Segments

Segments define the scope for prompt evidence: which AI models to test, how often to run them, and what geography or language context they represent. They are the engine behind Cleotic's data collection -- each segment runs its prompts against the selected AI models on the configured schedule.

Why segments matter

Different AI models can have very different views of your brand. ChatGPT might mention you frequently while Claude barely knows you exist. A segment lets you configure exactly which models to test and at what frequency, so you get a clear picture for a specific slice of the market.

A segment is similar to a campaign, market, or recurring research programme. You can use multiple segments within a project to separate your monitoring -- for example, one segment for the United States and another for the United Arab Emirates, or one for launch-campaign prompts and another for weekly category checks.

Creating a segment

You can create segments during the project wizard or from the project's Project Settings page.

When creating a segment, you configure:

Name

A descriptive label for this segment (e.g., "Daily US English", "Weekly UAE English").

Geographic context

The country this segment is focused on, or Global. Segment geography is stored as global or a lower-case ISO 3166-1 alpha-2 country code such as us, gb, ae, or pk. Country values drive country-aware website fetch and assessment where supported.

Language

The language context for this segment (e.g., "English", "Spanish", "German"). Language remains a label for organising prompts and reporting context.

AI models

Select which AI models to query. Models are grouped by provider:

  • OpenAI -- GPT models (consumer and pro tiers)
  • Anthropic -- Claude models
  • Google -- Gemini models
  • And others as available

Each model uses a vendor:tier format internally (e.g., openai:consumer, anthropic:pro), but you'll see friendly display names in the selection interface.

Select at least one model. More models give you broader coverage, but each additional model means more API calls per prompt run.

Refresh frequency

How often your prompts run automatically:

  • Hourly -- Available on higher tiers that support more aggressive monitoring
  • Daily -- Good balance for most use cases
  • Weekly -- Suitable for long-term trend tracking with lower usage

When enabled, AI models can use web search to supplement their responses. This can surface more current information and more citations, but is only available on custom plans in the current UI.

Segment status

Like projects, segments can be active or paused:

  • Active -- Prompts run on the configured schedule
  • Paused -- Scheduled runs stop, but existing data remains accessible

Pausing a segment is useful when you want to temporarily reduce usage or focus on specific segments. You can pause and resume from Project Settings or the segment detail page.

The segment page

When you open a segment detail page, you see:

  • Stats grid -- Geographic context, language, number of models, refresh frequency, and prompt limit at a glance
  • Prompts -- All prompts in this segment, with options to add, pause, resume, and delete prompts where available. See Prompts.
  • Analytics details -- Visibility scores, share of voice, and model breakdown specific to this segment

Tips

  • Start with daily frequency. It gives you enough data to spot trends without excessive API usage.
  • Use multiple segments for different scopes. A "US English" segment and a "UK English" segment can reveal how AI visibility differs across markets.
  • Don't over-select models. Each model adds to your prompt run time. Start with the most popular models (ChatGPT, Claude, Gemini) and add others as needed.

Plan limits

Segment allowances depend on your plan and project configuration:

  • Business supports 3 segments per project
  • Starter supports 1 segment per project
  • Enterprise removes the per-project segment cap
  • Custom adds hourly monitoring and other advanced options

See Plans and usage for your current in-app usage meter and Pricing for the public comparison.