Writing, summarizing, studying, planning

You open Claude because you need something done before lunch: a cleaner draft of a status email, a short brief from a 12-page PDF, a study plan for a certification, or a two-week plan for a messy project. You type one vague sentence, get something polite and long, then spend ten minutes rewriting the thing yourself. That loop is common. It is also fixable.

This is Part 5 of Learn Claude from scratch. Parts 1 through 4 covered what Claude is, plan choices, first sessions, and how chats and Projects hold context. Here we stay practical: four jobs Claude handles well for most people, a prompt pattern you can reuse without jargon, and worked examples you can paste and adapt. Privacy and memory get their own chapter in Part 6. Workplace connectors show up later in the series. For broader AI habits at work, keep the Practical AI series open next to this one, and use Learn when you want the full path map.

What you will learn

• Why Claude is a good default for writing, summarizing, studying, and planning
• A five-part prompt pattern: role, goal, constraints, example, output format
• Worked prompts and sample outputs for each of the four jobs
• How to tighten weak prompts without turning them into a novel
• Mistakes that make drafts sound generic or factually loose
• A short practice drill you can finish in one sitting

Four jobs Claude handles well

Claude is a general model. People use it for code, research, and dozens of other tasks. For day-one skill building, four jobs pay off quickly because they show up in almost every role:

• Writing: drafts, rewrites, tone shifts, structure for emails, docs, and posts
• Summarizing: long notes, PDFs, transcripts, threads turned into something you can act on
• Studying: explanations, quizzes, spaced review plans, gap checks before a test or interview
• Planning: timelines, checklists, risk lists, meeting agendas, “what should I do next” sequences

These jobs share one property: the hard part is rarely “make words appear.” The hard part is stating the audience, the goal, and the format so the draft is usable on the first or second try. Claude is strong when those pieces are clear. It is weak when you ask for “something good about Q3” with no audience and no definition of done.

None of this means you stop thinking. For analytics and SQL, you still verify numbers and logic (see How to check AI-written SQL). For writing that will ship under your name, you still read every line. The model speeds drafting and structuring. You keep ownership of truth and tone.

The prompt pattern that actually sticks

You do not need a library of “secret” templates. One pattern covers most of the four jobs:

• Role: who Claude should act as (editor, tutor, project coordinator)
• Goal: what success looks like in one sentence
• Constraints: length, tone, what to avoid, tools or facts it must not invent
• Example: a short sample of good output, or a bad sentence to fix
• Output format: bullets, table, email body, numbered steps, quiz with answers

Anthropic’s own prompting guidance for Claude stresses clear, direct instructions and useful examples rather than clever wording. You can go deep later in their docs; for chat use, this five-part pattern is enough to beat “write me a summary.”

Here is the same request, thin vs usable:

You can skip a piece when the job is tiny (“shorten this to 40 words”). For anything that will leave your screen, put all five in. Constraints and output format remove the most rework.

Job 1: Writing

Writing with Claude is not “type a title and accept the blog.” It is draft generation under constraints: audience, length, voice, and must-include facts. Strong uses include status updates, difficult replies, first-pass docs, and tone shifts (friendly to formal, long to short).

Worked example: rewrite a status email

Suppose your rough notes look like this:

Rough notes:
- dashboard delayed, still waiting on finance definition of "active customer"
- Sam on PTO Fri
- we can ship partial view without cohort filter
- need decision by Wed noon or we miss the release train

Prompt:

Role: You are my calm internal editor for a data team.

Goal: Turn my rough notes into a status email for my manager and the product owner.

Constraints:
- Under 160 words
- Neutral tone, no blame
- Do not invent dates, metrics, or owners I did not give
- Keep every concrete fact from the notes

Example of the tone I want:
"We are blocked on one definition. Everything else can ship behind a flag."

Output format:
1) Subject line (max 8 words)
2) Email body with short paragraphs
3) Closing line that states the decision needed and the deadline

A solid first draft might look like this (yours will vary; treat it as a shape, not scripture):

Subject: Dashboard timing and one definition block

Hi both,

We are still waiting on finance’s definition of “active customer,” which is blocking the full dashboard. Sam is out Friday, so review capacity is thinner this week.

We can ship a partial view without the cohort filter if that is useful for the release train. To stay on that train, we need a decision by Wednesday noon on whether partial is acceptable and who owns the final definition.

Thanks,
[Your name]

Notice what the prompt protected: no fake metrics, no invented owner for the definition, a clear ask. If the model invents a “92% confidence” line, delete it. That is a constraint failure, not a reason to trust the next paragraph less carefully.

