CCDV-F - Agents and Workflows - Section 1.2

Construct Claude agents using the available methods, tools, and platforms.

Published skill weight 5.3 percent. Covers the Claude Agent SDK, custom agent loops and harnesses, managed agent deployment models including the choice between self-hosted and Anthropic-hosted, and hooks for making an action deterministic rather than leaving it to prompt compliance.

Claude Agent SDKcustom agent loops and harnessesself-hosted versus Anthropic-hosted deploymenthooks for deterministic actions

Practice question for this objective

Free sampleAgents and Workflowsmedium

A platform group must ship three internal agents in one quarter: a log triage agent, a documentation agent and a release-notes agent. All three need the same core behaviour, namely an agentic loop that calls tools, handles errors and manages a growing context. The group has two engineers and no appetite for maintaining shared infrastructure of its own. Which construction approach best fits that staffing constraint?

  • AWrite one bespoke harness in-house that all three agents import, implementing the loop, tool dispatch and context handling to the group's own specification.
  • BBuild the log triage agent on the Claude Agent SDK and hand-roll the other two, since documentation and release notes are simple enough to run as single model calls.
  • CRun the three agents as subagents beneath a coordinator agent that decides which of them handles each incoming request and supervises the work they return.
  • DBuild all three agents on the Claude Agent SDK, which supplies the loop, tool invocation and context handling, and write only the tools and prompts that differ between the three. Correct
Reach for the Claude Agent SDK when several agents need the same loop, tool dispatch and context handling, rather than maintaining a bespoke harness. The agentic loop, tool invocation, error recovery and context management are the same in every tool-using agent and are the bulk of the work. The Agent SDK provides them as maintained components, so a small team writes only the tools and prompts that make each agent different, which is the part that carries actual product value.

Why A is wrong: Sharing one harness across three agents is sound instinct, but the group then owns and maintains that loop indefinitely, which is precisely the shared infrastructure burden two engineers said they cannot carry.

Why B is wrong: Some tasks genuinely are single-call workflows rather than agents, but the stem states all three need a tool-calling loop with error and context handling, so two hand-rolled loops are being written for no stated reason.

Why C is wrong: Coordination is a real pattern, but the three agents serve separate purposes and no routing problem is stated, so this adds a supervisory layer the task has not earned and still leaves the loop unbuilt.

Why D is correct: The SDK already implements the behaviour common to all three agents, so the two engineers write only the differentiating tools and prompts and inherit maintenance of the loop rather than owning it.

See more CCDV-F practice questions, answers explained.

More in this domain

Back to all Agents and Workflows objectives, or the CCDV-F cert hub.

Examworthy is not affiliated with or endorsed by Anthropic. Original, blueprint-aligned practice material only.