Concepts

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

easy first

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. 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 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. 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. Agent Memory Systems How AI agents implement memory: short-term context, long-term storage, vector retrieval, and the architecture that ties it together. Agent Observability How to implement distributed tracing, logging, and monitoring for AI agents using OpenTelemetry and purpose-built tools like Langfuse and Braintrust. agent-first documentation: writing for machines that read like humans how to write documentation that both humans and AI agents can actually use 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. agentic loops: observe, plan, act, verify the core pattern of autonomous agents. simple in theory, messy in practice, and full of ways to fail. 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. AI agent orchestration how multiple AI agents coordinate work — supervisor patterns, hierarchical delegation, swarm architectures, and when each makes sense. AI code review patterns multi-pass review, confidence scoring, adversarial checking, and other patterns for using AI to review code without false confidence. AI Memory Compression Techniques for compressing AI observations into retrievable semantic summaries that fit in context windows 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 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. 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 Browser Agents AI that clicks, types, and scrolls your browser autonomously to complete web-based tasks Building an AI Second Brain Transform AI from chatbot to persistent knowledge partner 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. cognitive offloading: when AI assistance becomes a crutch the hidden cost of outsourcing thinking to AI and when offloading becomes atrophy 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. cognitive prosthetics: AI as assistive technology for neurodivergent minds how AI assistants work as executive function support for ADHD, autism, and other cognitive patterns 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. 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. context engineering context engineering is the discipline of crafting optimal context for AI agents — memory, retrieval, compression, and instruction design. 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. Context Window Management Keep your AI sharp by managing what fits in its working memory 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. 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. Digital Gardens Non-linear personal knowledge sites that grow over time. Not blogs. Notes evolve publicly without pressure to be finished. digital twin: ai that models you an agent that knows how you think, decide, write, and work. useful, powerful, and deeply weird. 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. 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. 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. Human-on-the-Loop Move from approving every AI action to supervising agents that act autonomously, escalating only when confidence drops or risk rises. Hybrid Retrieval: When RAG Meets Long Context Combine RAG retrieval with long-context windows strategically instead of treating them as competing approaches 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. 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. 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 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. Local LLM Runtimes: When to Use Ollama vs vLLM Ollama excels for single-user development with simple setup. vLLM delivers 20x higher throughput for production multi-user deployments. Choose based on your workload. Malleable Software Software as clay you reshape, not appliances you consume MCP Server Composition Connect your AI agent to multiple MCP servers at once, combining calendar, database, files, and search through one protocol Memory Attribution and Provenance Track where AI memories came from, when they were created, and how much to trust them 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. 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. Multi-Agent Knowledge Management When a single AI can't handle your PKM needs, specialized agents working together can automate capture, processing, and synthesis. Personal Search: Searching Your Own Data Build a search engine for your notes, journals, tweets, and memories instead of the web Plan Mode in Claude Code Research before coding to avoid wrong approaches and hallucinations 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. 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. Principles for AI Delegation What to delegate to AI and what to keep human Prompt Engineering for Agent Coding Structure prompts that make AI coding agents 30-40% more effective 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 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. 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. Self-Evolving Agents Build AI agents that improve through structured feedback capture, automated evaluation, and continuous retraining loops Self-Updating Instructions (Procedural Memory) Build AI agents that modify their own operating instructions based on experience, feedback, and observed failures Small Bets Stop betting everything on one startup. Build a portfolio of small projects that compound over time. 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. Subagent Patterns: Parallel, Sequential, Background Three dispatch patterns for delegating work to AI subagents and when to use each one. 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. The Architecture of a Personal OS Personal OS architecture: interface, agent, memory, integration, and tool layers. Build your AI system incrementally in 4 weeks 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. 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. The Jagged Frontier AI capabilities have irregular boundaries. Some tasks it nails, others it fails spectacularly. Learn to map the frontier for your work. the qualified self beyond quantified self, beyond second brain. from numbers to notes to narratives — the evolution toward self-knowledge that actually routes. the skills ecosystem: how AI capabilities become composable tools understanding how plugins, skills, and tool discovery work in the emerging AI agent landscape 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. The Three-Layer Workflow Match your AI tool to the task: tab completion for most work, agents for multi-file changes, reasoning for architecture token economics: the hidden cost structure of AI assistance understanding token pricing, context window costs, and how to optimize AI usage without going broke 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. 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. Vibe Coding Building software through conversation instead of keystrokes 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. 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 What is a Personal Operating System? What is a personal operating system? Learn how AI agents like Claude Code manage your tasks, memory, calendar, and decisions autonomously 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. 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.

79 concepts