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 task requires breaking down the user's request into a step-by-step plan to add the yearly company dinner to the calendar and set a reminder. The context provides information about the tools available and the user's request. Here is the plan:

Response: 1. **Clarify Details**: Use the 'request_user_input' tool to ask the user for the exact date of the company dinner and any specific time or location details.
2. **Search for Relevant Emails**: Use the 'email' tool to search for emails containing more information about the company dinner (e.g., date, time, location).
3. **Verify Calendar Availability**: Use the 'calendar' tool to check for any existing events on the same date to avoid conflicts.
4. **Create the Calendar Event**: Use the 'calendar' tool to add the company dinner to the calendar, including setting a reminder a few days before the event.
5. **Confirm with the User**: Use the 'request_user_input' tool to confirm the details of the event and reminder with the user.