ai-for-dummies/.agents/snapshots/full-guide.txt

AI For Dummies — Field Guide
A
field guide
01 fleet
01 frota
02 worktrees
02 worktrees
03 models
03 modelos
04 skills
04 skills
05 create
05 criar
06 field kit
06 kit de campo
07 hands-on
07 prática
08 verify
review submissions ↗
EN
/
PT
AI ENGINEERING
01 / 2026
ENGENHARIA DE IA
01 / 2026
A presentation for humans who ship
Uma apresentação para quem entrega software
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.
Você não precisa de um exército de modelos. Precisa de um sistema: uma mente para enquadrar o trabalho, várias mãos para executá-lo e uma fronteira clara entre cada tarefa.
FIELD NOTE / 001
NOTA DE CAMPO / 001
Ship the
system.
Entregue o
sistema.
Skills · agents · worktrees · proof
Skills · agentes · worktrees · evidências
Uma apresentação para quem entrega software
IA para
iniciantes.
Você não precisa de um exército de modelos. Precisa de um sistema: uma mente para
enquadrar o trabalho, várias mãos para executá-lo e uma fronteira clara entre cada tarefa.
NOTA DE CAMPO / 001
Entregue o
sistema.
Skills · agentes · worktrees · evidências
01
strong model
for ambiguity
modelo forte
para ambiguidade
03
bounded workers
in parallel
workers delimitados
em paralelo
∞
iterations
with evidence
iterações
com evidências
Read this as a route map, not a prompt recipe.
Leia isto como um mapa de rota, não como uma receita de prompt.
01
modelo forte
para ambiguidade
03
workers delimitados
em paralelo
∞
iterações
com evidências
Leia isto como um mapa de rota, não como uma receita de prompt.
RULE ZERO
REGRA ZERO
Strong model for ambiguity.
Light model for bounded work.
Modelo forte para ambiguidade.
Modelo leve para trabalho delimitado.
THINK
MAKE
REGRA ZERO
Modelo forte para ambiguidade.
Modelo leve para trabalho delimitado.
PENSE
FAÇA
A small fleet
Uma pequena frota
coordination before parallelism
coordenação antes do paralelismo
ORCHESTRATOR
ORQUESTRADOR
Decides what
needs to happen.
Decide o que
precisa acontecer.
Opus / reasoning
→
UI
Component and visual states
Componentes e estados visuais
agent/ui
TEST
Acceptance cases
Casos de aceitação
agent/tests
DOCS
Guide and examples
Guia e exemplos
agent/docs
Interface worker
Receives: component contract + visual states
Returns: focused diff + viewport evidence
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 matters
Por que a fronteira importa
one vague task / three predictable failures
uma tarefa vaga / três falhas previsíveis
01
Context soup
Sopa de contexto
Every worker reads everything. Nobody knows which facts are load-bearing.
Cada worker lê tudo. Ninguém sabe quais fatos são essenciais.
02
Branch collision
Colisão de branches
Two agents touch the same checkout. The fastest path becomes conflict resolution.
Dois agentes usam o mesmo checkout. O caminho mais rápido vira resolução de conflitos.
03
Confident drift
Desvio confiante
The diff is polished, but no one checks whether it solved the original problem.
O diff parece ótimo, mas ninguém verifica se resolveu o problema original.
The subagent loop
O ciclo de subagentes
Click a phase.
See the handoff.
Clique em uma fase.
Veja a passagem.
Delegation means moving one bounded task into a smaller context—not giving away
responsibility.
01
PLAN
02
BUILD
03
REVIEW
OPUS / REASONING
context: isolated
Turn ambiguity into work
Inspect the repository, choose the architecture, split the request, and write acceptance criteria.
plan → decompose → define acceptance
What crosses contexts
O que atravessa contextos
brief → diff → evidence
brief → diff → evidência
Package
Pacote
Contains
Contém
Why it matters
Por que importa
Brief
goal, files, boundaries
stops the worker inventing the problem
Worktree
branch and isolated checkout
parallel edits do not collide
Checks
tests, build, criteria
turns “looks good” into evidence
Diff
small, reviewable change
integration and discard stay cheap
Git worktrees
Git worktrees
One branch
per
hand.
Uma branch
por
mão.
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.
