Find your next useful read.

Browse the library

62 resources

• Chapter 016 min read

  AI as an Operating System

  Three instances ran while I slept and dropped a finished morning brief in one Slack channel. The unlock isn't AI doing my work faster — it's AI deleting my context-switching across forty open tabs. Stop visiting a chatbot. Start living inside an OS.

  General
• Chapter 028 min read

  The Five-Tool Stack

  I get asked once a week what's in my stack. People want a list of thirty. The honest answer is five. Each tool plays one role — head chef, sous chef, walk-in fridge, mobile cook, voice — and the discipline is refusing to blur them. Surface area is the enemy.

  General
• Chapter 037 min read

  Why Claude Forgets You

  The single most expensive cognitive error in modern business is treating AI like a coworker you're slowly training. It isn't. Every session is a fresh temp on day one — sharp, capable, amnesiac. Once that lands, you stop hoarding chat history and start running a workforce.

  General
• Chapter 049 min read

  Obsidian as Working Memory

  My paid mentee has been feeling my AI's work for over a year and has never met it. The trick is a vault — folder of markdown files I hand every fresh instance on wake-up. Without it, the model is a genius with amnesia. With it, you have an OS that compounds for years.

  General
• Chapter 058 min read

  What a Skill Is

  If you're re-explaining the same workflow to Claude every time, you're paying full cognitive cost on every order. Skills are the recipe card pinned above the burner — a folder, a SKILL.md, a description that fires when you need it. Skills are the difference between using AI and operating AI.

  General
• Chapter 0611 min read

  Parallel Subagents and Fan-Out

  This 25,000-word book was written by 15 AI agents in parallel in six minutes wall-clock for under $40. Once you've used a swarm, sequential work feels like writing email by candlelight. The model didn't get smarter that morning — the architecture got smarter. You don't need a bigger model. You need a conductor's mindset.

  Claude
• Chapter 077 min read

  Scheduled Tasks

  Synchronous AI is a vending machine — useful only when you walk up to it. Scheduled tasks turn AI into a chef who preps meals before you sit down. The Saturday canvas that closes your week, the morning brief that lands before your coffee — they're not bigger models. They're scheduling decisions.

  Building Products
• Chapter 087 min read

  Chat, Cowork, or Claude Code?

  Same model, three surfaces. Most operators have one Claude tab open and think Claude is one thing. Sedan, SUV, pickup — knowing which one to drive when is half the unlock. Get the choice wrong and you spend an hour on what should take ten minutes.

  Claude
• Chapter 097 min read

  Blast Radius and Key Hygiene

  Eleven minutes — that's how long it took for a leaked Stripe key to drain $4,200 from a friend's startup. Agents are 10x contractors and 10x attack surfaces; the part that doesn't get airtime in keynotes is what'll wake you up at 3 AM. Skim this chapter least; read it most.

  Security
• Chapter 108 min read

  Hosted Agents, Local Models, Frontier

  It's 2:14 AM in London and one operator is directing a generative video pipeline that would have required a studio a year ago. The leverage isn't in any single tool — it lives in the seams. Here's the menu, the hardware reality, and the seven-step shape of the day you stop reading about this and start operating in it.

  AI Agents
• Chapter 118 min read

  Build a Skill in 30 Minutes

  A skill is a folder. SKILL.md is the only required file. After 20 of them, you stop prompting and start calling functions. Here's the morning-briefing skill, written end to end — description, body, scripts, anti-patterns, the test loop, and the five ways skills fail.

  Claude
• Chapter 1212 min read

  Connectors and MCP

  An AI agent without connectors is a chef with no kitchen — it can describe a meal but can't cook. MCP is the USB-C of AI tools: one port, every device. Here's the full taxonomy, the install path for Cowork and Claude Code, and the 50-line custom server you can write in an evening.

  Claude
• Chapter 136 min read

  Claude Code in 10 Minutes

  Install Claude Code, verify the installation, and run one read-only task in a test repo. Allow about ten minutes with an account and terminal ready; authentication or troubleshooting can take longer. Connectors are an optional next step.

