Opper

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.

Agents – cerebras/qwen-3-32b Task | Opper AI

Input Tokens

0

Output Tokens

0

Duration

0

Cost

0

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 retrieving all open orders for customer ID 'cust_42'. The 'database' tool's 'list_orders' method is the correct approach since it's designed to list orders by customer ID. The required parameters for this method are 'action' (set to 'list_orders') and 'customer_id' (provided as 'cust_42').

Response: {"tool": "database", "method": "list_orders", "params": {"action": "list_orders", "customer_id": "cust_42"}}