Skip to content

■ LIBRARY // CONCEPTS

Concepts

Core concepts of AI-powered personal operating systems: architecture, delegation principles, context management, and vibe coding with Claude Code

The mental models that make a personal operating system work. Understand the why before the how.

■ CONCEPT // HARD
10 AI Agent Failure Modes: Why Agents Break in Production The documented ways AI agents fail: hallucination cascades, context overflow, tool calling errors, and 7 more. Diagnosis patterns and fixes for each. Explore concept
■ CONCEPT // HARD
Agent Checkpointing: Save, Restore, and Rewind Autonomous Work How checkpoint systems enable long-running agent workflows by saving state periodically, allowing recovery from failures and rollback from bad decisions Explore concept
■ CONCEPT // HARD
Agent Guardrails: Input/Output Validation for Autonomous Systems How to implement runtime guardrails that validate agent inputs, filter outputs, and enforce business rules. Covers NeMo Guardrails, layered checking, and production patterns. Explore concept
■ CONCEPT // CORE
Agent Handoffs: When and How to Transfer Control Learn when to use agent handoffs vs single agents. Includes code patterns from OpenAI Swarm and practical implementation examples. Explore concept
■ CONCEPT // MEDIUM
Agent Memory Systems How AI agents implement memory: short-term context, long-term storage, vector retrieval, and the architecture that ties it together. Explore concept
■ CONCEPT // HARD
Agent Observability How to implement distributed tracing, logging, and monitoring for AI agents using OpenTelemetry and purpose-built tools like Langfuse and Braintrust. Explore concept
■ CONCEPT // CORE
agent-first documentation: writing for machines that read like humans how to write documentation that both humans and AI agents can actually use Explore concept
■ CONCEPT // HARD
Agentic Design Patterns: ReAct, Reflection, Planning, Tool Use When to use ReAct loops, self-critique, task decomposition, and tool calling in AI agents. A practical pattern library for building effective agent systems. Explore concept
■ CONCEPT // CORE
agentic loops: observe, plan, act, verify the core pattern of autonomous agents. simple in theory, messy in practice, and full of ways to fail. Explore concept
■ CONCEPT // CORE
AGENTS.md: How to Write Instructions for AI Coding Agents AGENTS.md tells AI coding assistants how to work on your project. Learn what to include, directory structure, examples, and common mistakes. Explore concept
■ CONCEPT // CORE
AI agent orchestration how multiple AI agents coordinate work — supervisor patterns, hierarchical delegation, swarm architectures, and when each makes sense. Explore concept
■ CONCEPT // CORE
AI code review patterns multi-pass review, confidence scoring, adversarial checking, and other patterns for using AI to review code without false confidence. Explore concept
■ CONCEPT // HARD
AI Memory Compression Techniques for compressing AI observations into retrievable semantic summaries that fit in context windows Explore concept
■ CONCEPT // CORE
AI sycophancy: why your assistant agrees too much and how to fix it understanding why AI models default to agreement and what to do about it Explore concept
■ CONCEPT // CORE
AI That Helps You BE, Not Just DO I tracked my screen for 16 days. the patterns I found — and why no AI tool bothered to show them to me. Explore concept
■ CONCEPT // CORE
ambient AI: when your assistant is always watching, always ready the promise and problems of always-on AI that observes your screen, hears your meetings, and proactively assists Explore concept
■ CONCEPT // EASY
Browser Agents AI that clicks, types, and scrolls your browser autonomously to complete web-based tasks Explore concept
■ CONCEPT // EASY
Building an AI Second Brain Transform AI from chatbot to persistent knowledge partner Explore concept
■ CONCEPT // CORE
CHOP: chat-oriented programming steve yegge coined it, the industry adopted it. CHOP is what happens when you stop typing code and start describing it. Explore concept
■ CONCEPT // CORE
cognitive offloading: when AI assistance becomes a crutch the hidden cost of outsourcing thinking to AI and when offloading becomes atrophy Explore concept
■ CONCEPT // CORE
cognitive prosthetic vs cognitive crutch when does AI assistance enhance cognition and when does it replace it? the bicycle-for-the-mind versus the wheelchair-for-the-mind, and how to tell the difference. Explore concept
■ CONCEPT // CORE
cognitive prosthetics: AI as assistive technology for neurodivergent minds how AI assistants work as executive function support for ADHD, autism, and other cognitive patterns Explore concept
■ CONCEPT // CORE
composable workflows: lego blocks for ai tasks the promise: small, reusable AI components that snap together into complex workflows. the reality: brittle, hard to debug, and full of edge cases. Explore concept
■ CONCEPT // CORE
context collapse and personal AI sociology's context collapse — when all your audiences merge into one — is now an AI problem. your AI doesn't know which you it's talking to. Explore concept
■ CONCEPT // CORE
context engineering context engineering is the discipline of crafting optimal context for AI agents — memory, retrieval, compression, and instruction design. Explore concept
■ CONCEPT // HARD
