CCAR-P - Solution Design & Architecture (17% of the exam) - Section 1.1

Translate business problems into Claude-based AI solutions.

Starting from a stated business problem rather than from a technology preference. Candidates should separate the outcome the business needs from the mechanism someone has proposed, decide whether a language model is the right tool at all, and frame a solution whose success can be measured against the original problem.

problem framing before solution choicemeasurable success criteriafit of an LLM to the taskdeterministic versus generative components

Practice question for this objective

Free sampleSolution Design & Architecturemedium

A retail bank's head of complaints asks for a customer-facing chatbot. Discovery shows that 18 per cent of complaints breach the regulator's five-business-day acknowledgement deadline, and case timing shows most of the delay sits in staff manually sorting each complaint into one of 12 regulatory categories before it can be routed. The team has eight weeks and must show the sponsor a measurable improvement in that breach rate. What should the architect recommend?

ABuild the customer-facing chatbot as requested, measured by how many complaints customers submit through it rather than by email each week
BFine-tune a model on five years of past complaints so it learns the 12 categories, and begin routing only once that training has finished
CDeploy an agent that investigates each complaint, decides the outcome and sends the final response letter to the customer without staff review
DUse Claude to classify each new complaint into the 12 categories and route it, measured by breach rate and by accuracy on a labelled sample Correct

Separate the outcome a sponsor needs from the mechanism they proposed, and aim the solution at the measured bottleneck with a matching success metric. The business problem is the acknowledgement breach rate, and the evidence places the delay in manual categorisation. Framing the solution as classification plus routing attacks that cause directly, fits an LLM's strength with unstructured text, and lets the team prove success with the breach rate and a labelled accuracy sample within the deadline. A chatbot answers the proposed mechanism rather than the problem.

Why A is wrong: It is tempting because it delivers exactly what the sponsor asked for. It is wrong because the measured delay sits in internal categorisation, not in how complaints arrive, so a new intake channel leaves the breach rate untouched and its success metric says nothing about the original problem.

Why B is wrong: It is tempting because historical labelled complaints look like ideal training data. It is wrong because fine-tuning comes before any prompt-based classification has been tried, adds data preparation and evaluation work that threatens the eight-week deadline, and may not beat a well-prompted model on a 12-category task.

Why C is wrong: It is tempting because it promises to clear the whole backlog at once. It is wrong because it is far larger than the stated problem, removes human judgement from a high-impact regulated decision, and the acknowledgement deadline only requires faster categorisation and routing.

Why D is correct: This targets the step the timing data identified as the bottleneck, uses a language model for a text classification task it suits, and ties success to the breach rate the sponsor cares about plus an accuracy check that catches misrouting.

See more CCAR-P practice questions, answers explained.

Exam traps in Solution Design & Architecture

Answers that look right on this material and are not. Each one is a distractor from a different question in the CCAR-P bank for this domain.

The assistant runs on a model tier too small to reason reliably about how garments fit different body shapes and sizes.
Why it is wrong: Tempting because fit advice sounds like a reasoning problem that a more capable model would handle better. It is wrong because the transcripts are already accurate 94 per cent of the time; the assistant faithfully repeats size charts that contradict each other, and a larger model reading the same inconsistent data inherits the same flaw.
The average satisfaction score from a survey shown after each assistant conversation, collected from launch and reported to finance monthly
Why it is wrong: It is tempting because it matches the director's description of success. It is wrong because it has no pre-launch baseline, does not measure escalations or engineer time, and survey responses are a self-selected sample that finance cannot connect to the stated cost.
Have Claude decide each application and write its own explanation, then map that explanation onto the regulator's reason codes
Why it is wrong: It is tempting because the explanation reads like a ready-made justification. It is wrong because a generated explanation is not guaranteed to reflect what actually drove the decision, so mapping it to reason codes does not give the field-level traceability the regulator requires.

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