ChatGPT Plugin

Otter

Run and analyze A/B tests

Brand: Unknown

Category: Pending
Primary Subcategory: Pending

Integration details

Description

Connect your Otter account to manage website A/B tests and understand experiment results. Find projects, check installation instructions, inspect pages for visual changes, create redirect or visual experiment drafts, manage experiment status, and read results. Results use Otter's server-side statistical interpretation, including Bayesian and frequentist analysis. You choose which Otter account to connect and approve its permissions; access remains limited by your current role. An active Otter account is required. Website changes require the Otter SDK to be installed. Creating a draft does not launch it. You can revoke the connection from Otter's Connected apps page.

Integration type: Plugin
Verification status: Not applicable
Platform: ChatGPT
Category: Pending
Primary Subcategory: Pending
Secondary Subcategories: None listed
Brand: Unknown
Access: Account required
First tracked: 2026-10-22
Tool count: 34
Geography: US

Agent DiscoverabilityChatGPT Plugin Discovery Score

ChatGPT organic discovery is live

Your score is coming

ChatGPT now suggests Plugins on its own when they match a user's request.Your Plugin Discovery Score measures how often yours appears, and it will show here as soon as it’s ready.

ChatGPT recommends Airtable when a user asks it to update a CRM. — ChatGPT surfaces Airtable because it matches the user's request.

Primary Subcategory

Competitive lineup

No Primary Subcategory assigned yetOnce Otter has a Primary Subcategory, the Plugins and Connectors it competes with will appear here with their scores.

Tools

34 tools agents can invoke

Archive a completed experiment.
Complete a running or paused experiment.
Create an A/B test experiment with variants, changes, goals, and targeting in one call. It is saved as a draft and does not run unless start_immediately is true, which runs launch preflight and starts it on the live site.
Create a new project with a name, URL, and platform. Requires an unrestricted API key (not project-scoped).
Delete a draft experiment. Only draft experiments can be deleted.
Permanently delete a project and all its experiments. This cannot be undone.
Get account details and plan information.
List all team members on the account.
Get plan limits and current usage.
Get full experiment details including variants, goals, and targeting rules.
Read launch status and current-configuration 7-day sampled change/JS health. These are diagnostic sampled executions, not unique visitors or statistical results. Requires results:read.
Get full results across all goals with optional segment filters.
Get a simplified summary for the primary goal with optional segment filters.
Get daily time series data for charting with optional segment filters.
Read current launch checks and duration assumptions before starting or resuming. Unknown verification is a warning; only explicit customer A/A intent may acknowledge identity.
Mint signed human preview links for saved variants. Requires a verified snippet and a concrete matching URL. No Otter conversion tracking; a settled preview does not prove startup timing.
Get details for a specific project by ID.
Get installation metadata, SDK snippets, and verification status for a project.
Get aggregate statistics for a project, including lifetime totals and last-30-day metrics.
Load one of the project's own pages in a real browser and return its elements with working CSS selectors. Call this BEFORE authoring visual changes: a selector that matches nothing applies no change and fails silently, leaving the variant identical to the control. Use the returned selector values verbatim.
List supported experiment types.
List experiments for a project, optionally filtered by status.
List supported goal types.
List all projects accessible to this API key. Returns paginated results.
List available targeting fields and operators for building targeting rules.
List supported visual change actions.
Pause a running experiment. New visitors will not be assigned while paused.
One-step creation of a redirect A/B test.
One-step creation of a visual A/B test with element changes.
Resume a paused experiment.
Start a draft experiment. Requires at least 2 variants and 1 goal.
Update a draft or paused experiment's configuration; on a paused experiment, include existing variant, change, and goal IDs to keep them. Its status is unchanged unless start_immediately (draft) or resume_immediately (paused) is true, which runs launch preflight and runs it on the live site.
Update a project. Only provided fields are changed.
Verify saved visual/personalization challengers with the real SDK mutations in fresh desktop/mobile contexts. Persists current configuration evidence; partial/unknown runs cannot pass. At most four variant/viewport combinations per call. Requires experiments:write.

FAQs

Otter ChatGPT Plugin FAQ

How the directory, categories and Discoverability Score work.

Read the methodology

How do I improve Otter's ChatGPT Plugin discoverability?

The levers are the listing surface agents actually read: names, descriptions, keywords, tool metadata, and registry health. Which lever matters depends on where discovery breaks, which is what continuous measurement shows.

Where is this profile measured?

This profile uses the geography attached to the latest public registry snapshot: US. Locale tags are intentionally omitted.