Context Rot: When More Tokens Mean Worse Results LLM performance degrades predictably as context windows fill up. Learn why this happens, how to detect it, and practical strategies to maintain output quality. Explore concept
■ CONCEPT // EASY
Context Window Management Keep your AI sharp by managing what fits in its working memory Explore concept
■ CONCEPT // CORE
convivial AI: Ivan Illich for the agent age Illich argued tools should enhance autonomy, not create dependence. applied to personal AI: what convivial design means, why your AI should be burnable, and the three tests every tool must pass. Explore concept
■ CONCEPT // CORE
data portability for AI owning your context, exporting your data, avoiding platform lock-in, and why the AI tool you use matters less than the data you feed it. Explore concept
■ CONCEPT // CORE
Digital Gardens Non-linear personal knowledge sites that grow over time. Not blogs. Notes evolve publicly without pressure to be finished. Explore concept
■ CONCEPT // CORE
digital twin: ai that models you an agent that knows how you think, decide, write, and work. useful, powerful, and deeply weird. Explore concept
■ CONCEPT // HARD
Episodic Memory for LLM Agents Give AI agents memory of specific past events with temporal context. The missing piece between semantic facts and procedural rules in the CoALA framework. Explore concept
■ CONCEPT // CORE
file over app: why ai should work with files, not databases steph ango's principle says apps are temporary, files are forever. ai tools ignore this. they shouldn't. Explore concept
■ CONCEPT // HARD
Graph Memory for Personal AI Knowledge graphs track relationships between people, projects, and time that vector databases miss. Build AI memory that understands context across sessions. Explore concept
■ CONCEPT // EASY
Human-on-the-Loop Move from approving every AI action to supervising agents that act autonomously, escalating only when confidence drops or risk rises. Explore concept
■ CONCEPT // HARD
Hybrid Retrieval: When RAG Meets Long Context Combine RAG retrieval with long-context windows strategically instead of treating them as competing approaches Explore concept
■ CONCEPT // HARD
Hybrid Search: Combining Keyword and Semantic Retrieval Vector search misses exact matches. Keyword search misses concepts. Hybrid search with reciprocal rank fusion combines both for personal knowledge bases. Explore concept
■ CONCEPT // CORE
identity as protocol identity isn't a profile or a personality test. it's a living protocol — a machine-readable document that routes AI behavior based on who you are, not what you've saved. Explore concept
■ CONCEPT // HARD
Late Chunking: Context-Aware Document Splitting for Better Retrieval Process entire documents through embedding models before splitting to preserve cross-chunk context that traditional chunking destroys Explore concept
■ CONCEPT // EASY
Learning in Public Stop lurking. Create learning exhaust: blogs, videos, talks. The fastest way to level up is documenting what you learn where others can find it. Explore concept
■ CONCEPT // EASY
Malleable Software Software as clay you reshape, not appliances you consume Explore concept
■ CONCEPT // HARD
MCP Server Composition Connect your AI agent to multiple MCP servers at once, combining calendar, database, files, and search through one protocol Explore concept
■ CONCEPT // HARD
Memory Attribution and Provenance Track where AI memories came from, when they were created, and how much to trust them Explore concept
■ CONCEPT // HARD
Memory Consolidation and Forgetting How AI agents consolidate short-term observations into long-term storage using sleep-inspired patterns, plus when and what to forget. Explore concept
■ CONCEPT // HARD
Model Quantization: Running 70B Models on a Laptop Reduce model precision from 32-bit to 4-bit to run large language models locally. Covers k-quants, GGUF, and choosing the right quantization level. Explore concept
■ CONCEPT // HARD
Multi-Agent Knowledge Management When a single AI can't handle your PKM needs, specialized agents working together can automate capture, processing, and synthesis. Explore concept
■ CONCEPT // HARD
Ollama vs vLLM vs llama.cpp vs LM Studio: choose the local runtime by job Choose a local LLM runtime by workload: Ollama for laptop/dev, llama.cpp for GGUF control, LM Studio for a desktop UI, and vLLM for multi-user serving. Explore concept
■ CONCEPT // EASY
Personal Search: Searching Your Own Data Build a search engine for your notes, journals, tweets, and memories instead of the web Explore concept
■ CONCEPT // EASY
Plan Mode in Claude Code Research before coding to avoid wrong approaches and hallucinations Explore concept
■ CONCEPT // CORE
Portable AI Identity: Own Your Context Across Platforms Portable AI identity lets your memory and preferences travel across ChatGPT, Claude, and any AI. Markdown files you control, not vendor lock-in. Explore concept
■ CONCEPT // HARD
Preference Learning: AI That Adapts to You How AI systems infer your preferences from interactions and adapt without configuration. Covers POPI, Mem0, LaMP benchmarks, and building preference-aware systems. Explore concept
■ CONCEPT // EASY
Principles for AI Delegation What to delegate to AI and what to keep human Explore concept
■ CONCEPT // EASY
Prompt Engineering for Agent Coding Structure prompts that make AI coding agents 30-40% more effective Explore concept
■ CONCEPT // CORE
Prompt Engineering Patterns That Work Five proven patterns to get better results from LLMs: chain-of-thought, few-shot, ReAct, prompt chaining, and role prompting with examples Explore concept
