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's initial request was to add the company dinner to their calendar and set a reminder. The agent was in the process of fulfilling this request by asking for the number of days before the event they would like to receive the reminder. However, the user has now interrupted with a new instruction to disregard the reminder and just ensure the company dinner is on their calendar. The agent must adapt its plan to align with the user's updated request. The agent will stop the process of setting a reminder and focus solely on adding the company dinner event to the calendar.

Response: {"action": "create_event", "params": {"event_name": "company dinner", "date": "<date extracted from email>"}}