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

3548

Output Tokens

274

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: The task requires listing open orders for customer cust_42. The database tool has a list_orders method that accepts customer_id as a parameter. This directly matches the requirement. Other tools (email, calendar, etc.) are irrelevant for data retrieval. Following instructions, I select the database tool with action 'list_orders' and customer_id 'cust_42'.

Response: Tool: database
Method: list_orders
Parameters: {"action": "list_orders", "customer_id": "cust_42"}