Task statement 1.4 · Prompting and task execution

1.4 · Prompting by Task Type

In Wrenfield Housing, the course example, the operations team has 640 repair jobs waiting. It asks Claude four things about that one backlog: what its figures show, what other housing providers have done, how to brief the board, and how to clear it. Each is a different task type, so one style of prompt gets most of them wrong.

Why it's tested

The tempting habit is to write every prompt the same way: describe the result and wait for it. That works for a letter, because the reader's needs are the test. On your own figures, the same prompt returns a confident conclusion with nothing to show where it came from, so you cannot check it. On outside facts, it gives no sources or dates. For ideas, it returns a few safe options, because asking for "the best ideas" makes Claude judge before it has explored.

KnowledgeWhat changes from one task type to the next

The parts of a prompt from 1.1 stay the same for every task: the task, the purpose and audience, the facts, the limits and the format. What changes is where the result's quality comes from, so each task type puts its weight on a different part. The exam guide names four task types. Analysis is work on material you give Claude, such as a spreadsheet. Research is gathering information that is not in the conversation yet. Drafting is writing for a reader. Brainstorming is generating options to choose from. This rules out any answer that treats one well-built prompt as right for every task.

So name the task type first, then build the prompt around it:

  1. Give what the type works from: data, a scope and dates, a reader and an example, or a problem and its limits.
  2. Ask for what lets you check it: evidence, sources, a match to the example, or a wide spread of options.
  3. Plan the next turn: check the figures, open the sources, edit the draft, or choose from the list.

Interactive · one backlog, four task types

Four columns, one per task type for the repairs backlog: analysis, research, drafting and brainstorming. Each column reads top to bottom: what the prompt adds, what Claude works from, what comes back, and your next step. The chosen column is solid and labelled chosen; the other three are dashed and faint. ANALYSIS ANALYSIS · CHOSEN PROMPT ADDS backlog export in tags, counts behind findings USES CLAUDE WORKS FROM only the attached backlog export RETURNS COMES BACK findings, each with its job counts YOU THEN YOUR NEXT STEP check the counts against the export RESEARCH RESEARCH · CHOSEN PROMPT ADDS scope, dates, sources; Research turned on USES CLAUDE WORKS FROM the web and connected tools, 1–3 minutes RETURNS COMES BACK a longer report with citations YOU THEN YOUR NEXT STEP open the sources, check their dates DRAFTING DRAFTING · CHOSEN PROMPT ADDS board as reader, tone, format, one example USES CLAUDE WORKS FROM your figures, in the example's style RETURNS COMES BACK a one-page board briefing YOU THEN YOUR NEXT STEP edit; a person checks before the board BRAINSTORMING BRAINSTORMING · CHOSEN PROMPT ADDS 20 varied ideas, no ranking yet USES CLAUDE WORKS FROM the problem and four areas to cover RETURNS COMES BACK a wide, unranked list of ideas YOU THEN YOUR NEXT STEP second turn: choose 3 against criteria Same backlog, same parts of a prompt: the task type decides what you add and what you check.

Choose the backlog's task type.

Analysis: Claude works only from the export, so the prompt asks for the counts behind each finding, and you check them.

Research: the answer is outside the conversation, so the prompt sets scope and dates, and you open the cited sources.

Drafting: the board is the reader, so the prompt gives tone, format and an example, and a person checks the draft.

Brainstorming: range comes first, so the prompt asks for 20 unranked ideas, and a second turn chooses.

Solid and labelled CHOSEN: the type you picked. Dashed and faint: the other three.

Analysis is where a confident answer does the most harm, because it sounds as if it came from your data. Anthropic's prompting guide gives two moves for long documents and data: put the material near the top, above the question, and ask Claude to quote the relevant parts before it carries out the task. The quotes show which rows each finding rests on, so you can check a finding instead of trusting it. Anthropic's prompting advice also suggests telling Claude to say so when the data is insufficient, rather than speculating.

Research differs because the material is not in the conversation yet, so the prompt must say where to look and what counts as a good answer. Anthropic's guide asks for clear success criteria and for checking information across several sources. For an associate, the scope is usually a place, a kind of source and a date range. Web search, a quick lookup, suits a fact that one or two searches can answer. Research is a mode for in-depth investigation. It runs searches that build on each other for one to three minutes, can use connected tools such as Google Workspace, and returns a longer report with citations.

Drafting and brainstorming pull in opposite directions. A draft has a reader, so its quality comes from the audience, the tone and the format, and an example of the style is often the fastest way to show all three. Anthropic's guide recommends wrapping an example in <example> tags so Claude can tell it from your instructions. Brainstorming needs range instead, so the prompt asks for many options and names the kinds to cover. Anthropic's blog quotes the designer behind Claude Design: ask for ten options, then remix the best, because most will not be good. Judging belongs in a second turn, because asking for the single best idea makes Claude filter before it has explored.

