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 previous plan by stating they no longer need a reminder, but still want the company dinner added to their calendar. My current step in the plan was to request the number of days before the event for a reminder, so I need to adapt to this new instruction. I will now skip setting a reminder and proceed to search for the event details and add it to the calendar. I'll use the context from the previous interaction to continue where I left off, which is searching for the date of the company dinner in the user's emails.

Response: Okay, I understand. Since you no longer want a reminder, I will skip that step. I will now search your emails to find the details for the company dinner and add it to your calendar.