Learn
Practical guides on prompting, tools, and building with AI. No fluff. All free.
I Gave My Skills Repo a Publish Button That Can't Leak Its Own Key
Packaging 13 skills for Claude Code and Codex, then splitting the build job from the push job so no branch can touch the token.
Read guide →A Text Editor Is a Security Decision
Autosave, a Mark Done button that never publishes, and an allowlist that decides what gets stored. Building Switchpath's project workspace, step 7.
Read guide →I Ran a Security Audit on My Own Vibe-Coded App and Found the Scary Part Isn't What You'd Expect
Two chat routes with no rate limiting, pointed straight at a shared API key, and why that's a money problem, not a data-theft problem.
Read guide →The 'Locked In For Life' Pricing Promise That Didn't Need Any Special Code
Rebuilding a messy pricing model into four clean tiers, and the one Stripe rule that made a big promise trivial to keep.
Read guide →The Citywide Rewrite I Talked Myself Out Of Building
Separating the impressive version of a fix from the version that actually solves the problem in front of you.
Read guide →Building an External Memory So Claude Stops Forgetting Everything on Reset
A two-file system for picking up exactly where a session left off, instead of starting from zero.
Read guide →The Assessment Tool That Almost Only Worked for People Already Using Claude
How a single question about distribution flipped an entire product's architecture.
Read guide →Two Half-Finished PRDs for the Same Product Is Its Own Kind of Debt
Merging two drafts into one 16-section document, and the one open question worth deliberately not answering yet.
Read guide →Before Writing Code, I Mapped Every Place the App Should Act on Its Own
Eight automatic behaviors, each with a trigger and an approval gate, mapped before a single line of Firstflow got built.
Read guide →The Step I Used to Skip: Deciding What the App Should Automate Before I Design the Database
Why mapping automation-versus-human-decision first changed the database design for a career-portfolio tool.
Read guide →The Difference Between a Vercel Subdomain and a Real Home
Closing the gap from a working Vercel URL to a real, owned domain, and the DNS records that mattered.
Read guide →What Almost 1,500 AI Sessions Actually Look Like, Mapped Out
Building a force-directed graph of my own usage instead of staring at a session count that didn't mean anything on its own.
Read guide →One Static HTML File With No Version Control Was Running My Whole Dashboard
The moment a personal dashboard felt risky enough to rebuild properly, and the reframe that turned a cleanup into an operating system.
Read guide →Does Someone Who Buys Your AI Agent Actually Own Anything?
Three different places an agent can live, and why that's a pricing decision, not just a technical one.
Read guide →Shipping Isn't Just Clicking Deploy: The DNS Setting That Almost Broke Email
What actually happened getting AI with AI Labs from finished code to a live domain.
Read guide →The Site Reverted to a Blank Word Document: Here's How the Actual Bug Got Found
Diagnosing before touching anything, and turning an emergency fix into a real design decision.
Read guide →The Framework That Changed How I Think About What AI Should Automate
Why the 'easy' work you keep automating away might be the practice rounds your judgment is built on.
Read guide →The Automation I Built That Refused to Log Into GitHub For Me
A Monday-morning sync routine, and the one line Claude wouldn't cross even though it could have found a workaround.
Read guide →The Same Question Kept Coming Up, So It Became a Skill Instead of Staying Buried in Chat History
Packaging hackathon troubleshooting into a reusable reference so the next integration starts from what was already learned.
Read guide →The First Real Decision in a Multi-Agent Hackathon Build Wasn't About Agents
Choosing a database under deadline pressure, and why the boring infrastructure call was the one that actually mattered.
Read guide →The Council Said Finish v1 First: So I Did, and Wrote v2 in Parallel
What happened after the LLM Council's verdict: shipping the thing in front of you before chasing the bigger vision.
Read guide →What Claude Code's Dynamic Workflows Actually Do (And Why I Didn't Build With It Yet)
Reading about a feature before you build around it, and finding out it's three pricing tiers away.
Read guide →The One File That Stopped Me From Re-Explaining Myself Every Session
What a CLAUDE.md file actually does, and what building a good one forces you to realize about your own working style.
Read guide →"No Changes Needed" and an Empty Database: What Vibe Coding Actually Looks Like
The gap between code that exists and code that runs, and why the debugging loop isn't you doing it wrong.
Read guide →Running an LLM Council on My Own Product Decision
Five AI advisers, radically different perspectives, one clear call instead of a hedge.
Read guide →I Had Never Added Up My Own AI Usage Until a Job Posting Made Me Look
647 Cowork sessions, 11,000+ Claude Code messages, 7.3 million tokens: the resume line most daily AI users haven't counted yet.
Read guide →Eleven Days Before a Deadline, I Almost Scrapped a Finished PRD
Using AI as an advisor with permission to disagree with you, instead of a cheerleader.
Read guide →Building a Focus System That Doesn't Assume a Neurotypical Brain
A two-day build: an auto-starting focus timer, then a hard 4-hour stop instead of a gentle reminder.
Read guide →Teaching Claude Your Voice (Without Just Describing It)
Why showing Claude real examples of how you talk beat trying to describe your own writing style.
Read guide →Picking a Buildathon Project Isn't a Product Decision: It's a Positioning One
Using AI to research what actually wins, instead of defaulting to whichever idea felt most exciting.
Read guide →The Product Name I Had Locked Turned Out to Belong to Someone Else
A near-miss with a name collision, and what it taught me about naming as positioning, not branding.
Read guide →Moving a Project From Lovable to Claude Code Is a Smaller Lift Than You'd Think
What actually changes and what actually stays the same when you migrate a no-code build into full code.
Read guide →I Made the Skills Behind My Own Build Process Public
Six Claude skills, free on GitHub, and why lowering the floor for other builders is the whole point.
Read guide →Claude vs ChatGPT vs Claude Code: What Each One Is Actually For
A practical breakdown of three AI tools most people use — not which is best, but what each one does that the others don't.
Read guide →Why Free Tools Are a Trust Test
Why this site gives real things away for free — and what that has to do with everything else on it.
Read guide →Picking your first AI tool
A short decision guide for choosing between ChatGPT, Claude, and Claude Code — based on what you're actually trying to do.
Read guide →How to write a prompt that doesn't fall apart
A practical structure for prompts that produce useful output the first time: context, task, format, constraints.
Read guide →What is an AI artifact?
A prompt, snippet, or template you built with AI — small, reusable, and worth saving. Here's what makes something an artifact and why that distinction matters.
Read guide →Want a structured path instead of one-off guides?
Join the Build Room — live coworking with a community that builds alongside you.