Claude and All Its Features
Anthropic's Claude is built around a strong safety framework and deep support for long-context, agentic, and coding workflows.
Long context window
Can hold very large documents, codebases, or conversation histories in a single session.
Artifacts
Generates interactive content — code, documents, diagrams — in a dedicated, editable side panel.
Projects
Groups conversations and reference material together for consistent, ongoing work.
Agentic coding
Tools like Claude Code let Claude plan, write, and execute multi-step coding tasks directly in a project.
Computer use
Can operate a computer interface directly — clicking, typing, and navigating software on your behalf.
Safety focus
Trained with a 'Constitutional AI' approach emphasizing helpfulness balanced with harmlessness.
What is 'Constitutional AI'?
A training approach where the model is guided by a written set of principles ('a constitution') to critique and improve its own responses, rather than relying solely on human feedback for every judgment call.
Key takeaways
- Claude emphasizes long context, Artifacts for interactive content, and Projects for organized ongoing work.
- Claude Code and computer-use capabilities support genuinely agentic, multi-step task execution.
- Claude is built around a Constitutional AI safety approach that balances helpfulness with harmlessness.
Check your understanding
0/2 answered1.What does the 'Artifacts' feature in Claude let you do?
2.Constitutional AI relies solely on human feedback for every safety judgment, with no written guiding principles.
Lesson summary
Claude combines long-context reasoning, Artifacts, Projects, and agentic coding/computer-use tools with a safety-first Constitutional AI training approach.
AI-generated notes