Domain 1 – Prompting and Task Execution (14%)

• Craft clear, specific prompts for business and technical tasks
• Decompose complex requests into manageable steps
• Iterate systematically on outputs
• Adapt style and structure for analysis, research, drafting, brainstorming, etc.

CCAO-F Domain 1 · Task 1.1

What You Need to Know

Treat Claude as a brilliant but new employee: highly capable, with no context until you supply it.

The Five Components of a Complete Business Prompt

1. Task — verb + deliverable (“Draft a one-page project update for the steering committee”)
2. Context — audience, purpose, decisions already made, constraints
3. Source material — paste/attach the real inputs; do not describe from memory
4. Output specification — format, length, tone, structure
5. An example — one sample of a previous document in the house style

Role and Audience Framing

Opening with a role shapes vocabulary, tone and priorities. Naming the audience changes the output more than most instruction tweaks.

Specificity Buys Time

A vague prompt produces generic output that needs heavy rework. A minute on the brief saves a rework cycle.

Key Concept: When an exam item compares prompts, count the components. The keyed answer almost always supplies the missing task, context, source material, output specification or example.

Exam Traps

• Accepting the one-line prompt because Claude will figure it out
• Choosing the option that polishes wording while the real gap goes unfilled
• Writing the deliverable yourself and using Claude only to proofread

Practice Scenario

Facilities coordinator needs Claude to draft a staff memo introducing a new desk-booking system. She has the supplier’s how-to guide and wants a draft she can send without reworking it by hand. Which prompt sets the work up best?

Build Exercise: Write the Five-Component Brief (20 min)

CCAO-F Domain 1 · Task 1.2

What You Need to Know

Complex work gets Claude’s best output when split into pieces it can do properly, one at a time.

Four Techniques (Lightest to Heaviest)

1. Numbered steps inside one prompt — for connected parts that must follow a sequence
2. Staged prompting in one conversation — for a deliverable built in layers; inspect each stage before the next
3. Plan-first prompting — when the right structure is not obvious; review a plan before drafting
4. Separate conversations per sub-task — for genuinely independent pieces

Choosing the Technique

• Connected parts → one conversation, staged
• Independent deliverables → separate chats
• Structure unclear → plan first

Carrying Context Forward

A new conversation does not automatically contain another conversation’s working material. Memory saves context about you as individual topics, not a transcript. Explicit persistence is required: paste the output, re-attach the file, or keep it in a Project’s knowledge base.

Exam Traps

• The do-everything mega-prompt
• Fragmenting connected work across separate conversations
• Plan-first prompting where the structure is already known and agreed

Practice Scenario

Programme director must produce a 20-page annual impact report: overview, five sections from five programme teams’ notes, one consistent voice. Wants to approve each part as produced and never re-explain settled decisions to a new chat. How should the work be structured?

Build Exercise: Stage a Multi-Part Deliverable (30 min)

CCAO-F Domain 1 · Task 1.3

What You Need to Know

A first output is a draft. Iteration (output → specific feedback → better output) is the normal working rhythm, not a failure state.

Feedback That Names the Gap

Good feedback does one of three things:

• Adds a missing constraint (audience, format, thing to avoid)
• Corrects a misreading
• Narrows the scope

“Make it better and try again” adds no new information and reproduces the problem.

Refine or Re-Brief?

• Output close → refine in the same conversation with targeted follow-ups
• Output shows the original prompt was wrong → rewrite the brief and start clean
• Asking for variants (formal / conversational / urgent) turns Claude into an options generator and you into the judge

Keep the Wording That Worked

When feedback finally lands the output, fold it back into the original prompt so the next run starts from the improved baseline.

Exam Traps

• The vague retry dressed as diligence
• Patching a fundamentally wrong brief through many follow-up turns
• Starting a fresh chat when the output was one specific fix away

Practice Scenario

Retail merchandiser asks Claude for product descriptions. First batch structurally fine but generic and off-voice. Same prompt in a new chat came back just as generic; she wants the copy fixed in one more round. Most effective next prompt?

Build Exercise: Run Two Feedback Cycles (20 min)

CCAO-F Domain 1 · Task 1.4

What You Need to Know

Four task types, each with a different briefing shape:

Type	Briefing shape
Analysis	Material + questions (attach the real data; name the questions and the decision the findings will inform; ask for findings, evidence, caveats)
Research	A scoped question, not a topic (scope, angle, what findings must inform). Use Research for multi-source thorough gathering; web search for one or two lookups
Drafting	Full five-component brief + exemplar + iteration; stage long work
Brainstorming	Wide then narrow — ask for quantity and range first; withhold criteria until the convergence step

The Diagnostic Habit

Name the type, then pick the shape. Most exam items hide the error in a plausible plan that applies the right briefing to the wrong task type.

Exam Traps

• Asking for an analysis without naming the questions it must answer
• Opening a brainstorm with tight constraints and a fixed number of acceptable directions
• Briefing research as a topic rather than a scoped question

Practice Scenario

University department administrator has four tasks: why tutorial attendance dropped; how three other universities run applicant open days; write the new-term welcome letter; generate ideas for lifting open-day attendance. Which working plan matches strategy to task?

Build Exercise: Brief All Four Task Types (30 min)