Task statement 3.1 · Product and model selection

3.1 · Choosing Product Features

In Wrenfield Housing, the course example, the communications team has four jobs in one week: a quick question about a newsletter heading, the tenant letters it writes every week, evidence on how other housing providers handle damp and mould, and the spring newsletter's layout for the printer. Each job fits a different Claude feature, and the wrong one costs time or lets the house style slip.

Why it's tested

The tempting habit is to do everything in a plain chat, because it needs no setup. That works for a one-off question. For recurring work, someone must paste the same files in every time, so in the week somebody forgets, the draft drifts from the house style. The opposite habit fails too: if you turn on Research, a mode that runs many searches, for a fact already in your file, you wait for a long report.

KnowledgeFour features and the job each one fits

The exam guide names four product features. A chat is a plain conversation: Claude answers from what you type or attach and from the conversation so far. A Project is a self-contained workspace with its own chats and two settings. Project knowledge is the files you add to it, and project instructions are the guidance that applies only to chats inside it. Research, the apps' name for the guide's "research mode" (1.4), investigates a question with searches that build on each other and returns a cited report. An artifact, a standalone document beside the chat (2.6), holds content you will edit, keep or share. This rules out any answer that treats the four as interchangeable ways to get the same reply.

Research and artifacts both start from a chat: you turn Research on from the + menu, and an artifact opens beside the conversation. So choose by what the job needs beyond one answer:

  1. Nothing: a plain chat, because a one-off question needs no setup.
  2. The same instructions and files every time: a Project, so every chat in it starts from them.
  3. Many outside sources: Research, so Claude searches widely and cites each claim.
  4. A result to edit, keep or share: an artifact, refined over several turns.

Interactive · one week, four jobs, four features

Four columns, one per job in the communications team's week: a quick question, the weekly tenant letters, the damp and mould evidence, and the newsletter's print layout. Each column reads top to bottom: the job, what it needs beyond one answer, the feature that fits, and what it gives. The chosen column is solid and labelled chosen; the others are dashed and faint. In the pasted every time state, the weekly letters column is dashed, amber and labelled wrong choice: a new chat each week with the style guide pasted in, so drafts drift when someone forgets it. QUICK QUESTION QUICK QUESTION · CHOSEN THE JOB which newsletter heading is clearer NEEDS BEYOND ONE ANSWER nothing: read once, nothing to keep SO USE FEATURE Chat a plain conversation GIVES RESULT an answer in seconds, no setup WEEKLY LETTERS WEEKLY LETTERS · CHOSEN WRONG CHOICE THE JOB tenant letters, every week NEEDS BEYOND ONE ANSWER style guide and handbook, every time SO USE FEATURE Project Tenant comms New chat each week guide pasted by hand GIVES RESULT every chat starts with both files drafts drift when someone forgets DAMP EVIDENCE DAMP EVIDENCE · CHOSEN THE JOB how other providers handle damp and mould NEEDS BEYOND ONE ANSWER many outside sources, a link per claim SO USE FEATURE Research searches that build GIVES RESULT a cited report; open the sources PRINT LAYOUT PRINT LAYOUT · CHOSEN THE JOB spring newsletter for the printer NEEDS BEYOND ONE ANSWER a page to edit, keep and send on SO USE FEATURE Artifact a document beside chat GIVES RESULT edited over turns, exported as a PDF Same team, same week: what the job needs beyond one answer decides the feature.

Choose a feature for each of the week's four jobs, starting with the choice that went wrong.

Pasted every time: each week's letters started in a new chat with the style guide pasted in, so in the week someone forgot it, the drafts drifted from the house style.

Quick question: one answer, read once, so a plain chat is the whole job.

Weekly letters: the same style guide and handbook every week, so they live in a Project and every chat inside it starts with them.

Damp evidence: the answer is spread across many outside sources, so Research runs searches that build on each other and cites them.

Print layout: the newsletter is edited, kept and sent to the printer, so it is an artifact, exported as a PDF.

Solid and labelled CHOSEN: the feature that fits the job. Dashed and faint: the other jobs. Dashed and labelled WRONG CHOICE: the weekly letters done in a new chat each time.

A Project pays off when work recurs. Without one, every new chat starts empty, so each person must paste the style guide in again. Inside a Project, Claude uses the project knowledge and instructions in every chat, and on a Team plan you can share the Project with colleagues. Projects are on every plan, including Free, which allows five. Setting one up is taught in 5.1. The decision here is only whether the work recurs enough to need one.

Research earns its wait when an answer is spread across many sources. It needs a paid plan, such as Team, and web search, the quick lookup tool, switched on. It also searches connected tools such as Google Workspace. Because it gathers many sources, it can use up your usage limits faster. For a fact you already hold in a file, a plain chat with the file attached is faster.

An artifact suits content with a life after the chat. Claude creates one for substantial, self-contained content, typically over 15 lines, and you can ask for one by name. A Docs artifact exports to Word, PDF or Google Docs. Artifacts start private to you, and on a Team plan sharing stays inside the organisation by default.

