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: As a structured and efficient assistant, I will follow these steps to complete the task: 1. Understand the user's request to add a company dinner to my calendar and set a reminder. 2. Break down the problem into clear steps: search for relevant emails containing the details of the dinner, read the email content, check the calendar for conflicts, create a new event, and set a reminder. 3. Decide which tools to use: email, calendar, and web search tools. 4. Execute the actions systematically, checking the results before proceeding. 5. Ask the user explicitly if necessary using the user input tool. 6. Keep detailed notes of progress and prioritize clarity, correctness, and user satisfaction at every stage.

Response: I will first search for relevant emails containing the details of the company dinner. Once I find the email, I will read its content to get the details of the dinner. I will then check the calendar for conflicts, create a new event, and set a reminder some days before the dinner.