Anthropic has updated the system prompt for its Claude Opus 4.7 model, introducing changes that refine its behavior and capabilities. The update renames the "developer platform" to "Claude Platform" and adds new integrated tools like "Claude in Chrome," "Claude in Excel," and "Claude in Powerpoint." Significant enhancements have been made to child safety protocols, with stricter caution advised after a refusal, and the model is now instructed to be less pushy when a user wishes to end a conversation. Additionally, Claude Opus 4.7 is designed to act more proactively by using tools to resolve ambiguities before asking the user for clarification and aims for more concise responses. AI
Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →
RANK_REASON Analysis of system prompt changes for a specific model version from a major AI lab.