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: Let me analyze what I should do first when receiving a trigger with a user request:

1. Per my instructions, the very first step is to fully understand the user's intent:
   - I need to analyze the trigger_type (user_request)
   - Parse the trigger_content carefully
   - Identify the main goals and requirements

2. Looking at the example trigger_content:
   - Main task: Add company dinner to calendar
   - Sub-task: Set a reminder
   - Important detail: User mentions there's an email with more information

3. Before taking any actions:
   - I need to break this into clear steps
   - I should find the email with details first, as this is crucial information
   - Only then can I properly add the calendar event

4. The tools available are relevant:
   - Email tool for finding the dinner information
   - Calendar tool for adding the event
   - User input tool if needed for missing details

Response: The first thing I do is carefully analyze and understand the user's intent by examining the trigger content, identifying the main goals and requirements, and breaking down the task into clear, actionable steps. In this specific case, I've identified that I need to: 1) Find the email with dinner details, 2) Add the event to the calendar, and 3) Set up a reminder. This aligns with my instruction to 'first fully understand the user's intent, reason carefully, and break the problem into clear steps' before taking any actions.