KnowledgeOne week, four jobs

Here is the team's week, each job with the feature that fits and the wrong choice that tempts:

Chat

"For the boiler item, which heading is clearer: 'Boiler checks, 3–14 March' or 'Your boiler service is due'?"

Wrong choiceResearch: a long report for a one-line answer.

Project

"Tenant comms", with the style guide and tenant handbook as project knowledge, and one instruction: "Follow the style guide in every letter."

Wrong choiceA new chat each week, with both documents pasted in by hand.

Research

"How do other housing providers find and fix damp and mould early? Sources from 2024 on, a link for each claim."

Wrong choiceA chat with web search off: Claude answers from what it already knows, with no links.

Artifact

"Lay out the spring newsletter as a one-page document: three items, boiler servicing first." Edited, then exported as a PDF for the printer.

Wrong choiceA long chat reply, copied into another program by hand.

SkillWorked example: the letters that drifted from the house style

Wrenfield's communications team writes tenant letters every week, such as repair appointment notices. Each must match the tenant handbook and follow the style guide: "Dear resident", sentences of 20 words or fewer, and the repairs line number at the end. Each officer started a new chat for the week's batch and pasted both documents in:

# before: a new chat each week
[style guide pasted] [tenant handbook pasted] Draft this week's letters …
→ week 6, nobody pasted the style guide: "Dear Sir/Madam … in accordance
   with your tenancy obligations …", 34-word sentences, no repairs line
# after: one Project, shared with the team
Project: Tenant comms
Knowledge: style guide, tenant handbook
Instructions: Follow the style guide in every letter.
→ every new chat in the Project starts from both documents

The cause was the choice of feature, not the draft. The style guide reached Claude only when a person remembered to paste it, so the house style held only until someone forgot. A Project keeps the documents and the instruction in the workspace, so every chat in it starts from them, including a new joiner's first. The communications lead still checks each letter, as Wrenfield's AI policy requires, but now checks facts, not style.

Memory is not a shared Project. Memory, which lets Claude carry what it learns between your chats (3.4), is managed by each person for themselves. On a Team plan it stays off for each member until they turn it on (checked 2026-10-15). So memory cannot hold a team's style guide.

Ask one question: what does this job need beyond one answer?
Nothing: it is read onceChat: ask, read the reply and move on.
The same instructions and files every timeA Project: put them in once, and every chat starts from them.
Evidence from many outside sourcesResearch: set the scope and dates, then open the cited sources.
A result to edit, keep or shareAn artifact: work on the document beside the chat, then export it.
Takeaway
  • A file that must shape every chat belongs in a Project, not in each person's habit of pasting it.
  • Research is slower and uses up limits faster, so save it for questions no single source answers.
  • Research and artifacts both start in a chat; a chat on its own is right for anything read once.

check yourself

0 / 3 answered

A five-person HR team answers staff questions about benefits every week, from the same policy handbook and in a fixed answer format. Each adviser opens a new chat and pastes in the handbook and the format. Last week a new joiner forgot the format, and staff received answers in two different styles.What is the most effective way to set up this recurring work?

Select one.

A sales operations manager has two jobs this week. The manager needs a cited overview of how dozens of competitors price their subscriptions, drawn from their websites and recent news. They also need a one-page pricing proposal that they and their director will revise over several days and then export for the board. Neither job will recur.Which TWO feature choices best fit these jobs?

Select two.

A charity's fundraising officer turns on Research and asks: "What is the deadline for our grant report?" After several minutes Claude returns a long cited report on grant reporting in general, and the officer notices their usage running low. The funder's award letter, which states the deadline, is a PDF on their laptop.What is the most likely root cause?

Select one.

sources

  1. Claude Help Center, "What are projects?": self-contained workspaces with their own chat histories and knowledge bases; project knowledge and project instructions; available to all users, with five Projects on Free; sharing with members of the organisation on Team and Enterprise. Checked 2026-10-15.
  2. Claude Help Center, "Understanding Claude's personalization features": project instructions apply only to chats within that Project. Checked 2026-10-15.
  3. Claude Help Center, "Use research on Claude": in-depth investigation with searches that build on each other; web search must be on; the + button; paid plans (Pro, Max, Team, Enterprise); the web and connected tools, including Google Workspace; research sessions can use up limits faster. Checked 2026-10-15.
  4. Claude Help Center, "What are artifacts and how do I use them?": when Claude creates an artifact (significant and self-contained, typically over 15 lines); templates including Docs and Slides; Docs export to Word, PDF and Google Docs; artifacts start private. Checked 2026-10-15.
  5. Claude Help Center, "Publish and share artifacts": on Team and Enterprise, artifacts stay inside the organisation by default. Checked 2026-10-15.
  6. Claude Help Center, "Use Claude's chat search and memory to build on previous context": individual users manage their own memory; on Team and Enterprise, memory is off for each member until they turn it on. Checked 2026-10-15.
  7. Wrenfield's four jobs, the Tenant comms Project, the style guide's rules and the week 6 draft are this course's example.