Start Here

AI Basics 101

A beginner's guide to working with AI tools effectively. Read time: ~10 minutes.

The Memory Myth

What you might think: "AI remembers our conversations and learns about me over time."

What's actually happening: Every time you start a new chat, you're talking to someone who has never met you. LLMs (Large Language Models) like Claude, GPT, and Gemini don't have persistent memory. They read your message, generate a response, and forget everything.

Why this matters: If you spent 2 hours explaining your project yesterday, today's AI has no idea. You're starting from zero.

Files Are Your Playbook

Here's the trick: AI can't remember, but your playbook can.

When you write context into a file:

  • AI reads it at the start of each session
  • It knows what you're building, what you've decided, where you left off
  • Re-explaining is gone, there's now a natural continuation

The playbook concept. Your markdown files aren't a one-time handoff. They're a living strategy document. Write your decisions once, and every future session reads them. Write your constraints once, and AI never violates them. The playbook grows with your project.

Without FilesWith Files
"So what are we building?""I see we're building X. Last session you completed Y. Ready to tackle Z?"
You re-explain every sessionYou pick up where you left off
AI makes wrong assumptionsAI follows your documented decisions

The Hallucination Problem

What you might think: "AI sometimes makes things up, but I can catch it."

What's actually happening: LLMs generate text probabilistically. Without ground truth, they'll confidently invent facts, make assumptions, or misremember earlier context.

Common Hallucinations

TypeExampleWhy It Happens
False memory"As we discussed last week..." (you never discussed it)No actual memory, fills gaps with plausible text
Invented facts"Your API uses OAuth 2.1" (you never mentioned auth)Guesses common patterns
Assumed contextChanges code you didn't ask to changeAssumes "improvements" are wanted
Phantom features"The login system already has password reset" (it doesn't)Confabulates from similar projects

Files as Ground Truth

The solution: Files are the single source of truth that prevents hallucinations.

Without FilesWith Files
AI guesses your tech stackCLAUDE.md: "Tech: Next.js 14, Supabase, Tailwind"
AI assumes features existPRFAQ.md: "What we're building, what's done, what's not"
AI invents past decisionsDECISIONS.md: "DEC-001: Why we chose X over Y"
AI contradicts itselfCONSTRAINTS.md: "Never use library X (reason)"

Building Your Ground Truth System

Start Small

You don't need 50KB of documentation. Start with three essentials:

The 4 Habits: These three files map to the protocol's core habits. Plan in markdown (TODO.md), protect decisions (CONSTRAINTS.md), and align AI with your goals (CLAUDE.md). The fourth habit, measure compound, comes from PROGRESS.md when you're ready to grow.

1. CLAUDE.md / Technical Facts Habit 3: Alignment

## Tech Stack
- [Exact versions and tools]

## Architecture
- [How things connect]

## Current State
- [What exists, what doesn't]

2. TODO.md / What's Next Habit 1: Markdown Planning

## Active
- [ ] Feature X
  - AC: Specific, testable criteria

3. CONSTRAINTS.md / Never Do This Habit 2: Protect Decisions

## Rejected Approaches
- Don't use library X (reason: Y)
- Don't implement feature Z (decided: DEC-015)

Pro tip: Number your sessions in PROGRESS.md. Session #1, set up protocol files. Session #2, first feature with context. Session #3, AI referenced a decision from Session 1 without being asked. That last one is the compound moment. When you can see the numbers growing, compounding feels real.

Grow Incrementally

Each time AI hallucinates:

  1. Catch it
  2. Document the truth in the relevant file
  3. Next session reads the correction
  4. Same mistake won't repeat

Token Economics

What Are Tokens?

Tokens are how AI measures text. Roughly:

  • 1 token ≈ 4 characters (English)
  • 1 token ≈ 3/4 of a word
  • This sentence is about 10 tokens

Every interaction costs tokens:

  • Input tokens: What you send (your message + context files)
  • Output tokens: What AI generates back

Context Budget

Think of AI like a person with a whiteboard. The whiteboard has limited space.

Everything must fit on the whiteboard:

  • Your current message
  • The files AI is reading (CLAUDE.md, TODO.md, etc.)
  • The conversation so far
  • Room for AI's response

If you fill the whiteboard with context, there's less room for AI to think and respond well.

The protocol's solution: Different roles load different amounts of context. Architect scope loads full context (~15%) for planning. Builder scope loads lean context (~5%) for focused implementation.

The Atomic Interaction Model

Every productive AI interaction follows the same five phases, whether you're delegating a task, building software together, or automating a workflow.

PROTOCOLLOADCLARIFYEXECUTERECORDREFLECT

Each cycle's RECORD makes the next cycle's LOAD richer.

LOADAI reads your context files. Picks up where you left off.
CLARIFYAI asks what's ambiguous before acting
EXECUTEAI does the work. Writes code, drafts content, runs tasks.
RECORDAI writes what happened. Decisions, progress, what changed.
REFLECTAI flags what to improve so the next session starts smarter

Which Protocol Is For You?

Ask yourself: "What's AI's role in my work?"

AI works FOR you → uno (Operate)

You define WHAT needs doing. AI handles HOW.

Examples: Trip planning, documentation, research, tracking projects

AI works WITH you → duo (Construct)

You and AI build together. AI designs, you approve. AI implements, you guide.

Examples: Software projects, product builds, anything with code

AI works AMONG systems → tre (Automate)

AI operates between your tools, with quality gates and human approval points.

Examples: Ticket triage, deployment checks, automated workflows (coming soon)

Glossary

TermMeaning
LLMLarge Language Model. The AI that powers tools like Claude, GPT, Gemini.
ContextEverything AI can "see". Your message, files, conversation history.
TokenUnit of text (~4 characters). Bigger context = more tokens = more cost
HandoffStructured transfer of context, like a shift change briefing
SessionOne atomic cycle of work with AI
ACAcceptance Criteria. How you know a task is actually done.

Your First Session Matters

Before you start, know what you're bringing to it:

The name of your project
One decision you've already made (tech stack, architecture, anything)
The first task you want to tackle

That's your CLAUDE.md, your DECISIONS.md, and your TODO.md. You're not setting up files. You're introducing yourself to your new collaborator.

Ready for the Next Step?

Now that you understand the basics, pick the protocol that fits your work.