  Claude
• Chapter 148 min read

  Slash Commands and Settings

  The ten-minute version of every Claude Code search history — flags, slash commands, settings keys, env vars, file paths. Bookmark it. You'll come back.

  Claude
• Chapter 1512 min read

  When to Skip Permissions

  There's a flag called --dangerously-skip-permissions. The name is the warning label. People still type it on their main machine, watch their .env get rewritten, and learn the hard way. This chapter is so you don't — and so you know what to do when you do.

  Security
• Chapter 1610 min read

  Hooks and Custom Subagents

  Hooks turn ad-hoc prompting into policy. Subagents turn one model into a team. Together, they're how you stop talking to Claude and start operating it.

  Claude
• Chapter 1712 min read

  25 Operator Tips

  None of this is in the docs because none of it is teachable until you've shipped a few hundred hours through the agent. Twenty-five tips in five buckets — context, cost, permissions, tooling, habits. I learned each the dumb way. You don't have to.

  General
• Chapter 189 min read

  Headless Claude and CI

  The real unlock is claude --print. Same binary as the IDE chat, runs as a deploy step, a GitHub Action, a 3 AM cron job. Going from 'I run claude in my terminal' to 'Claude is part of my infrastructure' is one flag — and one mental shift from driving to scheduling.

  Building Products
• Chapter 199 min read

  Shipping a Product in a Saturday

  One operator ships a real, deployed voice-brief product in a single Saturday — four hours of hands-on work, $80 in tokens, zero salary. The compounding doesn't show up in the spend column. It shows up in the calendar.

  Building Products
• Chapter 208 min read

  tmux, Worktrees, Named Sessions

  Four panes, four agents, one human conducting. The terminal becomes an org chart and you become the CEO. tmux + named sessions + git worktrees is the trick that turns a single laptop into a small team.

  Claude
• Chapter 2110 min read

  Which Mode Right Now?

  Four modes now, one tool, four completely different relationships with the agent. Plan → Interactive → Auto was the stack; /goal added a fourth in May 2026 that removes per-turn approval the way Auto removed per-tool approval. Most operators run Claude Code in the wrong mode for the job and lose either time or money. Pick the mode that matches the cost of a wrong action — not the urgency.

  Claude
• Chapter 228 min read

  Resume, Replay, Fork

  Sessions in Claude Code are a filesystem, not a memory. Resume picks up where you left off. Fork preserves the original timeline and grows a new branch. The session remembers this morning. The vault remembers your career.

  Claude
• Chapter 2310 min read

  A Saturday Build, Hour by Hour

  Eight hours, $72 in tokens, six bugs hit and fixed, one shipped pipeline. Hour-by-hour log of a real Saturday build with the misfires kept in — including the rabbit holes the Don'ts list killed before they started.

  Building Products
• Chapter 2411 min read

  The Tier List

  Three tier lists — AI tools, connectors, and infra — ranked without diplomatic phrasing. The stack changes every six months. The thing that's actually S-tier is the discipline. The tools are leverage. The discipline is the lever.

  Team + Tier
• Chapter 259 min read

  Evals — Smoke, Regression, Golden

  A skill shipped a $0-pipeline canvas to my COO and stayed broken for nine days because no eval was watching. Start with a small artifact check, then gate every delivery on validated inputs and output. An earlier dry run is useful warning, not permission to publish a later unchecked result.

  Building Products
• Chapter 2610 min read

  How Do I Get My Team to Adopt?

  I shipped a Cowork briefing skill to twelve sales reps and by 9:47 AM the rollout had already split into a 4-3-2-2-1 distribution that nobody warns you about. Tools don't adopt themselves and the early adopter is your worst onboarding partner. The team CLAUDE.md, skills as policy, and a 30-day metric that isn't usage.

  Team + Tier
• Chapter 279 min read

  Voice Agents — STT, LLM, TTS

  A LinguaLive prototype answered an investor call on the third ring and went silent for 1.4 seconds before it spoke. The model wasn't slow — the stack was. Voice agents fail politely, and polite failure is what costs you the deal.

