Home / Claude Certified Developer – Foundations / Objective 1.2

Domain 1: Agents and Workflows · 15% of the exam · Full exam outline

1.2 Agent Construction with Claude

What this objective covers · 5% of the exam

Methods, tools, and platforms for constructing Claude agents, including the Claude Agent SDK, custom agent loops and harnesses, managed agent deployment models (self-hosted vs. Anthropic- hosted), and hooks for deterministic actions.

Practice questions

Question 1easy

An agent's refund tool is described only as "Issues refunds." Which rewritten description follows the guidance for a tool that changes data?

Included in Sample: sample every domain.See plans

Choose an answer to check it. Afterward, select any option to review its explanation.

This widens the trigger instead of restricting it, inviting calls on any payment mention without checking the order first.

A restrictive description tells Claude what must be true before the call and what the tool is never for, which narrows when a data-changing tool gets selected.

Pointing to an external document gives the model nothing to act on; the conditions and exclusions must be in the description itself.

This adds detail about how the tool works but still gives no precondition and no limit on when it should not be called.

Question 2easy

An agent first drafts a multi-step plan for reorganising a shared drive and then carries it out. The team's main worry is that a flawed plan will lead to a wrong result. Where should a human check go?

Included in Master: master every domain.See plans