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 now replied, specifying their preference to receive the reminder three days before the event. According to the plan and the notes in the scratch_pad, the next step in the process is to search the user's emails for information about the yearly company dinner in order to extract the event date and key details. This information is necessary to proceed with creating the calendar event and setting the reminder as the user requested. Only after retrieving and verifying the correct event date and details can the agent appropriately add the event to the calendar with the correct reminder setting. Therefore, the immediate next action is to initiate a search of the user's emails (using the 'email' tool) with keywords likely to yield information about the yearly company dinner.

Response: The next action is to use the email search tool to look for emails related to the yearly company dinner in order to find the event's date and details.