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

# 1. Answer a question

> Create a support Agent and inspect its first response.

[Support assistant tutorial](/learn/support-assistant)

Complete the [installation](/learn/installation), then save the code below as `support.ts`. This first checkpoint gives the model instructions without tools or order data.

## Complete checkpoint

```typescript support.ts theme={null}
import { Agent, openai } from "@agentium/core";

const agent = new Agent({
  name: "support",
  model: openai(process.env.OPENAI_MODEL ?? "gpt-6.1-sol"),
  instructions:
    "Help customers with orders. Ask for an order ID before discussing an order.",
});

try {
  const result = await agent.run("Where is my order?");
  if (result.status !== "completed") {
    throw new Error(`Run ended with status: ${result.status}`);
  }
  console.log(result.text);
} finally {
  await agent.close();
}
```

## Run it

```bash theme={null}
npx tsx support.ts
```

## Verify the result

You should see a request for an order ID. Exact wording varies. The model has no order database, so it cannot verify a shipment yet.

`result.status` tells you whether the run completed; text alone is not a success check. `finally` closes the resources owned by this Agent even if a request fails.

**Try changing the input:** ask for the delivery date of ORD-1042. Notice why instructions alone cannot establish the delivery date.

<Card title="Give it an order lookup" icon="arrow-right" href="/learn/tools">Continue to the next chapter.</Card>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.