Claude system prompts documentation updated

Anthropic has refreshed its technical documentation on system prompts in the API. Developers now have guidance on tuning model behavior through top-level instructions.
The materials cover methods for controlling tone, response formats, and safety limits. The documentation is in the official developer section on Anthropic’s site.
Up next
Claude Code v2.1.186 update
Claude Code v2.1.186 makes model responses to bash output the default. The model now proactively engages with bash command output, rather than just considering context. The update also adds direct MCP server authentication from the terminal, streamlining SSH workflows.
Related stories
- Claude helped make claude.ai 3x faster in two weeks
- New Claude Cookbook guides cover search benchmarks, safety fallbacks, and multi-agent patterns
- Linear and Ramp users can pay for Claude without an API key
- Fable 5.2 keeps thinking when told to answer directly
- Claude expands MCP Apps support with app tools and more
- Claude guide: start on Opus 5.5, try Fable 5.2 before max
Comments
No comments yet. Be the first.
Join the conversation
Sign in to leave a comment. It appears after moderation.

