Zettelkasten Explained Simply: How to Get Started
Notes pile up but the system doesn't work: links get saved, summaries get written, and none of it turns out to be usable later. Here's Zettelkasten without a Luhmann biography or an app comparison: what the method actually is, what notes you need, how to link them properly, and the one step to start with today.
AI and Learning: What Helps vs What Just Feels Like Progress
AI made explanations cheap, but it also got good at sounding convincing even when you haven't actually learned anything. Here's which scenarios actually train a skill, which ones just create the illusion of understanding, and the Rust example where I fell for it myself.
How to Connect AI Video Notes to Your Knowledge Base
A shelf of fifty AI video summaries nobody ever reopens isn't a knowledge base, it's an archive. A full pipeline for turning a summary into connected knowledge: separating source from knowledge, letting AI suggest links while you confirm them, and feeding what you already know back into the next video.
Prompt Engineering for Document Analysis
A prompt for document analysis isn't a one-off phrasing, it's a spec for a procedure: role, context, criteria, constraints, and output format. Covers how to build prompts for extraction, comparing sources, catching contradictions, and multi-step analysis, and how to test them across different documents instead of just the one that happens to work.
Why Small Teams Outpace Large Ones
More people almost always means more total hours worked, but not more speed. As a team grows, so does the number of connections between its members, and part of every added hour goes to coordination instead of the task. Here's what that overhead is actually made of, where a small team genuinely wins, and where "small" just means small, not fast.
AI Chat with PDF: How to Work with Large Documents Using AI
A PDF no longer has to be read cover to cover. You can just ask it about a specific clause, figure, or section instead. Here's how AI chat with a document actually works, what's worth asking it, where it gets things wrong, and how it differs from plain search and from a regular ChatGPT conversation — plus what this looks like in practice in Cruxly.
Focus and Deep Work in the Age of AI Distractions
AI has cut the barrier to switching attention to almost nothing: you can ask anything in a second without leaving your work context, and that ease is exactly what makes switching so tempting. Here's how AI both breaks and protects the ability to work deeply, and how to set boundaries around it instead of cutting the tool out entirely.
How Not to Burn Out: Burnout Prevention
Burnout prevention doesn't come from one good vacation or willpower alone — it comes from systematically adjusting workload, boundaries, recovery, and the way you structure work itself. Here's how burnout differs from ordinary fatigue, what structurally causes it, how to catch the early signs, and what actually works for prevention versus what just mutes the symptom for a while.
AI Code Review: How to Automate Reviewing Code
Tests pass, the linter is quiet, and there's still a logic bug sitting in the code. Here's how AI review actually works under the hood, what's worth handing it, how to wire it into CI/CD and Pull Requests without drowning in noise, and why the decision to merge still belongs to a human.
AI and the Future of the Engineering Profession
If a machine can write most of the code, what's the engineer's value then? Here's the shift from producing code to building systems: what AI already takes over, why architectural thinking and verification get more expensive, what happens to junior and senior roles, and why accountability for what ships still sits with a human.
Productivity Systems: How to Organize Work and Life
GTD, time-blocking, energy management, personal Kanban: all of them work for someone and fall apart for someone else. Here's what a productivity system is actually made of, how to pick one that fits, and why most systems break down not from laziness, but from a bad fit for the specific person using them.
How I Build AI Products Solo: Cruxly and Planio
Two products, zero co-founders. Here's how I decide what to build, where Claude Code actually fits into that, why Planio looks nothing like Cruxly, and what failed before any of it started working.
Architecture for AI-Driven Development
An agent struggles with a tangled system just as much as a person does. Here's how repo structure, documentation, naming conventions, and autonomy boundaries determine how much an AI agent can actually help.
AI Video Notes: How to Quickly Summarize Lectures
A one-hour video can turn into a structured summary in a minute instead of half an hour of manual work. Here's how it works under the hood, how to get a summary you can actually trust, and what to do with it afterward so it doesn't get lost among hundreds of other notes.
AI Tutor: Set Up ChatGPT or Claude as Your Teacher
Tutor mode doesn't turn itself on. By default, the model solves the problem for you instead of walking you toward the answer. Here are working prompts for different subjects, and what to do when the model still slips back into handing you finished answers.
How AI Helps You Break Through a Learning Plateau
A plateau rarely means "work harder." It's usually a signal that you're stuck at the wrong difficulty level or practicing the wrong skill, and AI is genuinely good at that diagnosis, if you know what to ask it.
AI for Developers: How AI Is Changing Software Engineering
The developer's job is shifting from writing code to defining tasks and checking the output. Here's what's actually changed in engineering work: from code review and testing to hiring and technical debt.
AI Second Brain: Building a Personal Knowledge System
Notes nobody ever rereads aren't a system, they're a pile. Here's how to build a second brain that actually works: from atomic notes and Zettelkasten to AI-powered connection search that surfaces links you'd never have spotted yourself.
Building with AI Coding Assistants: A Practical Workflow
This site was built end to end alongside Claude Code, from the Rust backend to the text you're reading right now. Here's how that workflow is actually put together: setup, CLAUDE.md, review, autonomy boundaries, and the failures that taught me most of it.
AI for Researchers: A Workflow for Working with Sources
Five open PDF tabs, three articles bookmarked for later, and not one coherent note about what's actually in them. Here's the workflow: from organizing sources to synthesizing information into one accurate piece of writing.
How to Learn with AI: The Complete Guide
Most people use AI for learning the wrong way: either as a machine that does the work for them, or they avoid it out of principle. Here's what actually works, from tutor-mode prompts to spaced repetition and study plans that survive contact with reality.