CCAR-F practice question 9 of 10
True or False: When designing a multi-step agentic workflow, it is a best practice to explicitly instruct Claude in the system prompt exactly which tools to call in exactly which order, to eliminate any possibility of Claude making suboptimal decisions.
Full set: 191 questionsAccording to Anthropic's architectural guidelines, there is a fundamental distinction between "workflows" and "agents." In an agentic workflow, the LLM is given autonomy to dynamically direct its own processes, reason about intermediate outputs, and decide which tools to call and when. If a task requires tools to be called in an exact, predetermined order to eliminate suboptimal decisions, it is a best practice to orchestrate this deterministically using application code (e.g., prompt chaining, state machines, or programmatic routing) rather than relying on an agentic prompt. Attempting to force strict, multi-step determinism purely through system prompt instructions in an agentic loop is an anti-pattern; it is brittle, prone to prompt-following degradation over long contexts, and negates the primary advantage of agents—their flexible, autonomous reasoning.
Selecting "True" is incorrect because it conflates autonomous agents with deterministic workflows. If an exact execution order is strictly required, developers should not use an open-ended agentic loop. Instead, they should use programmatic orchestration (such as explicitly chaining API calls or using the toolchoice parameter in code) to guarantee the execution path, rather than hoping the model perfectly follows a complex sequence of instructions in the system prompt.
1. Anthropic Official Documentation. "Building effective agents." Section: Workflows vs. Agents. (Defines workflows as systems where paths are predefined by code, whereas agents dynamically direct their own processes and tool usage based on environmental feedback).
2. Anthropic Official Documentation. "Tool use (function calling)." Section: Forcing tool use. (Details how to use the toolchoice parameter programmatically when a specific tool must be used, rather than relying solely on prompt instructions for strict determinism).
Keep practicing
Take the free CCAR-F practice test
Ten exam-style questions with answers and explanations, plus the exam facts and study guides.
More questions
Other CCAR-F practice questions
- Question 1You are building a customer support resolution agent using the Claude Agent SDK. The agen…
- Question 2Your team is building an MCP integration where Claude needs to fetch real-time inventory …
- Question 3You are building developer productivity tools using the Claude Agent SDK. The agent helps…
- Question 4You are integrating Claude Code into your Continuous Integration/Continuous Deployment (C…
- Question 6You are building a structured data extraction system using Claude. The system extracts in…
- Question 7You are building a structured data extraction system using Claude. The system extracts in…
