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: First, I will locate the email containing details about the yearly company dinner. Then, I will read it to extract the date, time, and any other relevant information. If something is missing, I will explicitly ask the user to fill in the gaps. Next, I will check for any potential conflicts on the calendar for that date. Finally, I will create an event in the calendar with the correct name, date, and a reminder set for a few days beforehand. This systematic approach ensures no key detail is overlooked.

Response: Here is the step-by-step plan:
1. Search for the relevant email using keywords such as 'company dinner' or 'yearly dinner'.
2. Read the identified email to extract the dinner's specific date, time, and location.
3. If any critical detail is missing, use the user input tool to request further clarification from the user.
4. Check the calendar to make sure there are no scheduling conflicts for the chosen date.
5. Add the dinner event to the calendar with a reminder a specified number of days before.
6. Confirm the final event details with the user, ensuring everything is correct.