> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gleap.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Frontend tools

Frontend tools let your AI agent execute actions directly inside your app — initiating a transfer, resetting a password, cancelling an order, etc.

Tools are defined on your AI agent in the Gleap dashboard (**AI agent > Tools > Frontend tool**) — name, description, parameters and execution mode all live there. Your app only registers a handler that executes the tool. Learn how to set up Frontend tools in our [help center article](https://help.gleap.io/en/articles/221-frontend-tools-let-the-ai-run-actions-in-your-app).

## Register a tool handler

Register the handler for a dashboard-defined Frontend tool. Use the tool's runtime name shown in the tool editor.

```csharp theme={null}
Gleap.RegisterAgentTool("send-money", async parameters =>
{
    var amount = parameters["amount"];
    var contact = parameters["contact"];

    // Run your own logic here.
    await BankingService.InitiateTransferAsync(amount, contact);

    // Return a string or any JSON-serializable object — the AI waits for this response.
    return "The transfer was initiated. The user must confirm it in the banking app.";
});
```

**Handler contract**

* The handler receives the parameters configured in the dashboard, filled with the values the AI collected. Values arrive as plain CLR types (`string`, `long`, `double`, `bool`, nested `IReadOnlyDictionary`/`IReadOnlyList`, or `null`).
* Return a string, or any JSON-serializable object (objects are serialized to JSON). The result is sent back to the AI, which uses it to reply.
* Async handlers are fully supported — the handler returns `Task<object?>`, and the AI waits for it. For a synchronous handler, return `Task.FromResult<object?>(result)`.
* Exceptions thrown by the handler are caught and reported to the AI automatically.
* If no handler is registered for a tool, the AI is informed so it can respond accordingly.

## Execution modes

Set per tool in the dashboard:

* `Auto` — the handler runs immediately when the AI calls the tool.
* `Ask before final execution` — the AI adds a confirmation button to its reply; the handler only runs after the user confirms.

## Migrating from `SetAiTools`

`Gleap.SetAiTools(...)` and the `AITool` / `AIToolParameter` types have been removed. Tools declared via `SetAiTools` could only return a static response to the AI — Frontend tools execute real code and return live results. Define your tools on the AI agent in the dashboard and register their handlers via `Gleap.RegisterAgentTool(name, handler)` instead.