Prompting Claude Opus 5.5
Behavioral differences from Claude Opus 5 and the prompting and harness patterns that address them: effort calibration, thinking behavior in API integrations and chat, progress updates, unattended and multiagent tasks, safeguard refusals, frontend design, complex visual inputs, multi-app workflows, and pasted text in user messages.
Summary
Claude Opus 5.5 introduces significant behavioral changes compared to its predecessor, focusing on improved prompting techniques and handling of multiagent tasks. The article details how these updates enhance API integrations, visual input processing, and user experience in chat environments.
Comments (218 of ) ⌛