We scan new podcasts and send you the top 5 insights daily.
James McAulay heard at agent company Jack and Jill that someone asked an agent how to improve its own system prompt, then implemented the ten-step answer. He says most people miss that file-based agents can inspect and rewrite their own instructions, unlike cloud chat, which cannot easily edit its own setup.
While Claude's built-in 'create skill' tool is clunky, its output reveals a highly structured template for effective prompts. It includes decision trees, clarifying questions for the user, and keywords for invocation, serving as an invaluable guide for building robust skills without starting from scratch.
Before delegating a complex task, use a simple prompt to have a context-aware system generate a more detailed and effective prompt. This "prompt-for-a-prompt" workflow adds necessary detail and structure, significantly improving the agent's success rate and saving rework.
Instead of spending time trying to craft the perfect prompt from scratch, provide a basic one and then ask the AI a simple follow-up: "What do you need from me to improve this prompt?" The AI will then list the specific context and details it requires, turning prompt engineering into a simple Q&A session.
Instead of manually refining a complex prompt, create a process where an AI agent evaluates its own output. By providing a framework for self-critique, including quantitative scores and qualitative reasoning, the AI can iteratively enhance its own system instructions and achieve a much stronger result.
The easiest way to teach Claude Code is to instruct it: "Don't make this mistake again; add this to `claude.md`." Since this file is always included in the prompt context, it acts as a permanent, evolving set of instructions and guardrails for the AI.
To create a self-improving system, establish a loop where after you manually refine an AI's output, you prompt it to reflect on the entire conversation. Ask it to suggest specific updates to its own underlying skill and evaluations to avoid the same manual corrections in the future.
Instead of preloading all context into a single system prompt, modern agentic systems use file-based skills. The agent references a directory and loads only the specific instructions or resources relevant to a task, improving efficiency, scalability, and reusability.
Replit uses an internal agent that analyzes user interaction traces, identifies errors, generates prompt changes to fix them, submits them as pull requests, and initiates A/B tests. This creates an autonomous, self-improving loop for the platform's AI capabilities.
The best AI results come from iterative refinement. After an initial build, continue conversing with the agent to tweak outputs. Tell it to adjust sentence structure or writing style and redeploy. This continuous feedback loop is key to improving performance.
Instead of manually maintaining your AI's custom instructions, end work sessions by asking it, "What did you learn about working with me?" This turns the AI into a partner in its own optimization, creating a self-improving system.