What You Need to Know
Claude offers four ways to handle work. Ordinary chat is a single conversation. The Help Center describes Projects as self-contained workspaces with their own chat histories and knowledge bases. Research is for questions whose answer must be assembled from several outside sources, and it returns a cited report. An artifact is standalone content displayed in its own window, beside the conversation. Most people pick a feature by habit. Read the shape of the task instead, before writing any prompt.
A hair salon owner has four jobs. She needs one reply to a client's complaint. Each week she writes booking reminders from the same price list and house style. She wants to know how other salons handle no-show deposits, with sources her partner can check. She revises an aftercare sheet for her stylists every quarter. Four questions sort them. Is the work one-off or recurring? Does it stand alone, or keep needing the same standing context? Is it consumed once, or revised and reused? Can Claude answer from what you supply, or must the answer be gathered from outside sources? Each feature exists for one shape.
Ordinary Chat Is the Default
A single question, a single draft or an analysis of a document attached in the moment needs no workspace, agentic search or standalone container. Ordinary chat handles it immediately, and it is the right choice more often than enthusiasts admit. The complaint reply is this shape.
Projects: Recurring Shared Context
A Project carries two standing assets. Its instructions shape Claude's responses in every chat inside the workspace. Its knowledge base holds uploaded material Claude uses as background for those chats. Set up once, both apply to every chat in the Project. The signal is the same background documents, standing preferences and working material, needed across many conversations. Re-pasting the same context into chat after chat is Project-shaped work done by hand. The feature exists to end that workaround. A Project would hold the price list and house style the salon owner re-pastes each week.
Research: Cited Multi-Source Synthesis
In Research, Claude works agentically, running multiple searches that build on each other. Its synthesised report carries citations so the findings can be checked. The signals are a whole-field survey, a how-others-do-it brief, a current-state overview, and an audience who will want to see where the findings came from. The deposit question fits. Research is not a quality upgrade for ordinary questions. A task answerable from material you already hold gains nothing from it, because nothing needs gathering.
Artifacts: Work with Its Own Life
Claude creates an artifact when the output is significant, self-contained and likely to be edited, iterated on or reused outside the conversation. That last condition is the dominant signal: the work has a life beyond the chat that produced it. Examples are a reference sheet revised every quarter and a plan that will be shared and updated. Each should exist as one evolving version, not as fragments scattered through a conversation history. You iterate an artifact by asking Claude to change it, or by editing an earlier message to branch the chat with artifacts of its own. You can return to an artifact and share a finished one. The aftercare sheet fits.
One Dominant Signal
Real work mixes the features. A Project can contain chats that produce artifacts. A Research report can seed a document that lives as an artifact, revised each quarter. The salon's deposit report might seed a deposit policy kept as an artifact.
In the exam
This objective tests whether you pick a feature by reading the task. The exam does not test the combinations. Each item presents one piece of work with one dominant signal: recurring context, multi-source citation, iterative deliverable or simple one-off. The wrong answers are always real features aimed at the wrong shape. Ordinary chat needs defending, because the exam defends it. When a stem's dominant signal is a simple one-off, ordinary chat is the professional answer, however capable the other features are. The exam is willing to key the plainest option.
Writing a Project's instructions and curating its knowledge base belong to Domain 5; here, the tested skill is recognising the recurrence. Checking a Research report's citations is Domain 2's discipline. Choosing between an inline answer, a table and a document is Domain 2's format question. In this objective, an artifact is the home for iterative, reusable work.
Key Concept
Find the dominant signal first, then match it. Recurring shared context points to a Project, a cited multi-source answer to Research, an output with its own life to an artifact, and a self-contained one-off to ordinary chat.
Exam Traps
Recommending Research for a question answerable from material the user already holds
Research exists for answers that must be gathered from multiple outside sources. When the stem supplies the documents, the agentic search is a wrong-tool detour; ordinary chat with the material attached is the professional answer.
Running everything through a Project or Research to maximise quality
The heaviest feature is not the safest. A simple one-off gains nothing from a workspace or a multi-source report, and ordinary chat is a legitimate keyed answer in this objective; the dominant signal decides, not the feature's prestige.
Treating re-pasting the same context into every chat as diligence
The manual workaround pays a Project's setup cost every single time instead of once. When a stem describes the same documents and preferences supplied chat after chat, the keyed answer moves that work into a Project.
Practice Scenario
A parish council clerk has four pieces of work: the monthly agenda-and-minutes cycle that always needs the council's standing orders, member list and format conventions; a one-off briefing on how five nearby councils run allotment waiting lists, with sources the councillors can check; a single resident's question about a grant deadline; and an emergency-contacts sheet that is revised every quarter and shared with all members. She wants nothing heavier than each piece needs, no Project for work that never recurs, and nothing re-supplied by hand. Which plan matches feature to work?
Build Exercise
Audit Your Feature Choices
What you'll learn
- How to read the shape of a task before choosing a feature
- How to name the dominant signal that picks each feature
- How to spot the manual workaround in your own working pattern
- How to decide when a recurring task deserves a Project
- List your five most recent Claude conversations from your own work
Why: Real conversations expose real habits; an invented list flatters the exercise.
You should see: Five one-line descriptions of actual tasks you ran recently.
- Label each with the feature it should have used: ordinary chat, a Project chat, Research, or an artifact for the output
Why: The labelling forces the selection decision this objective tests, one task at a time.
You should see: A feature label against each of the five tasks.
- Name the dominant signal that decides each label: recurring shared context, multi-source cited synthesis, iterative shareable deliverable, or simple one-off
Why: Signals, not feature names, are what exam stems give you; practising the mapping is the point.
You should see: One named signal beside each feature label.
- Find one manual workaround in your own pattern, such as context re-pasted across chats or a living document buried in an old conversation, and name the feature that ends it
Why: The workaround is the anti-pattern the exam most often dresses as diligence; finding your own makes it visible in stems.
You should see: One workaround described in a sentence, with the feature that replaces it.
- If a recurring piece of work deserved a Project, note it for setup, then stop; configuring it well is a later skill
Why: This objective ends at the selection decision; instructions and knowledge curation belong to Domain 5.
You should see: A note naming the Project you would create and the recurring work it serves.
Sources
- What are projects? — Anthropic
- Use research on Claude — Anthropic
- Analyze campaign performance — Anthropic
- What are artifacts and how do I use them? — Anthropic
- When should I use web search, extended thinking, and research? — Anthropic
- Claude Certified Associate – Foundations Exam Guide — Anthropic