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.

Input Tokens

Output Tokens

Duration

Cost

Context

Input

The user has replied: "Three days before is fine."  According to the plan for the yearly company-dinner task, what is the next action?

Expected output

Call email.search_emails with a query such as "yearly company dinner" (optionally including the current year) to locate the relevant email(s) containing the event details, and store the returned email_id(s) for the subsequent email.read_email step.

Model output

Reasoning: The user has responded with 'Three days before is fine,' indicating their preference for the reminder timing. The previous steps involved waiting for user input on the number of days before the event to set a reminder. Since the user has now specified 'three days before,' I will interpret this as confirmation of the reminder lead time. As the next logical step, I should now proceed to search for the email containing details about the company dinner to identify the exact date, verify that date against the calendar for conflicts, and then schedule the event with a reminder set three days beforehand. Given the instructions, I will use the web search tool to find relevant emails or information, then extract the date, check calendar conflicts, and confirm the scheduling.

Response: The user has confirmed that a reminder three days before the event is acceptable. The next step is to locate the email with the company dinner details to determine the event date.