CCAR-F Agentic Architecture and Orchestration Practice Question
A document-processing agent reads contracts and must extract a list of payment milestones, each with an amount, currency, and due date. Downstream billing systems cannot tolerate hallucinated fields, and the extraction must be validated programmatically before anything is written to the database. The architect wants Claude to emit data that can be parsed and checked with certainty rather than relying on post-hoc regex over prose. Which approach best satisfies this requirement?
⚠ Common exam trap
The trap here is treating a well-written JSON instruction as equivalent to a schema-enforced tool call, when only the latter gives the client a machine-checkable contract.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Define a tool whose input_schema describes the milestone array with required amount, currency, and due date fields, and force Claude to call it using tool_choice.
Tool definitions carry a JSON Schema in input_schema, and tool_choice can force the model to emit arguments conforming to that schema rather than free text. The client then validates the structured fields before persisting them, giving a deterministic contract that prompt wording alone cannot provide. This is the standard pattern for extraction feeding strict downstream systems.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Instruct Claude in the system prompt to reply only with JSON and add a reminder to double-check every field before answering.
Why it's wrong here
Prompt-only JSON requests usually produce parseable output, but nothing structurally prevents extra prose, missing keys, or invented values, and there is no schema the client can enforce. It offers no hard guarantee, so it cannot meet a requirement where hallucinated fields must be blocked before database writes.
- ✓
Define a tool whose input_schema describes the milestone array with required amount, currency, and due date fields, and force Claude to call it using tool_choice.
Why this is correct
A tool's input_schema is a JSON Schema the API validates the generated arguments against, and setting tool_choice to that tool forces the model to produce a structured call. The client receives typed, parseable input it can validate field by field before any database write, which is exactly the guarantee required.
- ✗
Raise the temperature to encourage variety and then filter the results with a second Claude call that rewrites non-conforming records.
Why it's wrong here
Higher temperature increases variability and makes malformed or invented fields more likely, not less. Adding a rewrite pass still leaves the final output unvalidated against a schema and adds cost and latency, so it does not provide the deterministic structure the billing integration demands.
- ✗
Use a very large max_tokens value and ask Claude to include the milestones in a markdown table so a parser can split on pipe characters.
Why it's wrong here
A markdown table is still free-form text; pipe-splitting breaks on escaped characters, multiline cells, and missing columns, and nothing enforces the required fields. Increasing max_tokens only allows longer output and does not create any schema-level guarantee against hallucinated or absent values.
About these practice questions
This CCAR-F question is part of Courseiva's 271-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Anthropic exam blueprint
This CCAR-F practice question is part of Courseiva's free Anthropic certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the CCAR-F exam.