Task statement 1.1 · Prompting and task execution

1.1 · Create Effective Prompts

In Wrenfield Housing, the course example, the communications team asks Claude for letters and reports that go to tenants. When a prompt, a message asking Claude for work, leaves out who will read the result and what it must say, Claude fills the gaps with guesses, and someone rewrites the draft by hand.

Why it's tested

The tempting habit is to send a short request and fix the draft afterwards, because typing a longer prompt feels slower than editing. Claude knows nothing about your organisation, your readers or your facts beyond what the conversation gives it, so a short request makes it guess each of them. The edits then take longer than the missing sentences would have, and a guessed fact can slip through to the reader. The opposite habit fails too, because a prompt is not better for being long, only for answering the questions the task depends on.

KnowledgeWhat Claude knows when it reads your prompt

A prompt is the message you send Claude: the request, plus everything you give it to work with. Claude works from that message, the conversation before it and any file you attach. It cannot see your inbox, your organisation's habits or the facts in your head, so it fills every gap with a likely guess. Anthropic's prompting guide asks you to treat Claude as a brilliant but new employee who lacks context on your norms and workflows. Its test for a prompt is to imagine a colleague with minimal context on the task following it: if they would be confused, Claude will be too. This rules out any answer that expects Claude to work out a missing fact, reader or standard from a vague request.

An effective prompt therefore answers, in plain sentences, the questions a new colleague would ask before starting. Anthropic's guidance and help articles point to the same parts, which you can add in this order:

  1. The task: what to produce, in one sentence.
  2. The purpose and audience: who will read the result, what it is for, and the reason behind any instruction.
  3. The facts and inputs: every name, date, figure or document the result depends on, typed in or attached.
  4. The limits: tone, length, and what to leave out.
  5. The format: the shape of the result, with an example when the shape is hard to describe.

Interactive · what Claude must decide as the prompt grows

Four parts of the boiler letter's prompt on the left, each with an arrow to the decision it settles on the right. The task settles what to write. Purpose and audience settle who reads it and what they must do. The facts settle the dates, time slots and contact. Limits and format settle tone, length and what the letter may offer. A part missing from the prompt is dashed and labelled not in the prompt, and its decision is dashed and labelled guessed. YOUR PROMPT WHAT CLAUDE MUST DECIDE Task Write a letter to tenants about boiler servicing SETTLES ANSWERED what to write: a letter Purpose and audience 1,200 Millbrook households must let the contractor in NOT IN THE PROMPT SETTLES LEFT OPEN ANSWERED GUESSED who reads it, what they must do → GENERIC, FORMAL TEXT Facts 3–14 March · 8:00–13:00 or 13:00–18:00 · rebook: repairs line NOT IN THE PROMPT SETTLES LEFT OPEN ANSWERED GUESSED dates, time slots, contact → BLANKS SUCH AS [DATE] Limits and format plain English, one page, offer nothing not listed here NOT IN THE PROMPT SETTLES LEFT OPEN ANSWERED GUESSED tone, length, what it may offer → A £20 CREDIT NOBODY OFFERED Each part left out becomes a decision Claude makes without you.

Step through the boiler letter's prompt, from one line to the full brief, and see what Claude is left to decide.

One line: Claude knows only that a letter about boiler servicing is wanted. It guesses the readers, the dates and the tone, so the draft is generic, full of blanks, and promises a £20 credit nobody offered.

Purpose and audience added: Claude now writes to Millbrook households and asks them to let the contractor in. The dates, slots and contact are still guesses, so the blanks stay.

Facts added: the dates, time slots and repairs line replace every blank. Tone, length and what the letter may offer are still Claude's choice.

The full brief: every decision the letter depends on is in the prompt, so the draft needs checking, not rewriting.

Dashed and labelled GUESSED: Claude decides without you. Solid and labelled ANSWERED: the prompt settled it.

Two habits make these parts work harder. The first is giving the reason behind an instruction, not only the rule. Anthropic's prompting guide uses the example of an instruction never to use ellipses: once the prompt adds that the text will be read aloud by a text-to-speech engine, Claude understands the goal and can apply it to cases the rule never named. The second is keeping material apart from instructions. When you paste a long document, wrapping it in tags such as <document> and </document> tells Claude where the material ends and your request begins. Numbered steps help in the same way when the order of the work matters.

