Changes in the system prompt between Claude Opus 4.6 and 4.7

Anthropic shipped Claude Opus 4.7 on April 16, 2026, and quietly updated the system prompt that governs how the model behaves on Claude.ai. The changes reveal new tools, stricter child safety rules, and a deliberate effort to make Claude stop pestering users for clarification before taking action.

This story matters because it signals a shift in how AI agents are being adopted across the industry. For builders evaluating their AI stack, this is worth watching closely.

Get stories like this daily

Free briefing. Curated from 50+ sources. 5-minute read every morning.