Prompting Claude Fable 5  🔗 **Source:** [Prompting Claude Fable 5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5) ## Highlights - Claude Fable 5 takes on problems that were previously too complex, long-running, or ambiguous for prior models, and is particularly effective at end-to-end work that takes a person hours, days, or weeks to complete. - Note: 📚 Claude Fable 5 excels at multi-day autonomous workflows requiring sustained focus · - Opening capability statement in the documentation - Core value proposition differentiating from previous models - Sets expectation for appropriate use cases (complex, not routine work) · #atom/literature/h1 - Effort is the primary control for the trade-off between intelligence, latency, and cost on Claude Fable 5. Use high as the default for most tasks, with xhigh for the most capability-sensitive workloads and medium or low for routine work. - Note: 📚 Effort levels replace prompt complexity as the primary performance control · - Key operational guidance for teams migrating from previous models - Replaces complex prompt engineering with simple parameter adjustment - Lower effort on Fable 5 still exceeds previous models' maximum performance · #atom/literature/h2 - Claude Fable 5 performs particularly well when it can record lessons from previous runs and reference them. Provide a place to write notes, as simple as a Markdown file. - Note: 📚 Memory systems significantly improve Claude Fable 5 performance across sessions · - Specific guidance in "Construct a memory system" section - Simple implementation (Markdown files) with structured format - Enables learning transfer and consistency across similar tasks · #atom/literature/h3 - Long-horizon AI requires infrastructure changes before capability changes - Note: [[Infrastructure-as-code practices]] — because extends to AI agent deployment · - [[Infrastructure-as-code practices]] — because extends to AI agent deployment · #atom/zettel/z1 - Test memory system effectiveness across different technical domains #fleeting - Note: ✏️ Fleeting capture #atom/fleeting/f1 - Investigate safety classifier false positive rates for WordPress security work #fleeting - Note: ✏️ Fleeting capture #atom/fleeting/f2 - Compare effort-level performance curves across development task categories #fleeting - Note: ✏️ Fleeting capture #atom/fleeting/f3