CCAO-F domain - 12% of the exam

Product and Model Selection

Product and Model Selection is 12% of the CCAO-F exam. These are the objectives it covers, each with practice questions, with every answer explained.

The domain in numbers

30
Practice questions
4
Objectives
8
Easy
22
Medium

Where people go wrong

  • Using Memory as a store for reference documents

    The wrong answers reach for Memory because it carries context between chats. Memory is tied to the person using Claude and is not a shared, reviewable record, so it will not reliably reproduce an exact 80-row table or a 40-page policy. Reference material and agreed figures belong in project knowledge, which every chat in the Project can draw on, including chats colleagues start, and which is replaced when the document changes.

    See it in a sample question
  • Defaulting to the most capable model for routine work

    The wrong answers treat Opus as the safe choice for every task, including 200 short post variants, 400 session descriptions to reformat and one-line meeting notes. For simple, high-volume or quick work it adds cost and waiting time without a meaningful gain. Haiku fits fast, low-cost volume, Sonnet balances capability and speed for varied everyday drafting, and Opus is kept for complex multi-step analysis.

    See it in a sample question
  • Carrying a cluttered chat forward

    The wrong answers keep working in one very long chat, or paste the whole old transcript into a new one. A long conversation blurs earlier detail, so rejected options compete with agreed ones, and pasting the full text recreates that clutter. The fix is a fresh chat that opens with a short summary of the agreed decisions, or a Project whose knowledge holds them when the work continues.

    See it in a sample question

Objectives in this domain

Sample questions from this domain

Free sampleProduct and Model Selectionmedium

A consultant at a management consultancy is running a six-week process review for a client and works in a Claude Project her team shares for that client. Each working session produces decisions on scope and recommendations, and a colleague will take over the engagement for its final fortnight. How should she make sure the agreed decisions carry forward?

  • AKeep the whole engagement in one ongoing chat so her colleague can scroll back through it
  • BRely on Memory to carry the decisions forward so they are recalled in her colleague's chats
  • CEnd each session by saving an updated, reviewed summary of all decisions so far to project knowledge, replacing the last Correct
  • DUpload every session's full chat transcript to project knowledge as a separate new file
Persist decisions from multi-session work as a single reviewed summary in project knowledge, updated by replacement, so they carry forward to other chats and people. Project knowledge is shared across every chat in the Project, so it is the right place for information that must outlive a single conversation. A concise, reviewed summary records only what was decided, and replacing the old version rather than adding another prevents contradictory files from confusing Claude or the incoming colleague.

Why A is wrong: A single thread seems to keep everything in one place. Over six weeks it becomes very long, earlier decisions blur with discarded options, and the colleague would have to reconstruct what was finally agreed.

Why B is wrong: Memory does carry context between chats, which makes it sound suitable. It is tied to the person using Claude rather than being a shared, reviewable record, and engagement decisions are reference material that belongs in project knowledge.

Why C is correct: A checked summary of every decision to date, held in the shared Project's knowledge, is available to every chat in the Project, including the colleague's, and replacing the previous version keeps one authoritative record instead of conflicting copies.

Why D is wrong: Saving everything feels thorough. Raw transcripts mix rejected options with final decisions and pile up as separate, sometimes contradictory files, so Claude and the colleague cannot tell which position is current.

Free sampleProduct and Model Selectioneasy

A communications officer at a local council uses Claude throughout the day for routine but varied drafting: newsletter items for residents, short press releases and replies to councillors' queries. The work needs good writing and some judgement about tone, but none of it involves deep, multi-step analysis, and she wants drafts back quickly between meetings. Which model type should she choose as her everyday default?

  • AOpus, because public-facing council writing deserves the most capable model on every draft
  • BHaiku, because quick turnaround matters more than quality for routine council writing
  • CSonnet, because it balances capability with speed for varied everyday drafting work like hers Correct
  • DOpus for drafting and Haiku for checking, so a second model confirms each draft is accurate
Sonnet is a sensible everyday default for varied work that needs good quality and quick turnaround but not deep, multi-step reasoning. Sonnet sits between Haiku and Opus, offering strong writing and judgement while staying responsive. For a steady stream of varied, moderately demanding drafts, that balance avoids both the extra cost and wait of the top model and the quality risk of the fastest one.

Why A is wrong: Public-facing writing feels important enough to justify the top model. The stem rules out deep multi-step analysis and asks for quick drafts, so Opus adds cost and wait time she does not need as a daily default.

Why B is wrong: Speed is one of her needs, which makes the fastest model appealing. The stem also says the work needs good writing and judgement about tone, so trading quality away for speed is the wrong balance.

Why C is correct: Her work needs solid writing quality and tone judgement, plus quick turnaround, without deep analysis. Sonnet is the model type that balances capability and speed, which matches that mix.

Why D is wrong: A second pass sounds like a safety step. Another model reviewing the draft is not independent evidence of accuracy, and pairing models adds cost and delay for routine drafting she wants back quickly.

Other domains in this exam

See also the CCAO-F cert hub, the study guide, and the cheat sheet.

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