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: The task involves handling a trigger related to a user request about a company dinner. First, I need to understand the user's intent, which is to add the dinner to their calendar and set a reminder. To approach this systematically, I will consider the steps: 1) Search for relevant emails to find details about the event, 2) Review existing calendar events to check for conflicts, 3) Extract date information from emails or look for available date info, 4) Confirm details with the user if any info is missing, and 5) Create the calendar event with an appropriate reminder. Since the context indicates that email content may contain details, I should begin by searching emails using relevant keywords. If necessary, I will read specific emails to clarify details. Throughout, I need to verify potential conflicts before creating the event and reminders, and seek user confirmation when any details are incomplete or uncertain.

Response: The first step is to search for emails related to the company dinner to gather details (such as date, time, location).