Skip to main content
Using Claude

Claude Projects, Artifacts & Memory: What They Are and How to Use Them

The core features that take Claude beyond chat: Artifacts (output panel), Projects (context workspace), and Memory (cross-session recall) — how they work and how to use them.

By
🌐 This article was machine-translated and may contain inaccuracies. Read the Korean original if in doubt.

Using Claude only for chat is a missed opportunity. Once you know features like Projects, Artifacts, and Memory, you can do the same work faster and more consistently. Here are the core features worth learning first. (Features and availability may change.)

🟢 Model references match the current lineup · model notice · Fable subscription
🟢 Model references match the current lineup · Claude Opus 5.5 / Claude Sonnet 5 / Claude Haiku 4.5 (higher tier: Claude Fable 5.1). This notice changes only when Anthropic ships a new model.

Fable 5 and 5.1 subscription (updated September 7, 2026): Claude Fable 5.1, released September 1, 2026, is the current Fable model and Fable 5 is now legacy. Plan terms are the same for both — Max and Team Premium plans include Fable at up to 50% of the weekly usage limit; Pro and Team Standard use usage credits (

🟢 Model references match the current lineup · Claude Opus 5.5 / Claude Sonnet 5 / Claude Haiku 4.5 (higher tier: Claude Fable 5.1). This notice changes only when Anthropic ships a new model.
0/M input, $50/M output tokens). The one-time
🟢 Model references match the current lineup · Claude Opus 5.5 / Claude Sonnet 5 / Claude Haiku 4.5 (higher tier: Claude Fable 5.1). This notice changes only when Anthropic ships a new model.
00 credit applied only to the Fable 5 transition and is not offered for 5.1. Some coding and debugging requests may be answered by an Opus model due to a security classifier (both models). See the Fable 5.1 guide and the Fable 5 availability guide for details.

Three core Claude features Artifacts show output in a panel; edit & share all plans Projects bundle instructions, files & context consistent reuse Memory remember context across chats manage in settings Claude takes text/images in and outputs text. No native image generation.

Artifacts — open results in a separate panel to view and edit

Artifacts open Claude's output — code, documents, diagrams — in a separate panel next to the chat. Long outputs no longer get buried in the conversation, and you can preview, edit, copy, and export them directly.

Supported formats (as of July 2026):

  • Code and scripts
  • HTML web pages and interactive React components
  • SVG vector graphics and Mermaid diagrams
  • Formatted Markdown documents
  • Downloadable files (.docx, .pptx, .xlsx, .pdf, etc.)

Artifacts are available on all plans, including the free tier. You can publish a finished artifact to create a shareable link, and recipients can view it without a Claude account. Some advanced features (e.g., persistent storage, Live Artifacts that stay connected to data and refresh automatically) are available on paid plans.

Projects — a workspace that holds your context

Projects are workspaces that maintain context across multiple conversations. When you start a new chat inside a project, Claude already knows:

  • Custom instructions — standing directions (tone, format, role, constraints) applied to every chat in that project
  • Reference files — documents you've uploaded for Claude to consult
  • The accumulated context of conversations in that project

For example, create a "Company Blog" project and add your brand tone, forbidden phrasing, and example posts — then you get consistent results without repeating the same setup every time. Projects suit recurring work where context and continuity matter.

If Artifacts are the "output," Projects are the "container for context (input)." Use them together: build and iterate inside a project, then share the resulting artifact as a link.

How projects work — set up once, applies every timeProject (workspace)Custom instructionsTone, format, role, limits — every chatReference filesUploaded docs Claude always consultsConversation contextWhat's built up in this projectNew chat→ already knows it allOpen a new chat inside the project and you skip re-explaining these three things.

Memory — remembering beyond a single conversation

Memory summarizes context from past conversations and remembers it across sessions. Anthropic began offering memory to all users, including the free tier, in March 2026.

  • It remembers context like your name, your location (when relevant to a query), ongoing projects and their status, and your working style.
  • You can view, edit, and delete what it remembers under Settings → Capabilities → Memory.
  • You can turn memory off, or use Temporary Chat mode for individual conversations you don't want remembered.
  • Each project has its own memory space — memories from project chats and from standalone chats are kept separate.
  • Memory itself is free, but the ability to search and cite past conversations is limited to paid plans (Pro, Max, Team, Enterprise).

With memory on, you don't have to re-explain your background every time. If keeping sensitive information stored feels uncomfortable, manage it in the settings above.

Other things worth knowing

  • File uploads — upload documents and images to analyze, summarize, or ask about.
  • Web search — use search for questions that need up-to-date information.
  • Connectors (MCP) — connect external services like Google Drive and Gmail to broaden context (availability varies by plan and settings).

One thing to note: Claude is a model that takes text and image input and produces text output. It has no native image, audio, or video generation (it can read and understand images, though).

When to use which featureArtifactsTo open output asideand edit itProjectsTo bundle contextand filesMemoryTo remember acrossconversationsStronger together — features/availability vary by plan/version · as of 2026.6

Summary

  • Artifacts: view, edit, and share outputs in a separate panel — all plans
  • Projects: bundle instructions, files, and context for consistent recurring work
  • Memory: remembers context across conversations, managed in settings

For autonomous work directly on your files, see Claude Cowork.

When you need live information, also check the web search & Research features.

Learn more: for Claude working directly inside your browser, see the Claude in Chrome guide.

For using Claude inside spreadsheets, see the Claude in Excel guide.

This article is for general guidance only. Features, availability, and plan structures may change per Anthropic's policies. Check the latest behavior in the Claude app and official docs.

Was this helpful?

Keep reading

Claude's Skills Explore Tab Explained — What 60 Plugins Do, How to Use Them, and Whether They Run Automatically (Sept 2026)

What each plugin listed under Settings → Skills → Explore does, how you call it, and whether it can run with nobody around — based on the SKILL.md files of 60 installed plugins and Anthropic's official docs.

62

Can Claude Really 'One-Click' Write a Web Novel? What's Realistic

There's a hope that feeding Claude a premise is enough to get a finished serialized novel, but the tasks Claude is actually good at and what still needs a human writer are different things. Here's a realistic workflow using real features like Projects and Styles.

35

When Your Claude Character Drifts Mid-Conversation: Keeping Persona Context Stable with Projects

Long conversations can wear down a carefully built character setup. Here's how Claude's project instructions and knowledge features keep a persona consistent over time.

34

How to Save Claude Usage: A Practical Guide for Research and Experimentation

A few small changes to how you chat can meaningfully cut your Claude usage. Here's how project caching, turning off extended thinking, Claude Code commands, and the September 14 weekly limit change all fit together.

88