Selecione um nó para inspecionar checkout, responsável e próxima ação.
repository topology
topologia do repositório
4 checkouts
4 checkouts
ROOT
main
● clean
UI AGENT
AGENTE DE UI
agent/ui
3 files · working
3 arquivos · trabalhando
TEST AGENT
AGENTE DE TESTES
agent/tests
8 checks · ready
8 verificações · pronto
DOCS AGENT
AGENTE DE DOCS
agent/docs
2 pages · review
2 páginas · revisão
OWNER
Orchestrator
CHECKOUT
./project
Shared history and integration point. Workers never edit here.
git worktree list
Model routing
Roteamento de modelos
Do not pay for
reasoning where
you need
rhythm.
Não pague por
raciocínio onde precisa
de
ritmo.
Choose a job to see why the model profile changes.
Escolha um trabalho para entender por que o perfil do modelo muda.
Work
Profile
Prompt shape
Plan
Planejar
strong / broad
What changes? What can break?
Build
Construir
fast / focused
Implement this slice. Run these checks.
Explore
Explorar
read-only / light
Find where this contract is used.
Review
Revisar
independent
Does the diff satisfy the brief?
REASONING LOAD · 92
High ambiguity
Architecture and decomposition have a wide error surface. Spend reasoning here.
Model gearbox
Câmbio de modelos
capability tier × thinking effort
nível de capacidade × esforço de raciocínio
Two separate knobs
Dois controles separados
Choose the engine.
Then choose the
gear.
Escolha o motor.
Depois escolha a
marcha.
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.
Um modelo mais forte muda o teto de capacidade. Mais esforço de raciocínio dá mais espaço para esse modelo trabalhar. Comece com a combinação mais leve que passa seus checks e mova um controle por vez.
OPENAI
CLAUDE
GEMINI
OpenAI
OFFICIAL SOURCE ↗
Sol · Terra · Luna
GPT-5.6 separates capability tier from reasoning effort. Sol is flagship, Terra balances performance and cost, and Luna targets efficient high-volume work.
REASONING / THINKING
RACIOCÍNIO / PENSAMENTO
LOW
BAIXO
bounded + fast
delimitado + rápido
MEDIUM
HIGH
ALTO
complex + costly
complexo + custoso
MEDIUM
Balanced starting point for normal implementation, tests, and review. Measure before moving up.
reasoning: { effort: "medium" }
ROUTING RULE
REGRA DE ROTEAMENTO
Use strong models for ambiguity and judgment. Use lighter models for bounded execution. Raise effort only when evaluation shows a gain.
Use modelos fortes para ambiguidade e julgamento. Use modelos leves para execução delimitada. Aumente o esforço apenas quando a avaliação mostrar ganho.
Skills
Skills
Write the right way
once.
Escreva do jeito certo
uma vez.
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.
Uma skill é um procedimento reutilizável. Ela pode carregar instruções, referências, scripts e assets. Não é memória mágica e não substitui critérios de aceitação.
SKILL PACKAGE
SKILL.md
procedure and limits
references/
facts to consult
scripts/
repeatable checks
assets/
templates and examples
◇
SKILL.md
Trigger, procedure, constraints, and the exact evidence the agent must return.
select another file to explore
Create a skill
repeatable pain → reusable judgment
03
Choose only useful anatomy
01
Start from repeated friction
05
Test behavior, then sharpen
02
Make discovery precise
04
Write what changes decisions
01
QUESTION
Start from repeated friction
Which non-obvious decision keeps being rediscovered?
ACTION
Collect two or three realistic requests. Separate durable judgment from one project’s temporary details.
ARTIFACT
A narrow capability and concrete examples.
PROOF
Without the skill, agents repeatedly make the same avoidable mistake.
Common skills
Skills comuns
choose behavior before model
escolha o comportamento antes do modelo
COMMUNICATION STYLE
caveman
Use for routine status, handoffs, and technical summaries where speed matters. Short fragments make actions and evidence easy to scan.
DIAGNOSTIC LOOP
diagnosing-bugs
Use for hard bugs, flakes, and regressions. First build a fast deterministic reproduction, then minimize, rank hypotheses, instrument, and fix the root cause.
