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: Okay, I need to create a plan to address the user's request to add the yearly company dinner to their calendar and set a reminder. Here's my plan:

1.  **Understand the user's intent:** I already understand the main goal is to add the event and a reminder.
2.  **Gather information:**
    *   Search for emails related to the company dinner to find the date, time, and any relevant details.
    *   If the date is not found in the email, ask the user for the date and time.
3.  **Create the calendar event:** Use the calendar tool to add the event to the user's calendar.
4.  **Set a reminder:** Set a reminder for the event a few days before, using the calendar tool.
5.  **Confirm with the user:** Confirm with the user that the event has been added and the reminder is set.


Response: The plan involves searching for relevant emails, extracting event details, creating a calendar entry, setting a reminder, and confirming the action with the user.