# Usage Examples

Once the MCP server is connected in your AI assistant (see [Setup](https://docs.absmartly.com/docs/APIs-and-SDKs/MCP-Server/setup.md)), you can drive ABsmartly with plain language. Here are prompts that map cleanly to the underlying [tools](https://docs.absmartly.com/docs/APIs-and-SDKs/MCP-Server/tools-reference.md).

## Discover what's available

```text
What ABsmartly operations can you help me with?
```

The assistant will call `discover_commands` and summarize the available groups.

## List running experiments

```text
Show me all running experiments
```

## Create an experiment from a template

```text
Create a new A/B test called "checkout_cta_test" with Control and Blue Button
variants
```

The assistant will draft a markdown template, show a preview, then create the experiment after you confirm.

## Full lifecycle

```text
Create an experiment, move it to ready, start it, then show me its details
```

## Feature flags

```text
Create a feature flag called "dark_mode" and start it
```

## Clone and modify

```text
Clone experiment 42 as "checkout_v2" and update the traffic split to 70/30
```

## Compare experiments

```text
Show me the differences between experiments 42 and 43
```

***

## Tips

* Destructive actions, such as `start`, `stop`, `archive` and `delete`, always pause for a confirmation step. You'll see the planned operation before it runs.
* Experiment creation from templates also pauses with a preview of the resolved payload — review the warnings before confirming.
* If you're unsure which command an assistant should call, ask it to "browse the ABsmartly commands first" — that triggers `discover_commands` and gives the model the right context before acting.
