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

You have just received a trigger with a user request. What is the first thing you do?

Expected output

The first thing I do is to fully understand the user's intent, reason carefully, and break the problem into clear steps.

Model output

Reasoning: I need to understand what the first step should be after receiving this user request trigger. The user wants to add a yearly company dinner to their calendar with a reminder, and they mentioned seeing an email with more information. Before I can create a calendar event, I need the specific date of the dinner and potentially other details like the time, location, and how many days before the event they want the reminder. Since the user explicitly mentioned receiving an email with more information, my logical first step should be to search for that email using the email tool to retrieve the necessary details. This approach will help me gather the required information before proceeding with creating the calendar event.

Response: The first thing I should do is search for the email containing details about the yearly company dinner. Since the user mentioned seeing an email with more information about the event, I'll use the email tool to search for emails related to the company dinner. This will help me gather the necessary information such as the specific date, time, location, and other relevant details that I'll need to properly add the event to their calendar and set an appropriate reminder.