■ CONCEPT // CORE
Prompt Injection in Skill Files AI agents read project files like CLAUDE.md or AGENTS.md. These files can contain hidden instructions that hijack the agent. Here's how the attack works. Explore concept
■ CONCEPT // CORE
self as process, not profile MBTI, enneagram, 'I'm a visual learner' — frozen snapshots pretending to be people. real identity is tensions in motion, not labels in a database. Explore concept
■ CONCEPT // HARD
Self-Evolving Agents Build AI agents that improve through structured feedback capture, automated evaluation, and continuous retraining loops Explore concept
■ CONCEPT // HARD
Self-Updating Instructions (Procedural Memory) Build AI agents that modify their own operating instructions based on experience, feedback, and observed failures Explore concept
■ CONCEPT // EASY
Small Bets Stop betting everything on one startup. Build a portfolio of small projects that compound over time. Explore concept
■ CONCEPT // CORE
spec-driven development writing specs before code — the new TDD for agentic development, where the spec is the most important artifact and the code is almost a side effect. Explore concept
■ CONCEPT // HARD
Subagent Patterns: Parallel, Sequential, Background Three dispatch patterns for delegating work to AI subagents and when to use each one. Explore concept
■ CONCEPT // EASY
Terminal-Native AI Coding: Neovim with Claude Code Run Claude Code alongside Neovim in split terminal panes. Keep your vim keybindings while getting AI assistance. No VS Code required. Explore concept
■ CONCEPT // EASY
The Architecture of a Personal OS Personal OS architecture: interface, agent, memory, integration, and tool layers. Build your AI system incrementally in 4 weeks Explore concept
■ CONCEPT // CORE
the creepy line: where ai privacy boundaries should be google's ex-CEO said don't cross the creepy line. most ai tools crossed it on launch day and kept going. Explore concept
■ CONCEPT // CORE
the discomfort principle good AI should challenge you. if your personal AI only confirms what you already believe, it's a recommendation engine wearing a philosophy costume. Explore concept
■ CONCEPT // CORE
The Jagged Frontier AI capabilities have irregular boundaries. Some tasks it nails, others it fails spectacularly. Learn to map the frontier for your work. Explore concept
■ CONCEPT // CORE
the qualified self beyond quantified self, beyond second brain. from numbers to notes to narratives — the evolution toward self-knowledge that actually routes. Explore concept
■ CONCEPT // CORE
the skills ecosystem: how AI capabilities become composable tools understanding how plugins, skills, and tool discovery work in the emerging AI agent landscape Explore concept
■ CONCEPT // CORE
the three tests: Illich, discomfort, freezing three diagnostic questions for any personal AI system. can you burn it? does it challenge you? does it freeze you? a framework for evaluating whether your tools serve you or own you. Explore concept
■ CONCEPT // EASY
The Three-Layer Workflow Match your AI tool to the task: tab completion for most work, agents for multi-file changes, reasoning for architecture Explore concept
■ CONCEPT // CORE
token economics: the hidden cost structure of AI assistance understanding token pricing, context window costs, and how to optimize AI usage without going broke Explore concept
■ CONCEPT // HARD
Tool Routing: How AI Agents Pick Which Function to Call Modern agents route between dozens of tools using semantic matching, LLM-as-router, hierarchical patterns, and fallback chains. Patterns for scoring, selection, and MCP sampling. Explore concept
■ CONCEPT // MEDIUM
Tool Use Patterns: How LLMs Call External Tools Function calling, MCP protocol, and ReAct patterns for AI tool use. Learn when to use each approach and how to implement them. Explore concept
■ CONCEPT // EASY
Vibe Coding Building software through conversation instead of keystrokes Explore concept
■ CONCEPT // HARD
Vision-Based Web Automation: Why Screenshots Are Replacing Selectors How computer vision and multimodal LLMs enable browser agents that see pages like humans instead of parsing brittle DOM structures. Explore concept
■ CONCEPT // HARD
Voice-First Note Capture: Whisper to Structured Markdown Use whisper.cpp for local transcription, then LLM post-processing to convert rambling voice memos into structured notes with headers, bullet points, and action items Explore concept
■ CONCEPT // EASY
What is a Personal OS? A Personal OS is the user's control plane for memory, identity, permissions, tools, workflows, actions, receipts, and rollback across AI agents and devices. Explore concept
■ CONCEPT // CORE
what is MCP? the Model Context Protocol explained what is MCP (Model Context Protocol)? a non-technical explanation of how MCP works, why it matters, and how it connects AI agents to the world. Explore concept
■ CONCEPT // CORE
why your second brain is dead the storage-first PKM paradigm was built for a pre-AI world. the bottleneck moved from finding to routing. what you need isn't a second brain — it's a first self. Explore concept
■ CONCEPT // MEDIUM
World Models for Personal Agents Why agents need explicit state, consequence prediction, planning, guardrails, and mismatch detection outside the chat transcript. Explore concept

80 concepts indexed in the sovereign library.