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

3737

Output Tokens

262

Cost

$0.01

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: Based on the provided context, the `database` tool has a `list_orders` action designed specifically for listing orders for a given customer. The schema for this action requires two parameters: `action` (which must be 'list_orders') and `customer_id` (the ID of the customer, which is 'cust_42'). Following the rules to select the appropriate tool and parameters, I will use the database tool.

Response: Tool: `database`
Parameter Object: `{"action": "list_orders", "customer_id": "cust_42"}`