CCAO-F - Prompting and Task Execution (14% of the exam) - Section 1.4

Adapt prompting strategies based on task type (analysis, research, drafting, brainstorming).

Matching the prompt to the job: asking for reasoning and evidence in analysis, sources in research, tone and audience in drafting, and range rather than one answer in brainstorming. Candidates should pick the strategy that fits the stated task type.

analysisresearchdraftingbrainstorming

Practice question for this objective

Free samplePrompting and Task Executionmedium

A marketing coordinator at a small charity is preparing for a trustee workshop next week, where trustees want to choose a spring fundraising campaign from options that differ in cost and audience. Her prompt "What is the best fundraising campaign for us?" returned one idea with a confident justification. What should she do next?

  • AAsk for a broad set of distinct ideas that vary in cost, audience and effort, without ranking yet Correct
  • BAsk Claude to set out the evidence and reasoning behind that one idea so trustees can trust it
  • CResend the same question several times and collect whichever different ideas come back
  • DUse research to find the single campaign that raised the most for similar charities last year
For brainstorming tasks, prompt for a deliberately varied range of ideas rather than a single best answer. A question framed as 'what is the best' invites Claude to converge on one answer. Brainstorming needs the opposite: an explicit request for many distinct ideas, dimensions to vary them along, and a pause on judging so options are not filtered too early. The choosing then happens with the people who own the decision.

Why A is correct: Brainstorming prompts should ask for range rather than one answer. Requesting many distinct ideas across cost, audience and effort, and holding off on ranking, gives the trustees the varied options they said they want to choose from.

Why B is wrong: Asking for reasoning and evidence is good practice for analysis, and trustees may want justification. It still leaves a single idea, while the workshop needs a spread of options for the trustees to choose from.

Why C is wrong: Repeating the prompt can produce some variation and feels like a fast way to get more ideas. The question still asks for the one best campaign, so results may cluster on similar ideas with no deliberate spread across cost and audience.

Why D is wrong: Grounding the choice in what worked elsewhere sounds evidence-led. It narrows the output to one campaign again and ignores the differences in cost and audience the trustees want to weigh for this charity.

See more CCAO-F practice questions, answers explained.

Exam traps in Prompting and Task Execution

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

  • Ask for twenty versions next time so that at least one of them is close enough to send

    Why it is wrong: More options feel like a better chance of a perfect letter, but this doubles the reading and merging work. Range suits brainstorming, not a single letter whose content is already fixed.

  • Ask Claude for a short, confident recommendation in a polished tone suited to a senior director

    Why it is wrong: Tempting because the reader is senior and busy, so a crisp recommendation feels respectful of her time. It applies a drafting strategy to an analysis task and hides the reasoning the director has said she needs before she will accept the recommendation.

  • Ask Claude in a chat what other councils did, then ask it to add a list of sources at the end

    Why it is wrong: Asking for sources sounds like it meets the reviewer's requirement. Sources added after the fact may not support the specific claims, and a listed source is not verified until someone opens it, so traceability is not actually established.

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