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 with a new request, asking to focus only on adding the company dinner to their calendar and not to set a reminder. Here's how I will adapt my plan:
1. Cancel the current step of asking for the reminder preference.
2. Proceed directly to search the user's emails for information about the yearly company dinner.
3. Extract the event date and details from the relevant email.
4. Add the event to the calendar.
5. Check for any conflicts in the calendar.
6. Notify the user of any conflicts and confirm the event has been added.
7. Update the scratch pad to reflect the changes in the plan.

Response: I will cancel the reminder step and focus on adding the company dinner to your calendar. I'll search your emails for the event details and add it to your calendar, checking for any conflicts.