Writing tips that save rounds

• Paste the facts you care about as a bullet list, then ask for prose. Models invent less when facts are already listed.
• Ask for two tones only when you will actually choose between them. “Make it better” is not a tone.
• For public writing, ban marketing fluff in constraints: no “revolutionize,” no empty superlatives, no fake customer quotes.
• When rewriting your own draft, say what must not change (names, numbers, legal phrasing).

Job 2: Summarizing

Summarizing is where Claude earns its keep on long inputs: meeting notes, RFCs, vendor PDFs, support threads. The failure mode is a vague paragraph that sounds right and drops the decision. Force structure.

Worked example: brief from messy notes

Source (imagine this was pasted from a transcript or doc):

Notes from vendor call (45 min):
- New API rate limit: 120 req/min per key (was 60)
- Price for add-on analytics pack: $1,200/mo annual, $1,500 month-to-month
- SLA still 99.5% monthly; no change
- They will not sign our data processing addendum until legal review next month
- Integration path they recommend: webhook on order.created, not nightly CSV
- Our open item: confirm whether PII fields can be excluded from webhooks
- Follow-up: they send sample payload by Friday

Prompt:

Role: You are a staff analyst writing a one-page vendor brief for a busy director.

Goal: Summarize the call so we can decide whether to keep evaluating this vendor this quarter.

Constraints:
- Only use facts from the notes
- Separate facts from open questions
- Call out anything that blocks procurement or security
- Max 200 words total for sections 1-3

Example of a good decision line:
"Proceed only if legal clears the DPA path by [date we set]."

Output format:
1) Snapshot (3 bullets max)
2) Numbers and limits (table-friendly bullets)
3) Risks / blockers
4) Suggested next actions (owner-agnostic, 3 items)
5) "Missing from notes" list if anything important is absent

Sample output shape:

If the model “helpfully” adds a competitor comparison you never discussed, that is hallucination dressed as diligence. Constraints that say “only use facts from the notes” reduce that, but you still check.

Summary formats worth reusing

• ELI5 then expert: one plain paragraph, then a technical paragraph, for mixed audiences.
• Decision brief: context, options, recommendation, risks (great for leadership).
• Action log: who / what / by when extracted from a transcript (leave owners blank if unknown).
• Contradiction hunt: “List claims that conflict across these two docs.”

For very long files, upload or paste in chunks and ask Claude to maintain a running outline, then merge. Part 4’s Projects idea helps when the same source set returns every week.

Job 3: Studying

Studying with Claude works when you treat it like a tutor with a whiteboard, not a magic download of expertise. Good uses: explain a concept three ways, generate quizzes, rebuild a topic from notes, prep for interviews, or turn a syllabus into a weekly plan.

Worked example: quiz yourself on a metric definition

Prompt:

Role: You are a strict but friendly analytics tutor.

Goal: Help me learn the difference between conversion rate and conversion rate (eligible), using my notes only for definitions, then test me.

My notes:
- Conversion rate = orders / sessions
- Conversion rate (eligible) = orders / sessions that saw the buy button
- We use eligible for product experiments; marketing still uses the first one in weekly decks

Constraints:
- Do not invent extra company metrics
- If I am wrong, explain the mistake in one short paragraph, then re-ask a similar question
- Keep language concrete (orders, sessions, button)

Example of a good quiz question:
"A user lands, never scrolls to the buy button, leaves. Which denominator includes them?"

Output format:
1) 5-sentence explanation in plain English
2) One analogy (not a sports analogy)
3) 6 quiz questions (mix true/false and short answer)
4) Answer key after the questions, clearly labeled

How to use the reply: answer the quiz yourself before reading the key. Then paste your answers back and ask Claude to grade only against the notes. That second pass catches soft grading, where the model is too polite about a wrong definition.

Study patterns that transfer

Studying code or SQL? Ask for explanations of your snippet, then restate the logic in your own words, then run checks yourself. Claude can invent plausible but wrong edge cases; your notebook or warehouse is the referee.

Job 4: Planning

Planning is sequencing work under constraints: time, people, dependencies, risk. Claude is good at turning a fuzzy goal into a first draft plan. It is bad at knowing your real org politics or calendar. You supply those as constraints.

Worked example: two-week analytics project plan

Prompt:

Role: You are a project coordinator for a three-person analytics squad.

Goal: Draft a two-week plan to ship a "weekly revenue by channel" dashboard that leadership trusts.

