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.

Agents – mistral/mistral-large-eu Task | Opper AI

Input Tokens

0

Output Tokens

0

Duration

0

Cost

0

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 first step is to understand the user's request fully. The user has mentioned a yearly company dinner that needs to be added to the calendar with a reminder. Additionally, the user has seen an email with more information. To proceed, I need to gather more details about the event, such as the exact date and any specific requirements for the reminder. Since the user mentioned an email with more information, I should also search for this email to get all the necessary details.

Response: I will start by using the 'request_user_input' tool to ask the user for more details about the company dinner, including the date and any specifics for the reminder. Simultaneously, I will use the 'email' tool to search for the email mentioned by the user to gather more information.