KnowledgeBusiness tasks and technical tasks

The exam guide asks for effective prompts for both business and technical tasks. The parts stay the same, but a different part carries the weight. A business task, such as a letter, a summary or a briefing, has no single right answer, so it depends most on the audience, the purpose and the tone. A technical task, such as a spreadsheet formula, a cleaned-up table or instructions for a tool, has a result that either works or fails, so it depends most on exact inputs and the exact shape of the result. Associates do not write code, but they do ask Claude for formulas and step-by-step instructions, so both kinds are part of daily work:

Letter, summary, briefing

Business task

The weight is on purpose, audience and tone: who reads it, what they should do, and how it should sound.

Left out: Claude writes for an average reader in a neutral voice.

Formula, data, steps

Technical task

The weight is on exact inputs and output: the program in use, column names, a few sample rows and the expected result.

Left out: Claude guesses the layout, and the answer fails on your real data.

SkillWorked example: the boiler letter that needed rewriting

Wrenfield's communications team had to tell the 1,200 households on the Millbrook estate that a contractor would service each home's boiler between 3 and 14 March. The first prompt was one line. The draft came back formal and generic, with blanks where the facts should be and a promise Wrenfield never made:

# before
Write a letter to tenants about boiler servicing.
→ "on [DATE] … call [CONTACT NUMBER] … a £20 credit for any missed visit"
# after
Write a one-page letter to the 1,200 households on our Millbrook estate.
Purpose: each tenant must let our contractor in to service their boiler.
Facts: visits run 3–14 March, mornings 8:00–13:00 or afternoons 13:00–18:00.
Tenants who cannot be in rebook through the repairs line.
Plain English, friendly but firm. Offer nothing that is not listed here.
→ every fact filled in, no blanks, no credit offered

The cause was missing context, not a weak model. The one-line prompt gave Claude the task and nothing else, so it wrote for a neutral reader, left blanks for facts it could not know, and added a credit that sounded plausible. The new prompt adds the purpose and audience, the facts and the limits, and its last line closes the gap the credit came through. The communications lead still checks the letter before it goes out, as Wrenfield's AI policy requires, but the check is now a read-through rather than a rewrite.

Longer is not the goal. Anthropic's prompting advice warns that longer, more complex prompts are not always better. Start simple, add only detail that answers a question the task depends on, and check that each addition improves the result.

Ask one question: could a colleague who knows nothing about this task do it well from your message alone? Yes → send it. No → first add what they would ask for: the purpose and audience, the facts, the limits and the format.
Takeaway
  • Claude knows only what the conversation gives it, so every missing fact, reader or limit becomes a guess.
  • An effective prompt gives the task, the purpose and audience, the facts, the limits and the format, with the reason behind each instruction.
  • Business tasks lean on audience and tone; technical tasks lean on exact inputs and the exact shape of the result.

check yourself

0 / 3 answered

An HR adviser pastes their organisation's new parental leave policy into Claude and asks: "Summarise this policy." The summary is accurate but uses HR terms such as "qualifying period". The adviser needs it for line managers, who must answer their staff's questions about the policy next week.What is the most effective change to the prompt?

Select one.

An events coordinator asks Claude: "Give me a formula that adds up the costs for each event." The formula it returns refers to columns the sheet does not have, so it fails. The coordinator works in Google Sheets, with event names in column A and costs in column D.Which TWO additions to the prompt would most directly fix this?

Select two.

A school office manager pastes two paragraphs of trip notes and writes: "Write a reminder to parents about the trip. Never mention costs." The reminder covers the date, the meeting point and what to bring, but it leaves out the payment deadline from the notes, which parents must meet.What is the most likely root cause?

Select one.

sources

  1. Claude Platform Docs, "Prompting best practices": Claude as "a brilliant but new employee who lacks context on your norms and workflows"; the golden rule of showing a prompt to a colleague with minimal context; being specific about format and constraints; numbered steps when order matters; context and motivation, with the ellipses and text-to-speech example; examples in <example> tags; XML tags to separate instructions, context and inputs. Checked 2026-10-15.
  2. Claude Help Center, "Introduction to prompt design": very specific instructions about exactly what you want; Claude has no background on you, your task or your organisation. Checked 2026-10-15.
  3. Claude Help Center, "My prompt isn't giving me a helpful answer": explain the ask simply and clearly; give as much context as possible; write for someone with no background knowledge. Checked 2026-10-15.
  4. Claude Blog, "Best practices for prompt engineering": constraints, audience and goal, and output structure as what to include; longer, more complex prompts are not always better; start simple. Checked 2026-10-15.
  5. Wrenfield's boiler letter, its one-line first draft and the £20 credit are this course's example.