Query Generation
Build reusable query sets — company briefing, categories, and queries — then pick a set when you create an experiment.
Visibility experiments
Measure how often your brand appears in AI-generated responses across leading models.
Sentiment experiments
Understand how AI models describe and perceive your brand in their responses.
Reading results
Interpret mention rates, sentiment scores, citations, and AI-generated analysis.
Analytics
Compare executions over time with trends, baselines, and source concentration.
Scheduling
Automate recurring experiment runs so your data stays current without manual effort.
Visibility vs. sentiment — which should you use?
- Visibility
- Sentiment
Choose a Visibility Analysis experiment when you want to measure whether your brand is being mentioned in AI responses at all.Visibility answers questions like:
- “Does Perplexity mention us when users search for our category?”
- “How often do we appear vs. our competitors?”
- “Is our website being cited as a source?”
Creating a new experiment
Company details, experiment type, and queries now live on a query set. Create or edit those in Query Generation first. Creating an experiment then has two steps: Query set and Create.1
Create a query set (if you do not have one)
From the sidebar under Strategy, click Query Generation, then New query set. Enter company details, analyze the domain, review categories, aliases, and tracked competitors, generate or import queries, and Save query set.See Query Generation for the full walkthrough, including CSV import, Keyword Planner, and comments.
2
Open New Experiment
From the sidebar under Strategy, click Experiments. Then click New Experiment.
3
Step 1 — Query set
Pick a saved query set that already has queries. Experiment type, company, domain, aliases, and tracked competitors come from that set — you will not enter them again.The selector shows each set’s name, company, category count, and query count. After you select one, a summary shows company, domain, type/subtype, aliases, tracked competitors, and query counts. Use Edit to open the set in Query Generation, or Manage query sets to go to the list.If you have no saved sets with queries yet, create one in Query Generation first.Click Continue.
4
Step 2 — Create
Confirm the Experiment Summary — including company aliases and tracked competitors when the query set has them. Those names are saved on the experiment for competitor mention tracking. Then configure:
- Model Selection — choose which AI models to test. If you select GPT Instant or GPT Thinking, an Enforce Web Search switch appears. New experiments start with this on, so those models search the web before answering unless you turn it off.
- Location Information (optional) — country, region/state, and city for geo-targeted answers
Managing your experiments
Filtering and sorting
On the Experiments page, search experiments and filter by type, subtype, or archival status. Sort by creation date or name.Pinning
Pin important experiments to keep them at the top of your list. Click the pin icon on any experiment card to toggle the pinned state.Tags
Add tags to categorize and filter your work. Tags are editable from the experiment detail view.Archiving
Archive experiments you no longer actively track. Archived experiments are hidden from the default view but remain accessible via the archived filter. Archiving does not delete any data.Rerunning and scheduling
From an experiment detail page you can:- Rerun Experiment — start a new execution with the current configuration
- Schedule — set a recurring cadence (see Scheduling)
Experiment settings
Open Settings on an experiment to manage:- Web search — organization admins can toggle Enforce web search. When on, supported GPT models search the web before responding. New experiments start with this on. The change saves immediately and applies to future runs, not past executions.
- Company aliases — copied from the query set; you can still edit them here
- Competitors — pre-filled from the query set’s tracked competitors; edit names and aliases here
- Tracked URLs — or add the same URLs to several experiments from Settings → Tracked URLs
- Queries and categories
- Outreach excluded domains (visibility experiments)
Deleting
Delete an experiment permanently from the experiment detail view. This removes the experiment and all of its executions and results.What’s next?
Query Generation
Build and edit the query sets you pick when creating an experiment.
Visibility experiments
Configure tracked URLs, company aliases, geo-targeting, and model selection for visibility.
Sentiment experiments
Understand sentiment subtypes, action item sync, and how to interpret sentiment scores.
Analytics
Track how visibility and sentiment change across executions.
Scheduling
Set up automatic recurring executions to track changes over time.