answers-YYYY-MM-DD.csv; the export for one prompt is named prompt-<id>-answers.csv. Export CSV is not shown to the Contributor role; see Team members.

Limits

• Add prompts dialog: at most 100 prompts per batch, 500 characters each.
• Prompt text when editing an existing prompt: 1000 characters.
• Additional instructions in the generate dialog: 255 characters.
• Count in the generate dialog: 1 to 10 prompts per run, and no more than the prompts still available on your plan.
• Recent answers on the prompt detail page: 15 per page.
• Top domains: the top 10 domains.
• Rankings: 5 brands per page.

The number of prompts your project may track is set by your plan. See Plans.