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. (As of May 2026. Features and availability may change.)
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 May 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.
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.
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).
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
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. (As of May 2026)