  AI Agents
• Chapter 2810 min read

  Six Failures, Six Bills

  $1,847 in eleven hours from a recursion I didn't catch. A skill that wrote to the wrong vault for nine days. A connector that exfiltrated a customer email. None of these showed up on a tier list. All of them changed how I run things.

  Security
• Chapter 2912 min read

  Why Is My Bill So High?

  My Anthropic bill went from $1,108 a week to $4,312 a week with zero workload change. The culprit was a 38-line CLAUDE.md edit that voided prompt caching on 60% of my morning briefings. The fix took 12 minutes. Knowing the fix existed took six months. This chapter is so you don't have to wait six months.

  Building Products
• Chapter 3010 min read

  When to Drop CC for the SDK

  A customer asked if the AI feature in their dashboard could run without me opening Claude Code. The honest answer was no — what they saw was a skill in my session, not a feature in their product. I wrote 34 lines of Python against the Anthropic SDK and shipped that afternoon. It's been serving customers for nine months. This chapter is what's inside those 34 lines.

  Building Products
• Chapter 319 min read

  Six Stages from Idea to Deploy

  I caught myself painting trim before the foundation was poured, on a Saturday, on my own time, on a project I cared about. Six stages — Ideation, Foundation, Creation, Polishing, Security, Deploy — and the order is the whole game. Skip one and the Saturday dies.

  Building Products
• Chapter 329 min read

  Agent Archetypes (Rick Platform)

  I onboarded a Belkins SDR onto a NemoClaw in three days — prior baseline was eleven. Rick is the archetype layer: pre-shaped agents that show up knowing what kind of job they're for. Pick the preset, plug in your accounts, ship. Graduate to a custom subagent later, when the preset starts costing you more than it saves.

  AI Agents
• Chapter 339 min read

  Browser Agents with Playwright

  At 4:11 AM a Playwright script logged into a competitor's pricing page, diffed it against yesterday, and posted to Slack while I slept. Two days later the same agent posted into the wrong channel and a customer saw a screenshot of someone else's pricing. Both halves of that week are the chapter — what browser agents unlock, and the rails you bolt on so they don't bite the company that built them.

  AI Agents
• Chapter 349 min read

  Persona Agents and the Four NEVERs

  At 9:14 AM Tuesday a Slack message went out under my name in my voice — drafted by an agent that read the thread, waited 6 minutes for me to type 'yes,' and posted. Two weeks earlier the same agent didn't wait, posted to a co-founder a quarter answer to a half question, and he called me about it within four minutes. The unlock is voice fidelity. The non-negotiable is the approval gate.

  AI Agents
• Chapter 3510 min read

  Codex or Claude Code — or Both?

  Codex opens a PR at 3 AM against the Belkins Sentry stream. I review and merge it in Claude Code at 9. Same repo, same .mcp.json, same CLAUDE.md — two agents, two contracts, one shift hand-off. The hard part isn't picking a model; it's keeping the night shift and the day shift from stepping on each other.

  AI Agents
• Chapter 369 min read

  When Do I Outgrow Claude Code?

  Five Claude Code subagents kept stepping on each other in a deal-research workflow because they all wrote to the same scratchpad. CrewAI cracked it with explicit handoff contracts. LangGraph cracked the next one with explicit state. The graduation from CC to a framework isn't about power — it's about contracts the orchestrator enforces instead of you.

  AI Agents
• Chapter 3712 min read

  Context Files — CLAUDE.md, memory, skills

  Prompt engineering is the visible part. Context-file architecture is the load-bearing part nobody writes about. CLAUDE.md is the kitchen rules taped to the wall. memory/ is the notebook the agent writes to. Skills are the recipes pulled on demand. Get the layers wrong and the model ignores all of them.

  General / Claude
• Chapter 388 min read

  Run Until Done

  /goal landed in Claude Code v2.1.139 on May 11, 2026, and it changes the unit of human approval from per-step to per-outcome. With /loop and Stop hooks alongside it, the autonomous-loop surface is finally a clean three-way — evaluator-driven, interval-driven, custom-logic-driven. Pick the wrong one and the agent loops forever; pick the right one and your Saturday gets shorter.

