Insights
Founder and builder perspectives on AI tools, thinking patterns, and the new way of working
Showing 205-216 of 336
Give Your Agent a Memory File: Persistent-Lesson Skills for Long-Horizon Runs
Fable 5 performs strongly with a markdown memory system. Here's the exact format Anthropic recommends, how to package it as a reusable skill, and why one lesson per file beats a growing scratch log.
Parallel Subagents by Default: Orchestration Patterns Fable 5 Rewards
Fable 5 dispatches parallel subagents more readily than older models. Spawn-and-block leaves that capability on the table. Here are the orchestration patterns that actually pay off.
Minutes-Long Turns Break Your Harness: Designing Async Agents for Fable 5
Fable 5 turns can run for minutes and autonomous runs for hours. If your harness assumes sub-30-second replies, it will time out mid-thought. Here's how to redesign for long turns.
Effort Is the New Dial: Routing Skills and Subagents from low to max
Fable 5 replaces the token budget with five effort levels. Here's how to route skills and subagents — routine work at low-medium, long-horizon at xhigh-max — plus what Claude Code's ultracode really is.
Don't Tell Claude to Show Its Work: The reasoning_extraction Trap in Skill Prompts
On Fable 5, asking the model to explain its reasoning or show its work can be refused with category reasoning_extraction and elevates fallbacks. Read the summarized thinking blocks instead.
Building Fallback-Aware Agents: Handling Fable 5's Refusal Stop Reason
Fable 5 refusals arrive as HTTP 200 with stop_reason refusal — not an error. Check it before reading content, and wire a server-side or client-side fallback to Opus 4.8. Code and a checklist inside.
Your Claude Code Skills Are Too Prescriptive for Fable 5
Anthropic says skill prompts written for older models are often too prescriptive and degrade Fable 5's output. Here's how to audit yours and swap step-by-step scripts for goal-and-constraints.
Claude Fable 5, Explained for Skill Builders: What Changes When You Build on Anthropic's New Flagship
Anthropic's Claude Fable 5 changes six things at once for anyone building skills and agents: always-on thinking, an effort dial, 1M context, new pricing, a refusal stop reason, and 30-day retention.
Trust Is a Design Material — and Taste Is Still Yours
Trust is a design material: confidence, citations, transparency, rubrics, guardrails, and handoffs. The series closer — skills set the floor, taste is yours.
System Prompts Are Design: Persona, Tone, Constraints
A system prompt is an interface. Architect it like one — labeled anatomy, important instructions first and last, parameterized templates, and testable constraints.
Designing AI Product Behavior, Not Just Pixels
The next design surface isn't the layout — it's how the product behaves. Context budgeting, turn-taking, generative UI, and frustration repair, in one skill.
Driving Blender and After Effects by Prompt
Direct 3D and motion graphics by prompt. Claude writes the Blender bpy Python and After Effects ExtendScript over MCP while you art-direct the result.