Agents – cerebras/llama-4-maverick-17b-128e-instruct Task | Opper AI

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

0

Output Tokens

0

Duration

0

Cost

0

Context

Input

The user has replied: "Three days before is fine."  According to the plan for the yearly company-dinner task, what is the next action?

Expected output

Call email.search_emails with a query such as "yearly company dinner" (optionally including the current year) to locate the relevant email(s) containing the event details, and store the returned email_id(s) for the subsequent email.read_email step.

Model output

Reasoning: The user has responded with 'Three days before is fine.' Now, according to the plan outlined in the context, the next step is to search emails to find the yearly company dinner date. The agent has already asked the user for the number of days before the event they want a reminder and has received the input. The next action is to proceed with searching the emails for information about the company dinner.

Response: The next action is to search emails to find the yearly company dinner date.