KnowledgeOne backlog, four prompts

Here is Wrenfield's backlog as each task type:

Analysis

The export first, in <data> tags, then: "Quote the counts behind each finding. If the data cannot show a cause, say so."

Comes backFindings the team can check against the export.

Research

With Research on: "How have other housing providers cut repair waiting times? Sources from 2024 on, with a link for each claim."

Comes backA cited report. The team opens its sources before quoting it.

Drafting

"Draft a one-page briefing for the October board meeting: neutral tone, three headings, in the style of the example." Last quarter's briefing goes in <example> tags.

Comes backA draft the operations director checks before the board sees it.

Brainstorming

"Give 20 ideas to cut the backlog, across scheduling, contractors, tenant reporting and staffing. Do not rank them yet."

Comes backA wide list. A second turn picks three that need no new IT system.

SkillWorked example: the backlog analysis that read like an opinion

Wrenfield's backlog export lists 640 open jobs by job type, estate, date reported and status, with no tenant names or addresses, as the AI policy requires. The first prompt asked for a verdict, and the verdict blamed something the export does not contain:

# before
[backlog export attached] What's going wrong with our repairs backlog?
→ "Delays are mainly caused by contractor shortages. Consider hiring."
# after
<data>[backlog export: 640 open jobs]</data>
Which three job types have the longest median wait, in days open?
For each one, quote the job count and the median from the data.
If the data cannot show why a job type waits, say so.
→ "Damp and mould: 112 jobs, median 41 days … the export has no
   contractor field, so it cannot show the cause."

The cause was a drafting-style prompt on an analysis task. "What's going wrong" asks for a conclusion. The export holds no contractor data, so Claude supplied a plausible cause from general knowledge and stated it as a finding. The new prompt asks questions the export can answer, asks for the figures behind each finding, and lets Claude say where the data stops.

More precise than the guide. The exam guide says "research mode"; the Claude apps call the feature Research. On paid plans, including Team, you turn it on from the + menu in a chat, with web search on (checked 2026-10-15). Exam answer: "research mode" means Research, chosen for an investigation across many sources rather than a quick fact.

Ask one question: what must the result rest on?
Your own data or documentsAnalysis: put the material first and ask for the evidence behind each finding.
Information outside the conversationResearch: set the scope and dates, use Research, and ask for a source for each claim.
What a reader needsDrafting: give the audience, the tone and the format, with an example.
A range of optionsBrainstorming: ask for many varied ideas, then choose in a second turn.
Takeaway
  • The parts of a prompt stay the same; the task type decides which part carries the weight.
  • Analysis and research need support you can check: quotes from your data, or a dated source for each outside claim.
  • Drafting needs a reader and an example; brainstorming needs range first and judging later.

check yourself

0 / 3 answered

A finance analyst uploads a spreadsheet of 400 expense claims and asks Claude: "Which departments are overspending?" Claude names three departments and a likely reason for each. The analyst will present the findings to the finance director, who always asks which figures each claim rests on.What is the most effective change to the prompt?

Select one.

A marketing manager asks Claude: "What is the best name for our new walking-tour app?" Claude replies with one name and a short reason for it. The manager wants a broad shortlist that they can test with a panel of customers before the team commits to any name.Which TWO changes to the approach would best give the manager that shortlist?

Select two.

A council policy officer asks Claude in a chat: "How have five large cities changed their parking rules since 2024?" Web search is turned off in their settings. The answer is fluent and well organised, but it gives no links, and two of the changes it describes date from 2021.What is the most likely root cause?

Select one.

sources

  1. Claude Platform Docs, "Prompting best practices": long context prompting (put long documents and inputs near the top, above the query; ask Claude to quote relevant parts first); research and information gathering (clear success criteria, verify across multiple sources); examples in <example> tags so Claude can tell them from instructions. Checked 2026-10-15.
  2. Claude Help Center, "Use research on Claude": Research investigates a question in depth with multiple searches that build on each other; turned on from the + button with web search on; paid plans (Pro, Max, Team, Enterprise); searches the web and connected tools, including Google Workspace. Checked 2026-10-15.
  3. Claude Help Center, "When should I use web search, extended thinking, and research?": web search for straightforward facts in one or two tool calls; Research over 1–3 minutes, with citations and a longer final report. Checked 2026-10-15.
  4. Claude Blog, "Best practices for prompt engineering": if the data is insufficient to draw conclusions, say so rather than speculating; ask explicitly for breadth. Checked 2026-10-15.
  5. Claude Blog, "How the product designer who built Claude Design uses it": ask for ten options, then remix; most will not be good. Checked 2026-10-15.
  6. Wrenfield's repairs backlog, its export, the damp and mould figures and the board briefing are this course's example.