A presentation for humans who ship

AI for
dummies.

You do not need an army of models. You need a system: one mind to frame the work, several hands to execute it, and a clean boundary between every task.

01strong model
for ambiguity

03bounded workers
in parallel

∞iterations
with evidence

Read this as a route map, not a prompt recipe.

RULE ZEROStrong model for ambiguity.
Light model for bounded work.

A small fleetcoordination before parallelism

needs to happen.', pt: 'Decide o que
precisa acontecer.', }, code: 'Opus / reasoning', }} workers={workerCards} />

{workers.ui.en[0]}{workers.ui.en[1]}{workers.ui.en[2]}

The orchestrator preserves intent, writes small contracts, and gathers results that can be verified. It does not need to type every line.

Why the boundary mattersone vague task / three predictable failures

01Context soup

Every worker reads everything. Nobody knows which facts are load-bearing.

02Branch collision

Two agents touch the same checkout. The fastest path becomes conflict resolution.

03Confident drift

The diff is polished, but no one checks whether it solved the original problem.

The subagent loop

Click a phase.
See the handoff.

Delegation means moving one bounded task into a smaller context—not giving away responsibility.

What crosses contextsbrief → diff → evidence

Git worktrees

One branch
per hand.

A worktree is another directory linked to the same repository. Each agent gets its own checkout and index; history remains shared.

Select a node to inspect its checkout, owner, and next action.

{labels.owner.en}{trees.main.owner.en}

CHECKOUT{trees.main.path}

{trees.main.note.en}

{trees.main.command}

Model routing

Do not pay for
reasoning where
you need rhythm.

Choose a job to see why the model profile changes.

{labels.reasoningLoad.en} · {routes.plan.score}{routes.plan.label.en}

{routes.plan.why.en}

Model gearboxcapability tier × thinking effort

Two separate knobs

Choose the engine.
Then choose the gear.

A stronger model changes the capability ceiling. Higher reasoning effort gives that model more room to work. Start with the lightest combination that passes your real checks, then move one knob at a time.

{providers.openai.label}{labels.officialSource.en}

{providers.openai.title.en}

{providers.openai.copy.en}

REASONING / THINKING

{efforts.medium.en[0]}

{efforts.medium.en[1]}

{providers.openai.config}

ROUTING RULE Use strong models for ambiguity and judgment. Use lighter models for bounded execution. Raise effort only when evaluation shows a gain.

{ /* Under Portuguese the legacy page paints the long skill sentence here, not "Skills": its `.skills > div:first-child > p` selector also matches this eyebrow and overwrites it. Reproduced on purpose -- see .agents/rules/content-i18n.md. */ } Skills

Write the right way
once.

A skill is a reusable procedure. It can carry instructions, references, scripts, and assets. It is not magical memory, and it does not replace acceptance criteria.

01 / trigger clearly 02 / load detail on demand 03 / return evidence

{skillFiles.skill.icon}

{skillFiles.skill.title}

{skillFiles.skill.en}

{labels.skillFileHint.en}

name: review-ui · check focus, mobile, reduced motion · run verification · return evidence

Create a skillrepeatable pain → reusable judgment

The skill forge

Teach the decision.
Keep the context light.

Do not package everything you know. Capture the non-obvious choices that repeatedly improve an outcome, then prove the skill changes behavior.

{ ['observe', 'trigger', 'scaffold', 'write', 'validate'].map((id) => { const step = skillWorkflow[id]; return ( ); }) }

{skillWorkflow.observe.number}{labels.workflow.question.en}

{skillWorkflow.observe.title.en}

{skillWorkflow.observe.question.en}

{labels.workflow.action.en}

{skillWorkflow.observe.action.en}

OUTPUT / SKILL PACKAGE

review-ui/
├── SKILL.md
├── agents/
│   └── openai.yaml
├── references/
│   └── accessibility.md
└── scripts/
    └── verify.mjs

VALIDATEquick_validate.py ./review-ui

AFTER REAL USE

observe failure→sharpen one rule→retest behavior→keep it narrow

Common skillschoose behavior before model

The field kit

Different jobs.
Different instincts.

A skill changes how an agent approaches work. Some shape communication. Others enforce research, debugging, review, or completion discipline. Select one to inspect its operating rule and verified source.

