Anthropic Publishes Prompting Guidance For Claude Opus 5.5

Anthropic published a prompting guide for Claude Opus 5.5, which launched Sept. 22, advising developers to test multiple effort levels rather than reuse Claude Opus 5 settings and to remove system-prompt lines telling the model to think carefully. Opus 5.5 defaults to medium effort, one level below Opus 5's high default, and thinking can no longer be turned off — requests that try return an error. Anthropic's testing found Opus 5.5 at medium effort matches or surpasses Opus 5 at high effort on coding and knowledge work, and removing a think-carefully line in a chat product made replies start sooner with "no clear decline in the quality of the reply.

Anthropic’s prompting guide for Claude Opus 5.5 https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5 advises developers to test multiple effort levels instead of reusing the setting used in Claude Opus 5. It also suggests chat applications remove system-prompt lines instructing Claude to think carefully before responding. Opus 5.5 launched Sept. 22 https://www.anthropic.com/claude-opus-5-5 . The guide says Opus 5 prompts should still work well without edits, and that the company’s Opus 5 guidance is a reasonable place to start. When the company tested this in a chat product, removing a think-carefully line made replies start sooner, with “no clear decline in the quality of the reply.” Opus 5.5 Defaults To Medium Effort Opus 5.5 runs at medium effort by default, one level below the high default on Opus 5. Thinking can’t be turned off on Opus 5.5, and requests that try get an error. Opus 5 allowed that at high effort or below. The guide calls effort the first setting to adjust when balancing quality against speed and cost. In Anthropic’s testing, Opus 5.5 at medium effort matches or even surpasses Opus 5 at high effort when it comes to coding and knowledge work. To cut thinking, the guide says to try lower effort settings before prompt changes, and save the higher levels like xhigh and max for tasks where they really make a difference in quality. Anthropic Suggests Reconsidering “Think Carefully” In Chat The guide’s reason for suggesting chat apps reconsider think-carefully lines is that Opus 5.5 decides for itself how much to think, with effort as the main control. Anthropic’s own docs include that kind of line. For Claude Opus 4.7, when effort has to stay low to keep responses quick, its page on effort https://platform.claude.com/docs/en/build-with-claude/effort recommended-effort-levels-for-claude-opus-4-7 suggests adding guidance such as “This task involves multistep reasoning. Think carefully before responding.” Agent Guidance Covers Time Budgets And Pasted Text For agent teams, the guide recommends using a time budget based on how long tasks might take. With Opus 5.5, the software helps by tracking elapsed time. Anthropic’s tests have shown that small agent groups, when using time signals, finish research tasks quicker than a single agent working without signals. Even under time budgets, these groups managed to achieve answer quality comparable to solo agents. The guide emphasizes that the time budget is just a suggestion, and setting a strict timeout can be quite helpful. The model might perform slightly less thoroughly under pressure. For users who input text from sources like emails, the guide suggests using tags with a random ID and adding a system note on how to manage tagged text. This approach encourages careful handling and, since tags are plain text that can be copied, they provide only one layer of protection against prompt injection. Why This Matters Several sections of the Opus 5.5 guide ask developers to re-check setup carried over from older models, such as workarounds for reading charts and screenshots, or instructions written for running with thinking off. The Fable 5.1 guide, which Roger Montti covered earlier this month https://www.searchenginejournal.com/anthropic-shares-power-prompts-that-improve-ai-results/589448/ , asked developers to revisit formatting rules. An app that never sets effort runs at medium on Opus 5.5 without any code change. Looking Ahead Using an output cap max tokens for Opus 5 with ‘thinking off’ might cut responses off on Opus 5.5. The guide mentions that ‘thinking’ uses some of that cap even when you don’t see it. For frontend projects, the Opus 5.5 guide recommends setting clear styles to avoid defaults like cream backgrounds and pill-shaped buttons. Vague requests to steer clear of a generic AI look often just switch one default for another. Featured Image: Samuel Boivin/Shutterstock