Claude Apps And Product Surfaces
Claude is now a suite of work surfaces. The app is not only chat; it includes projects, artifacts, memory, connectors, specialized apps, and agentic work modes that change how Claude gets context and takes action.
The Projects support article says free users can create a maximum of five projects.
Source: What are projects? Citable fact Up to 10xPaid-plan projects can enable retrieval-augmented project knowledge to expand capacity by up to 10x when project knowledge approaches context limits.
Source: What are projects?The Core App
The Claude product overview presents Claude as an AI for problem solvers: a workspace for analysis, writing, coding, data work, and collaboration. The web, desktop, and mobile apps are the easiest place to use Claude interactively and to attach files or context without writing code.
The core app is where most product features appear first or become visible to non-developers: projects, artifacts, memory, connectors, voice or mobile access, and specialized workflows. Each feature has separate availability and privacy details, so verify the relevant support article before rollout.
Projects And Artifacts
Projects are durable workspaces with chat history, uploaded knowledge, and project instructions. They are useful when Claude needs stable context across related conversations: product specs, client research, legal background, recurring editorial voice, or codebase notes.
Artifacts are substantial outputs in a dedicated window: documents, code, visualizations, mini-apps, and other shareable content. They are useful when the deliverable needs iteration outside the chat transcript.
Connectors, Search, And Memory
Connectors let Claude access apps and services, retrieve data, and take actions within connected services. The support docs state that Claude inherits each person’s permissions from the connected service, which is the key governance point: connector access should mirror real organizational access.
Memory and chat search help Claude build context from previous conversations. The memory support article says Claude can generate memory summaries and project-specific summaries; incognito chats are excluded from memory and search behavior, subject to retention caveats.
Specialized Claude Apps
Claude Cowork moves Claude from chat into delegated desktop work. Support docs describe Cowork as running directly on your computer with chosen files and tools, with code running in an isolated virtual machine but still capable of making real file changes.
@Claude brings Claude into Slack threads for Team and Enterprise. Claude Science is a beta workbench for scientific tooling and local or infrastructure-based compute. Claude Security is a public beta for Enterprise security teams that scans code, validates findings, and suggests patches.
Claude Cowork
Delegated desktop work with local files, connectors, plans, subtasks, and computer-use paths.
@Claude
Slack-native Claude for Team and Enterprise channels, threads, routines, and shared outputs.
Claude Science
Research workbench for scientific tools, compute, provenance, and domain workflows.
Claude Security
Enterprise beta focused on vulnerability scanning, validation, and patch suggestions.
Projects allow you to create self-contained workspaces.
Cite This Page
Claude Central. "Claude Apps And Product Surfaces." Last checked July 6, 2026. https://claudecentral.com/claude-apps
FAQ
Are artifacts available only in the browser?
No. The artifact support article says artifacts are available in Claude, Claude Desktop, and Claude Code, though usage details differ by surface.
Do connectors bypass app permissions?
No. The connector support article says Claude inherits each person’s permissions from the connected service.
Should every team turn on every connector?
No. Connectors should be enabled based on least privilege, auditability, user training, and the workflow’s real need for data access or write actions.