Agents

AI agent reasoning and tool selection tests planning, tool choice, and self-diagnosis capabilities. These skills are crucial for autonomous ticket triage systems and complex agent workflows where models must decide which tools to use, plan multi-step processes, and diagnose when things go wrong. This represents some of the most challenging tasks as they require open-ended reasoning and decision-making.

Duration

Input Tokens

3539

Output Tokens

135

Cost

$0.00

Context

Input

You need to list all open orders for a specific customer whose ID is `cust_42`. Which tool/method do you choose and what parameter object do you send?

Expected output

Use the **database** tool with parameters {"action": "list_orders", "customer_id": "cust_42"}.

Model output

Reasoning: To list all open orders for a specific customer whose ID is `cust_42`, I need to use the `database` tool with the `list_orders` method. This method requires the `customer_id` parameter to specify which customer's orders to retrieve. The task is straightforward, and no additional context is needed beyond the provided information.

Response: I choose the `database` tool with the `list_orders` method. The parameter object I send is: `{"action": "list_orders", "customer_id": "cust_42"}`.