  Claude
• Chapter 399 min read

  Skills You Should Steal

  By May 2026 the public skills ecosystem crossed a million entries — and a dev.to audit found 73% of them silently broken. The fix isn't installing more, it's knowing which nine libraries to steal from and which three gap-filling skills no one's written yet. Star count is not a security signal.

  AI Agents
• Chapter 4012 min read

  Prompting, or the Knob You Probably Shouldn't Tune

  Prompting is a basic skill now — necessary, table stakes, not the lever. The leverage moved up the ladder: skills, swarms, memory, and the data layer underneath. Most prompt-engineering content is written for benchmark scores, not for whether the workflow still runs on Tuesday morning. This chapter is what to keep, what to drop, and where the real leverage actually lives — with one of my own published prompts as the worked example of both.

  Claude
• Chapter 419 min read

  Send the Link, Not the File

  Every report, pitch, audit, deck, and model in my portfolio ships as a live interactive HTML link in a private repo, not as a PDF or slide attachment. The cheaper, better, more current artifact also happens to be the one that takes less of your night. This chapter is the thesis; /html-first is the deep reference with the embedded case studies, the recipe, the applications gallery, and the twelve public examples in the wild.

  Building Products
• Chapter 4212 min read

  Codex on a Loop

  Codex isn't a better Claude Code — it's a second prior I run on a loop. Pointed at Sentry + PostHog + BetterStack via MCP and crons, it fixes fresh signals in worktree-isolated PRs, proof-checks the day driver's diffs by running the tests CC didn't think to run, and — one afternoon, in about ten minutes — hatched a desktop pet from a cross-vendor skill. Best execution is always a second opinion plus a proof check, never one agent trusted blind.

  AI Agents
• Chapter 4313 min read

  Codex as Saviour

  Codex pointed at a real product with one constraint — simplify, follow the design system — deleted a net 91,874 lines across 718 files, repositioned the product to one promise, and hardened the risky paths it exposed, all behind real build, CI, browser, and API checks. Simplification and security turn out to be the same phase.

  AI Agents
• Chapter 4412 min read

  Dreaming — Memory That Curates Itself

  Dynamic workflows impressed me by holding a whole task's memory in a two-hundred-line script. That made me ask the harder question: what holds MY memory across hundreds of sessions? Rick's been dreaming on a Mac mini for months — OpenClaw logic, multiple models, dated files. Anthropic shipped Dreaming as an agent that writes its own memory. I built the Claude Code version deliberately weaker: propose-only. It digests sessions outside the model, fans out read-only agents that each cite a verbatim quote, re-verifies every quote against the raw transcript, and writes a review file I skim — it never writes to memory itself. Memory is the moat, and the moat is a lot of work.

  General / Claude
• Chapter 4514 min read

  The App Store Without Swift

  Claude Code one-shot every line of native SwiftUI for LinguaLive — and still could not ship it. The App Store is just another deploy target, but with the strictest gates in the book, and the operator, not the agent, walks through every one: a Mac with Xcode, the $99/yr membership, the signing maze, the account-deletion rule, the App Privacy label, a working demo login for the reviewer. The lesson is not 'you can build iOS with no Swift' — the code is the easy part now. It's that shipping native means owning the platform-and-policy surface the agent is structurally locked out of. The proof isn't a download count — it's one RevenueCat row where an INITIAL_PURCHASE became a RENEWAL: $7.99 that recurred on its own, because a real StoreKit purchase ran on a real phone. Read honestly, that row proves recurring revenue and a stacking renewal — not total scale.

