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: The user wants to add the yearly company dinner to their calendar with a reminder. To accomplish this reliably, we need to: locate the relevant email for date and details, extract the event information, verify there are no scheduling conflicts, and then create the calendar event with the appropriate reminder. If any information is missing or ambiguous, we should ask the user. This step-by-step plan aligns with the tools available and ensures accuracy and user confirmation.

Response: Step 1: Search the user’s email for keywords like “yearly company dinner.”
Step 2: Read the identified email(s) to extract the event date, time, location, and any additional details.
Step 3: Parse and verify the extracted event information.
Step 4: Check the user’s calendar for conflicts around the proposed event date.
Step 5: If details are incomplete or conflicts exist, ask the user for clarification or alternative dates.
Step 6: Create the calendar event with the extracted name, date, and set a reminder a few days before.
Step 7: Confirm with the user that the event was added correctly.