Constraints:
- Team: Maya (SQL/dbt), Jordan (BI), me (stakeholder + QA)
- Max 6 hours per person per week on this project
- Source of truth is the warehouse; no direct prod DB access
- Definition of revenue is already signed off (attached summary below)
- Do not invent tools we do not have (we have dbt, BigQuery, Looker)
- Flag risks that need a human decision

Definition summary:
- Revenue = recognized order total in USD, excluding tax and shipping
- Channel from last non-direct touch in our marketing attribution table

Example of a good task line:
"Maya: draft dbt model grain = order_id, with tests for null channel (4h)"

Output format:
1) Outcome statement (1 sentence)
2) Day-by-day plan (10 working days), tasks with owner initials and hour estimates
3) Definition of done checklist (8 items max)
4) Risks table: risk | likelihood H/M/L | mitigation
5) Questions for stakeholders (max 5)

What you should do with the plan: fix hour estimates against reality, move owner tags, and delete any task that assumes access you do not have. The value is the skeleton and the risk list, not a perfect Gantt chart.

Planning formats that stay honest

• Pre-mortem: “It is two weeks later and we failed. List the five most likely reasons.”
• Meeting agenda: goal, decisions needed, time boxes, pre-reads.
• RACI lite: for each deliverable, who does, who reviews, who is informed (skip fake precision).
• Personal weekly plan: top 3 outcomes, deep work blocks, explicit “won’t do this week.”

If your plan depends on secret strategy docs or real customer lists, stop and read Part 6 before pasting. Public process notes and synthetic examples are enough for most planning drills.

One pattern, four outputs: quick map

How to tighten a weak reply in one turn

When the first answer is soft, do not restart from zero. Reply with a surgical fix:

Keep the structure. Cut length by 30%. Remove any claim not in my notes.
Replace adjectives with concrete facts. Add one open question at the end
if a number is missing. Do not add a conclusion paragraph.

Other high-yield follow-ups:

• “Show your assumptions as a bullet list, then rewrite without the ones I mark false.”
• “Give me version A (skeptical) and version B (optimistic), same facts.”
• “Convert this to a table with columns X, Y, Z.”
• “Mark every sentence that needs a source I must supply.”

Common mistakes

• One-word goals. “Summarize,” “plan,” “write” without audience or length.
• Hidden constraints. You wanted formal, short, and no emojis, but never said so.
• No example of voice. One good sentence from you beats three paragraphs of adjectives.
• Accepting invented numbers. If you did not provide a metric, treat new metrics as bugs.
• Studying without retrieval practice. Reading a long explanation is not the same as answering questions.
• Planning without capacity. Beautiful timelines that ignore hour limits fail on day two.
• Skipping the human pass. Anything customer-facing or executive-facing still needs your eyes.
• Pasting secrets to get a better draft. Better drafts are not worth leaked credentials or regulated data. Part 6 covers the paste ladder.

How this connects to the rest of the series

Part 4’s Projects and files make these four jobs stickier: put brand voice notes, metric definitions, or a syllabus in a project, then reuse the same prompt pattern. Part 6 covers what should never land in that project. Later parts touch work integrations and cases where Claude is the wrong tool (for example, live production changes without review).

If you want the wider habit stack (verification, data caution, how AI fits analytics work), the Practical AI series is the companion path. LLM vocabulary sits in What are LLMs, ChatGPT, generative AI, and more.

Practice drill (about 45 minutes)

1. Pick one real task from your week in each job (four tasks total), even tiny ones.
2. Write a five-part prompt for each before you open Claude.
3. Run all four. Save the prompts that worked in a personal note or Project file.
4. For the writing and summary tasks, do a red-pen pass: delete every invented fact.
5. For the study task, answer the quiz without looking, then grade yourself.
6. For the plan, cut anything that exceeds your real hours by half and see what remains.

Quick recap

• Start with four jobs: write, summarize, study, plan.
• Use role + goal + constraints + example + output format.
• Force structure in summaries so decisions and numbers do not vanish.
• Study with quizzes and grading, not only explanations.
• Plan with real capacity and explicit risks.
• Edit every draft that ships under your name; verify every number.

Next up, Part 6 covers memory, privacy, and what never to paste, including how chat history differs from memory and project files.

Sources

• Anthropic, Prompting best practices: https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices
• Anthropic, Prompt engineering overview: https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/overview
• Anthropic, Effective context engineering for AI agents: https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents
• Claude product overview: https://claude.com/product/overview
• Analytics Made Simple, Practical AI series: https://analyticsmadesimple.com/series/practical-ai/
• Analytics Made Simple, What are LLMs, ChatGPT, generative AI, and more: https://analyticsmadesimple.com/analytics/what-are-llms-chatgpt-generative-ai-and-more/
• Analytics Made Simple, How to check AI-written SQL: https://analyticsmadesimple.com/tutorials/how-to-check-ai-written-sql/
• Analytics Made Simple, Learn: https://analyticsmadesimple.com/learn/

More definitions in Key Terms →

Merch on Etsy

Open store →

Data Science T-Shirt View on Etsy → ETL Data Science Shirt View on Etsy → Apache Kafka T-Shirt View on Etsy → Y-Hat Coffee Mug View on Etsy →