The Guides
11 free guides · no email wall to readSell AI to Local Businesses — Without Building Any of It
The exact stack, offer, and 30-day plan to launch your own AI agency this month — reselling voice agents, chat agents & automations under your own brand.
Read the guide →Agent Tokenomics: How to Price an AI Agent for a Client (Without Guessing or Losing Money)
A practical guide to estimating the per-task token cost of an AI agent, then using model-routing — cheap model for the easy calls, frontier model for the hard ones — to cut that cost by half or more. With a worked example you can copy.
Read the guide →The Agentic Security Checklist: Lock Down Your AI Agent Before the Enterprise Demo
An enterprise buyer will ask one question you can't bluff: "What can this agent actually do on a machine?" This is the pre-demo checklist — shell permission tiers, the auto-mode blind spot, and the skill-marketplace supply chain — so you walk in able to answer it.
Read the guide →Claude Fable 5: The 5-Minute Field Guide
What Anthropic's new top-tier model is, when it's worth the money, and how to switch without breaking your code.
Read the guide →The Hermes Agent Field Guide: The Open-Source AI That Writes Its Own Skills
What Hermes Agent is, the two commands that install it, why it gets better the more you use it, and how to run the whole thing from your phone. Facts checked against the live Nous Research docs.
Read the guide →The Jevons Paradox for AI: Why "It's Too Late" Is Exactly Backwards
As AI gets cheaper and better, total demand for it goes UP, not down. Here's the 200-year-old economic law behind that, why Andrej Karpathy says his own demand for software is now growing, and how to read it so you act instead of freeze.
Read the guide →Karpathy's Method: How to Build 10x Faster with Claude (Spec → Verifier → Environment)
Andrej Karpathy stopped 'prompting' a while ago. Here's the practical three-layer way to apply how he actually works — with the exact prompts to drop into Claude — so you stop babysitting output and start shipping.
Read the guide →Nested Subagents: Claude Code's Depth-5 Upgrade (and 5 Patterns That Actually Use It)
Your AI agent now spawns its own agents — up to five layers deep. Here's what that really means for your context window, the five workflows it unlocks, and how to switch it on in Claude Code and Codex.
Read the guide →OpenClaw vs Hermes vs Claude Code: Which Agent Actually Runs Your AI Business
An honest, source-checked comparison of three open/agentic stacks on the five things that matter when an agent has to RUN, not just demo: self-generating skills, memory and identity, where it runs, openness, and lock-in risk.
Read the guide →The Ultracode Field Guide: When 1,000 Agents Beat One Genius
One page to decide if ultracode is worth the token bill, when plain /effort high beats it, and the 3 settings that stop the spend from surprising you.
Read the guide →The Provider-Agnostic AI Stack: Surviving the 2026 Lock-Down (Gemini CLI Dies June 18)
Two of the three big AI labs just restricted open/flat-rate access in a single quarter. Here's exactly what's changing, what breaks on June 18, and how to build a stack no single vendor can hold hostage.
Read the guide →