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

# Sending commands

> How to send prompts to your AI agent through Telegram and work with the streaming output.

Once your agent is paired and running, controlling it is as simple as sending a Telegram message. Type a prompt in natural language and the agent starts working immediately. Output streams back to Telegram in real time.

## Basic usage

Open Telegram, find the RemoteAgent.CHAT bot, and type any prompt:

```
List all the files in this project and summarize what each one does
```

```
Fix the TypeScript error in src/api/users.ts
```

```
Add input validation to the POST /api/products endpoint using Zod
```

```
Write unit tests for the authenticate() function in lib/auth.ts
```

```
Refactor the database queries in services/orders.ts to use transactions
```

The agent begins processing immediately. You see output appearing progressively in Telegram — each chunk of text arrives as the AI produces it, so you can read the beginning of a long response before it is finished.

## Streaming output

Output is streamed in real time from your agent to Telegram. For long responses, messages are split automatically at Telegram's 4096-character limit. You may see multiple messages appear in sequence for a single command.

<Note>
  Streaming means you see results as they are produced — not all at once at
  the end. For a typical "fix this bug" task, you will often see the AI's
  reasoning, the file it is editing, and the final diff, all appearing
  progressively within a few seconds.
</Note>

## Aborting a running task

If you want to stop the agent mid-task — for example, if it is taking too long or going in the wrong direction — send:

```
abort
```

The agent receives the abort signal and terminates the current runner process. You receive a confirmation message. The agent then returns to the idle state and is ready for the next command.

<Warning>
  Aborting stops the AI mid-execution. If the runner was in the middle of
  writing a file, the file may be in a partial state. Check your working
  directory after aborting if you used a runner with file-write capability
  (claude-sdk, claude-code, aider).
</Warning>

## Continuing a task

When the agent is waiting for your input — for example, if it asked a clarifying question — just reply naturally with your next message. The agent will automatically resume from where it left off.

There is no explicit `continue` command. If the agent is waiting, any message you send continues the task.

## Examples by category

### Code review

```
Review the changes in the last git commit and point out any issues
```

```
Check auth.ts for security vulnerabilities
```

### Bug fixing

```
I'm getting a 500 error on POST /api/checkout — fix it
```

```
The tests in __tests__/cart.test.ts are failing — investigate and fix
```

### Feature development

```
Add a rate limiter to the /api/telegram route — max 10 requests per minute per user
```

```
Create a new API endpoint GET /api/stats that returns total session count for the current user
```

### Explanation

```
Explain what the realtime.ts file does
```

```
What does the pairing flow do step by step?
```

### Git

```
Show me the diff since yesterday
```

```
Commit all staged changes with a meaningful commit message
```

## Message length and splitting

Telegram has a hard limit of 4096 characters per message. RemoteAgent.CHAT handles this automatically:

* Output is split into consecutive messages at the character boundary
* Code blocks are preserved — splits never happen in the middle of a code fence when possible
* Very long diffs or file listings may produce several messages in sequence

There is no limit on how long a task can take or how much output it can produce. The relay will keep forwarding chunks as long as the runner is producing them.

## When the agent is busy

If you send a command while the agent is still processing a previous one, the new command is queued. You will receive a message like:

```
Agent is busy — command queued. Send "abort" to cancel the current task.
```