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

Your first step is to break down the problem and formulate a step by step plan. What is the plan?

Expected output

(1) Ask the user how many days before they want the reminder. (2) Use the email tool to search for emails about the yearly gathering. (3) Read the relevant email to extract the event date. (4) Use the calendar tool to add the event. (5) Check for any calendar conflicts. (6) Add the reminder X days before the event

Model output

Reasoning: The user’s request is to add the yearly company dinner to their calendar and set a reminder a few days in advance. The context indicates there is an email with more details, but the details themselves are missing. Therefore, my step-by-step plan must first locate that email to extract the date and any other relevant information, then create the calendar event and reminder accordingly.

Response: Step-by-step plan:
1. Search the user’s emails for any message containing the phrase “yearly company dinner” or similar keywords.
2. Read the identified email(s) to extract the event date and any additional details (time, location, dress code, etc.).
3. Check the user’s calendar for the extracted date to confirm no conflicts.
4. Ask the user how many days in advance they want the reminder (since they said “some days before” but did not specify).
5. Create the calendar event with the event name “Yearly Company Dinner,” the extracted date, and the user-specified reminder.
6. Confirm with the user that the event has been successfully added and the reminder is set.