  Building Products
• Chapter 4618 min read

  Designing with AI

  Generation went to zero — anyone can prompt a polished-looking page in seconds, which is exactly why every AI page looks the same. The scarce skill flipped from making an interface to choosing which one is right, and choosing is a judgment a generator can't make for you. This chapter proves it with this book's own receipts: a contrast failure that sat in our own light-theme tokens for weeks until the arithmetic caught what every eye had passed; the swarm-before-v1 discipline; a design system as the ruler that tames model drift; and flicked.email — one product with three live landing pages (chaos, hype, calm) in three different heading typefaces, all AI-built, where only a human can say which intent is true. First-person here is Claude and Claude Code; every other tool is labeled researched. The final section turns the same discipline on AI image generation — art direction as intent for pixels, encoded as a public taste skill, with a moon-base concept set for Reach as the worked example. Taste is the last mile, the system is taste externalized, and the last mile is the whole job now.

  Building Products
• Chapter 4711 min read

  The Measurement Layer

  Chapter 25's three-line eval is a smoke detector for an internal skill's artifact. But when the model's output IS the product — a tutor's reply, a generated cold email — a boolean can't tell you if it's any good; you need a graded test set, and most builders skip it because it feels like research-team work. It isn't. Anthropic's own developer course ships the exact code: a way to SCORE output and a way to RETRIEVE the right context. I ported both to TypeScript in a weekend — a scorer that shows its failures and a hybrid retriever, 29 tests green. Pick measurement, or pick hope.

  Building Products
• Chapter 4813 min read

  The Traffic Graph That Lies

  Most 'agentic SEO' is a self-reported traffic graph that craters in six months — the operator who claimed 24k clicks in three months on a zero-backlink site, and the SEO veterans who called it vanity, were mostly right. So I pointed the swarm at Google across two AI-built products and pulled the real numbers. Folderly EmailGen is a genuine win: a brand-new subdomain hit #1 for 'business email generator,' 467K impressions over the year, third-party traffic value climbing from ~$0 to ~$320/mo. LinguaLive is the cautionary tale: a 153K-impression graph that looks like a win until you see roughly nineteen of every twenty clicks are people already typing the brand name. The honest part is the divergence — Google's own console shows EmailGen 3.3K clicks across ~1,000 queries while Ahrefs sees 21 keywords; so you triangulate, and you don't trust a graph you can't independently check.

  Building Products
• Chapter 4910 min read

  GPT-6 Astra for Real Work

  Trial Astra on difficult work with an inspectable finish line: a scoped patch, a cited decision brief, or a reconciled deliverable. Published benchmarks justify investigation, not a personal recommendation. These synthetic protocols are unrun; compare accepted outputs, total spend, and review time before changing your default model.

  Team + Tier
• Chapter 5010 min read

  Claude Fable 5.1 for Difficult Workflows

  Consider Fable 5.1 for difficult debugging and research-to-document work when a cheaper baseline misses a defined acceptance test. This is a source-backed guide, not a hands-on verdict. Pin the model ID, record the model that actually serves each step, approve enterprise data handling, and count cache writes, partial attempts, fallbacks, and review before deciding whether to switch.

  Team + Tier
• Tool

  AI workflow planner

  Define inputs, approvals, and acceptance tests. Export an operating specification.

  Building Products / AI Agents
• Guide

  Learn the basics

  Free foundational courses and a learning ladder before the playbook.

  Getting started
• Guide

  Day zero

  A first-session path for operators new to working with AI.

  Getting started
• Guide

  Templates and configurations

  Context-file skeletons, MCP configuration examples, and hook scripts.

  Reference / AI Agents
• Guide

  Command cheat sheet

  Commands, paths, and settings to keep beside your terminal.

  Reference
• Guide

  AI operator glossary

  Definitions connected to the chapters where each concept is used.

  Reference / Getting started
• Guide

  Research notes

  Papers translated into operator implications, with links to their sources.

  Research
• Tool

  AI Radar

  A source-linked feed of AI papers, repositories, and ecosystem developments.

  Research
• Guide

  Agent workflow

  Issue specifications, task queues, and review responsibilities for a multi-agent team.

  AI Agents / Building Products
• Guide

  Vault starter

  An Obsidian working-memory structure for reusable context.

  Getting started / Reference
• Guide

  Starter skills

  Reusable task instructions to adapt for your own work.

  AI Agents / Reference
• Tool

  30-day learning plan

  Build a learning schedule around your available time and experience.

  Getting started