| // Use your MDX content with this component. | |
| import React from 'react' | |
| import MDX from '@mdx-js/runtime' | |
| import components from '../utils/markdown/markdown' | |
| // Renders a cimple loading spinner as a test | |
| import Loading from './Loading' | |
| const mdxComponents = { |
| /* An example app that uses expo-auth-session to connect to Azure AD (or hopefully most providers) | |
| Features: | |
| - secure cache with refresh on load | |
| - securely stored refresh token using expo-secure-store | |
| - uses zustand for global access to the token / logout | |
| Based on [this gist](https://gist.github.com/thedewpoint/181281f8cbec10378ecd4bb65c0ae131) | |
| */ |
A single prompt (~1400 tokens), placed in a project's .claude/CLAUDE.md, can bootstrap a Claude Code instance into a self-improving system — one that captures learnings, extracts patterns, evolves its own configuration, and gets meaningfully better at helping its user with each session.
No pre-built infrastructure required. No user-level config. No hooks, skills, templates, or elaborate folder hierarchies. Just a seed and the affordances Claude Code already provides.
A pattern for building personal knowledge bases using LLMs.
This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.
Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.
