A field manual

VLAD'S
PLAYBOOK

The Ultimate AI Dive Deep

For operators who want to stop juggling tabs and start running AI like an OS. 47 chapters. One operator. Belkins, Folderly, the Newsletter, and a portfolio of others.

by Vlad Podoliako · Edition 10.7 · June 2026

3-10B tokens / mo · 5 companies · 47 chapters · 25 widgets · $0 to read · no email gate
Before
Ten tabs. Twenty minutes. No decisions yet.
gmail.comhubspot.comapp.slack.comnotion.socalendar.google.comsentry.iodashboard.stripe.comapp.ahrefs.comchat.openai.comlinear.app
After
One channel. One coffee. The week is closed.
#ops · 6:30 AM
1.HubSpot — 2 deals advanced overnight, 1 went dark
2.Folderly — deliverability holding 96%, no incidents
3.Mentee A — prep doc generated, three open threads
4.One investor on calendar at 2 PM, conflict resolved
The why
It has always given me satisfaction to be able to create what I have in mind.
— Vlad Podoliako

Forty-Six Chapters

Read straight or jump where you need it. Each chapter stands alone.

  1. 01 AI as an Operating System

    The Day I Killed My Tabs

  2. 02 The Five-Tool Stack

    Five Tools, Not Fifty

  3. 03 Why Claude Forgets You

    AI Is a Temp Agency, Not a Genius

  4. 04 Obsidian as Working Memory

    The Vault — Where AI Becomes Useful

  5. 05 What a Skill Is

    Recipes the Chef Reads Before Cooking

  6. 06 Parallel Subagents and Fan-Out

    The Swarm

  7. 07 Scheduled Tasks

    Make AI Work While You Sleep

  8. 08 Chat, Cowork, or Claude Code?

    Three Doors to Claude

  9. 09 Blast Radius and Key Hygiene

    Don't Get Owned

  10. 10 Hosted Agents, Local Models, Frontier

    The Wild Stuff

  11. 11 Build a Skill in 30 Minutes

    How to Build a Skill, End to End

  12. 12 Connectors and MCP

    Types, install paths, custom servers

  13. 13 Claude Code in 10 Minutes

    The 10-Minute Quickstart

  14. 14 Slash Commands and Settings

    The Cheat Sheet

  15. 15 When to Skip Permissions

    Permissions, Sandboxes, and Sharp Edges

  16. 16 Hooks and Custom Subagents

    From Autocomplete to Coworker

  17. 17 25 Operator Tips

    Hard-Won Wisdom from Hour 200

  18. 18 Headless Claude and CI

    claude --print in Production

  19. 19 Shipping a Product in a Saturday

    How to Build Products with AI

  20. 20 tmux, Worktrees, Named Sessions

    Running Six Claudes at Once

  21. 21 Which Mode Right Now?

    Interactive, Plan, Auto

  22. 22 Resume, Replay, Fork

    Session Management

  23. 23 A Saturday Build, Hour by Hour

    Vibe Coding, with the Misfires Kept In

  24. 24 The Tier List

    Every Tool Ranked Without Mercy

  25. 25 Evals — Smoke, Regression, Golden

    Evals or Hope, Pick One

  26. 26 How Do I Get My Team to Adopt?

    Getting Twelve People to Use This

  27. 27 Voice Agents — STT, LLM, TTS

    Phone Number to Production

  28. 28 Six Failures, Six Bills

    The Receipts I'd Rather Not Show You

  29. 29 Why Is My Bill So High?

    Token Math, Caching, Batch, Routing

  30. 30 When to Drop CC for the SDK

    Building with the Anthropic SDK Directly

  31. 31 Six Stages from Idea to Deploy

    Ideation, Foundation, Creation, Polishing, Security, Deploy

  32. 32 Agent Archetypes (Rick Platform)

    OpenClaw, NemoClaw, Hermes

  33. 33 Browser Agents with Playwright

    Login, Click, Scrape, Post

  34. 34 Persona Agents and the Four NEVERs

    Writing on Your Behalf Without Becoming a Bot

  35. 35 Codex or Claude Code — or Both?

    Day Shift, Night Shift

  36. 36 When Do I Outgrow Claude Code?

    Beyond CC — CrewAI, LangGraph, SDK

  37. 37 Context Files — CLAUDE.md, memory, skills

    Where Conventions Live, Where They Die

  38. 38 Run Until Done

    Goals, Loops, and the Evaluator That Tells the Agent to Stop

  39. 39 Skills You Should Steal

    A tour of the 1M-skill ecosystem, the 73% that's broken, and the gaps an operator can fill

  40. 40 Prompting, or the Knob You Probably Shouldn't Tune

    Why most prompt engineering content is wrong for operators

  41. 41 Send the Link, Not the File

    Every Deliverable as a Live Artifact

  42. 42 Codex on a Loop

    The Second Opinion, Proof-Checked While You Sleep

  43. 43 Codex as Saviour

    When a Second Prior Deletes 90,000 Lines and Hardens What's Left

  44. 44 Dreaming — Memory That Curates Itself

    The Surfacer That Proposes, Never Writes

  45. 45 The App Store Without Swift

    A Native iOS App, Real Recurring Revenue, and Not One Line of Swift I Wrote

  46. 46 Designing with AI

    A Model Can Generate Any Interface in Seconds. It Still Can't Tell You Which One Is Right.

