---
format: "aidr-story-markdown/v1"
id: "72a68f793144bdd2ac1a0c12bdf9edb1cc1802351efa78ccb88cafdce3e491b0"
canonical_url: "https://aidr.today/72a68f79?lang=en"
title: "Prompting Claude Opus 5.5"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-28T07:33:29.000Z"
category: "Models"
topics: ["anthropic","llm"]
source_urls: ["https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5","https://news.ycombinator.com/item?id=49874728"]
summary: "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."
---

# Prompting Claude Opus 5\.5

> [Open the canonical story](<https://aidr.today/72a68f79?lang=en>)

**Published:** 2026-09-28T07:33:29.000Z
**Category:** Models
**Topics:** anthropic, llm

## Summary

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\.

## Sources

- [Story source](<https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5>)
- [Discussion](<https://news.ycombinator.com/item?id=49874728>)