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

USER INTERRUPTION: The user says, "Actually, never mind about the reminder — just make sure the company dinner is on my calendar."  What do you do to adapt your plan?

Expected output

I will revise the plan by removing the reminder step entirely, then proceed to: (1) search and read the relevant email to obtain the dinner date, (2) check for calendar conflicts, (3) create the event with calendar.create_event **without** the reminder_days_before parameter, and (4) inform the user of any conflicts and confirm the event has been added.  What matters is that the plan is explicitly updated and no reminder is scheduled.

Model output

Reasoning: The user has interrupted the current plan and modified their request. The original request was to add a company dinner to the calendar and set a reminder. The user has now stated "never mind about the reminder — just make sure the company dinner is on my calendar." This means I should proceed with adding the event to the calendar but omit the reminder. I need to adapt my plan by removing the step related to setting a reminder. The subsequent steps should focus on finding the event details and adding it to the calendar without a reminder. I will continue by searching emails for company dinner information and then add the event to the calendar.

Response: Understood. I will make sure the company dinner is on your calendar and will not set a reminder for it. I'll proceed with finding the event details from your emails and adding it to your calendar.