  47. 47 The Measurement Layer

    When the AI Output Is the Product, a Three-Line Eval Isn't Enough

Now · Edition 10.7 · June 2026
Vlad's Playbook is public. 47 chapters, 3 live embedded case studies, the source is open and is the recipe.
Read the launch
New · Live · Updated hourly

Radar — what's moving in AI, ranked by lead time

A self-updating index of what's travelling through the AI ecosystem, ranked by where it sits on the gradient — papers to repos to community to analysis. The receipts are on every row. See it before the crowd does.

New here? Start here

Learn the basics first

New to AI, Claude, Claude Code, or Cowork? The official free courses in the right order, a five-word primer, and the learning ladder — then the book.

New · Model file

Fable 5 — the withheld model, buyable

Anthropic shipped the model it said it wouldn't — split in two. Pricing, the full benchmark table read honestly, the fallback architecture, and the June 22 clock.

Dynamic Workflows

Opus 4.8 — the swarm that runs itself

Claude writes a script that plans, fans out hundreds of parallel subagents, and verifies its own work. What it is, the validator loop, how to turn it on, and when not to.

New · Showcase

Good taste, on tap

Stop your AI from generating generic slop. A before/after of Leon Lin's public taste-skill (45k★, credited) — and the moon-base and three-design receipts I built with the discipline.

Memory

Dreaming — the loop pointed inward

A local, propose-only twin of Anthropic's Dreaming: it digests your sessions, surfaces candidate memories that each cite a verbatim quote, and re-verifies every one against the raw transcript — and never writes to memory itself.

New · Method

The Self-Audit

The swarm pointed at the agent's own setup. Five auditors, an adversarial red-team, 41 findings — including two refutations that would have broken the system if executed. Your config rots faster than your code.

New · Reference

What Claude Code actually costs

Every plan and API rate, verified — then the receipts: the real monthly bill, the $1,108→$4,312 cache mistake, and the three levers that cut it.

New · Comparison

Claude Code vs Codex

Ran both in anger. Verdict per job — including the night shift Codex actually wins.

New · Reference

Hooks that can't be talked out of

Ten real configs with verdicts — what each caught in production, and the three hook ideas that failed expensively.

New · Setup

Claude Code + MCP

The setup guide grounded in a real roster: the servers worth wiring, what each one costs and earns, and the ones that got cut.

New · Examples

12 agents that actually ran

A receipts gallery: the book swarm, the 4 AM watcher, the $0.40/min voice agent — every example with a cost and a failure on record.

Sovereign Stack

Don't get deprecated

Open-weights LLMs that survive the deprecation calendar — Ollama, the hardware ladder, the heretic question, and the nano-gpt Saturday.

Method

HTML-ization

Stop sending dead files. Every report, pitch, and audit ships as a live interactive artifact — two real ones embedded and clickable.

The launch

Edition 10.7 is public

Typewriter hero, animated stat odometer, three live embedded artifacts, all 47 chapters as a click-anywhere mosaic, a post-credit scene.

Live diary

Launch week

The launch as its own experiment in the thesis. Four surfaces, seven days, receipts accruing — honest, even the embarrassing ones.

Resources

Vault library

CLAUDE.md skeletons, .mcp.json examples, hook scripts, SKILL templates, the five reusable prompts. Copy, paste, ship.

Reference

Cheat sheet

Slash commands, settings, env vars, file paths, keyboard shortcuts. Print it. Tape it next to your monitor.

Vocabulary

Glossary

Fifty-plus terms you'll need, grouped A–Z. Linked inline throughout the book. Hover any underlined term to read it.

Tier list

Rank without mercy

Drag-and-drop your own tier list across AI tools, connectors, and infra. The live LMArena leaderboard for reference.

Orchestration

Swarms

Multi-agent orchestration — the four-pattern visualizer, ten swarm skills shipped, seven patterns I use, the orchestration prompts to steal. Three real multi-session screenshots.

GitHub

GitHub for non-developers

Five non-code uses, eight gh commands you actually need, what you can safely ignore. Six worked examples — Vlad's Playbook, AFC, Karpathy, Simon Willison ×2, profile READMEs.

The stack

66 skills · 32 agents · 12 plugins

Vlad's full Claude Code setup. Every skill folder, every custom subagent, every plugin — sanitized and shareable. Freshly pruned by the Self-Audit.

Research

What shifted this week

External findings that move what an operator does Monday — model releases, deprecations, benchmark shifts. Dated, sourced, signal-not-receipt discipline.

Stay close

The next edition lands when this list says it does.

No course. No paywall. Operator playbooks weekly. 10K+ subscribers.