# Experiment types

Compare experiment types available at the project, message, and content levels.

Compare experiment types available in Airship:

| Experiment type | Scope | Description | Channels |
| --- | --- | --- | --- |
| [Holdout Experiment](https://www.airship.com/docs/guides/experimentation/holdout-experiments/) | Project | Exclude a group of users from all messages, or from messages with specific [Campaign Categories](https://www.airship.com/docs/reference/glossary/#campaign_categories), to measure the overall impact of your messaging program. | App, Web, Email, SMS, Open channel |
| [Feature Flag rollout](https://www.airship.com/docs/guides/experimentation/feature-flags/) | App or web content | Release a feature to a targeted audience and/or percentage, then monitor interaction. | App, Web |
| [Feature Flag A/B test](https://www.airship.com/docs/guides/experimentation/feature-flags/) | App or web content | Compare audience behaviors when a feature is hidden or present, or experiment with different feature experiences. | App, Web |
| [A/B test](https://www.airship.com/docs/guides/experimentation/a-b-tests/types/) | Message | Compare message variants to identify the best-performing option. | App, Web, Email, SMS, Open channel |
| [Intelligent Rollout](https://www.airship.com/docs/guides/experimentation/intelligent-rollouts/) | Message | Maximize conversions by automatically optimizing message campaign performance in real time. | App, Web, Email, SMS, Open channel |
| [Sequence Control Group](https://www.airship.com/docs/guides/experimentation/control-groups/) | Message | Exclude a percentage of a [Sequence](https://www.airship.com/docs/reference/glossary/#sequence) audience from receiving messages to measure performance or pace a controlled rollout. | App, Web, Email, SMS, Open channel |