{ /* getCollection's order is not the deck's order. Sort by the card number so the tabs stay 01..07 as the legacy page has them, instead of shifting between builds. */ sortedCommonSkills.map((skill) => ( )) }

{commonSkills.ponytail.number}{commonSkills.ponytail.kind.en}

{commonSkills.ponytail.title}

{commonSkills.ponytail.rule.en}

{labels.commonSkill.whenToUse.en}

{commonSkills.ponytail.use.en}

{labels.commonSkill.example.en}

{commonSkills.ponytail.example.en}

{labels.commonSkill.watchOut.en}

{commonSkills.ponytail.caution.en}

{labels.commonSkill.source.en}

ONE PRACTICAL LOADOUT

PLAN unlazy → BUILD ponytail-lite → DEBUG diagnosing-bugs → REPORT caveman

INSTALL PACKAsk your coding agent to verify, install, and validate the skills.

{install.en}{install.pt}

Hands-on10 minutes / one missing feature

Tiny Tasks lab

Same task.
Better operating system.

Start with a deliberately incomplete static task board. Run one prompt as written, reset, then run the skill-enabled version. Compare diff size, verification evidence, and unnecessary complexity.

Open the starter →Clone from Gitea →

Open the rules lab →Clone from Gitea →

THE MISSING FEATUREAdd All / Open / Done filters that survive reload and browser navigation.

STACK HTML · CSS · JavaScript DEPENDENCIES none FILES 3

RUN AGood prompt

{handsOn.en.basic}{handsOn.pt.basic}

RUN BGood prompt + skills

{handsOn.en.skills}{handsOn.pt.skills}

COMPARE THE RUNS

01 Files changed

02 New dependencies

03 Checks actually run

04 Evidence returned

Verificationrun each gate separately

Checks become evidence

Three layers.
Run each one alone.

Run a gate on its own line, print its exit code, attach the output. The result is the deliverable.

01 · STATIC

Lint and types

Format, lint, type-check. Fast and scoped to one file. Run on every save.

pnpm lint; echo "lint=$?" pnpm typecheck; echo "typecheck=$?"

02 · BEHAVIOR

Unit and contract

Tests that repeat. Run before claiming done.

pnpm test; echo "test=$?" cd services/api && go test ./...

03 · INTEGRATION

Real UI and API

Drive the actual UI, API, or browser. Slower and flakier — only this catches mobile overflow and a missing 404.

pnpm check:ui; echo "ui=$?" TURBO_FORCE=true pnpm e2e

FOUR WAYS A GREEN REPORT IS FALSE

Pipe a gate

tail, grep, or head hide the real exit code — a pipeline returns the last command's status.

Swallow a rejection

A silent {'.catch(() => {})'} hides a panic, an upstream limit, or a partial failure.

Trust the cache

Turbo caches results. A gate that "passes" may not have run — use TURBO_FORCE=true.

Skip the third layer

Lint and unit can both be green while the page breaks on mobile and the API never returns 404.

RUN IT YOURSELF · two labs, under 10 minutes each

Path A · verification lab

Fill the four-row comparison strip on the starter. Run A naively, Run B with $gate-discipline and $webapp-testing.

Open the starter →Clone ↗ git.marcospaulo.dev.br/.../src/branch/pages/hands-on/starter Path B · rules lab

Toggle every rule off, run the prompt. Toggle every rule on, run it again. Compare diff size, gate invocations, and the names of checks the agent names back.

Open the rules lab →Clone ↗ git.marcospaulo.dev.br/.../src/branch/pages/hands-on/rules

Keep learning12 new readings + primary docs

Go deeper with official documentation, production case studies, Medium, and practitioner workflows. Rules and enforcement case study → Skills review desk → Primary references → 12-part reading path →

Navigate by ideashort chapters / one system

Prefer a focused chapter? Start with the route map, then jump directly to models, agents and worktrees, skill creation, rules, or the skills review desk.

AI fordummies.

AI fordummies.

Click a phase.See the handoff.Clique em uma fase.Veja a passagem.

One branchper hand.Uma branchpor mão.

Do not pay forreasoning whereyou need rhythm.Não pague porraciocínio onde precisade ritmo.

Choose the engine.Then choose the gear.Escolha o motor.Depois escolha a marcha.

{providers.openai.title.en}

Write the right wayonce.Escreva do jeito certouma vez.

Teach the decision.Keep the context light.Ensine a decisão.Mantenha o contexto leve.

{skillWorkflow.observe.title.en}

Different jobs.Different instincts.Trabalhos diferentes.Instintos diferentes.

{commonSkills.ponytail.title}

Same task.Better operating system.Mesma tarefa.Melhor sistema operacional.

Three layers.Run each one alone.

Lint and types

Unit and contract

Real UI and API

AI for
dummies.

AI for
dummies.

Click a phase.
See the handoff.

One branch
per hand.

Do not pay for
reasoning where
you need rhythm.

Choose the engine.
Then choose the gear.

Write the right way
once.

Teach the decision.
Keep the context light.

Different jobs.
Different instincts.

Same task.
Better operating system.

Three layers.
Run each one alone.