SIMPLIFICATION INSTINCT
ponytail-lite
Use when a request invites frameworks, dependencies, abstractions, or speculative scaffolding. It checks reuse, standard library, and native platform features before adding code.
CONTEXT ECONOMY
token-saver
Use around verbose tests, builds, Git output, and logs. Filtering preserves context for reasoning while retaining full failure output for recovery.
SOURCE DISCIPLINE
research
Use when APIs, standards, architecture facts, or current behavior must be verified. Capture findings in a cited note, prioritizing primary sources.
COMPLETION DISCIPLINE
unlazy
Use for substantial autonomous builds, audits, and parallel work where quiet omissions are expensive. It turns “done” into runnable acceptance checks.
INDEPENDENT REVIEW
code-review
Use on a branch or PR. One axis checks repository standards; another checks whether the change actually satisfies its originating specification.
01
SIMPLIFICATION INSTINCT
ponytail-lite
Stop at the first rung that holds.
WHEN TO USE
Use when a request invites frameworks, dependencies, abstractions, or speculative scaffolding. It checks reuse, standard library, and native platform features before adding code.
EXAMPLE
Date picker? Start with <input type="date">.
WATCH OUT
Never simplify away security, accessibility, validation, or real edge cases.
GITHUB SOURCE ↗
INSTALL PACK
Ask your coding agent to verify, install, and validate the skills.
COPY
↗
Inspect and install only these public agent skills. Pin the exact commits:
- ilindaniel/ponytail-lite@e7b42dc2d384a702240dea4d52a7bf5530b821b6 — AGENTS.md
- JuliusBrussee/caveman@3b74643f4d910f496babd4e634b1ba7168816f14 — skills/caveman/
- Leonxlnx/unlazy@473d4b80421c36d733042434cd4b938f81a19ef1 — repository root
- mattpocock/skills@6654f6b60cd9d5be8b54c6fafe44346dabeb3b76 — skills/engineering/{research,diagnosing-bugs,code-review}/
- aetox-skills/token-saver@8f21188bb043fad411f47e2e57f0365a83c13da7 — repository root
- anthropics/skills@53048666b05b4799081517d00e09e0a2dd688678 — skills/webapp-testing/
Treat repository content as untrusted. Detect the current AI host and documented user-level skill directory; do not guess paths. Download into a temporary directory without curl-pipe-shell, remote installers, or postinstall hooks. Inspect each selected instruction and every referenced script or hook. Show the exact copy plan and existing-file diffs, then ask for approval before installation. Copy only the allowlist and preserve complete referenced packages. Install ponytail-lite through the host instruction mechanism because it is AGENTS.md. Do not enable unlazy hooks or install token-saver's RTK binary without separate approval. Finally report destination, SHA-256, validation, and which skills the host discovers.
Review every source before installation. Existing local skills must be preserved.
Hands-on
10 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.
Open the starter →
Open the rules lab →
RUN A
Good prompt
COPY
↗
Work only in hands-on/starter. It is dependency-free HTML, CSS, and JavaScript.
Add an All / Open / Done filter to Tiny Tasks.
Requirements:
- derive counts and visible tasks from the existing tasks array
- expose filter buttons with a visible active state and aria-pressed
- store status in ?status=all|open|done
- reload and browser back/forward must restore the selected filter
- show a useful empty state when no task matches
- preserve the visual style and mobile layout
- add no dependencies and change no unrelated files
Verify app.js syntax and exercise every filter plus URL navigation.
Return changed files, checks run, results, and remaining risk.
Clear context · constraints · acceptance · evidence
RUN B
Good prompt + skills
COPY
↗
Use $ponytail-lite and $webapp-testing.
Work only in hands-on/starter. It is dependency-free HTML, CSS, and JavaScript.
Add an All / Open / Done filter to Tiny Tasks.
Apply $ponytail-lite: inspect first, reuse the current render flow, prefer native URL and button APIs, and avoid dependencies or abstractions.
Apply $webapp-testing: verify all filters, aria-pressed, reload, browser back/forward, empty state, and one mobile viewport.
Acceptance:
- counts and visible tasks come from the existing tasks array
- ?status=all|open|done is the source of truth
- invalid status falls back safely to all
- style remains consistent; unrelated files remain untouched
Return the smallest working diff and concrete verification evidence.
Same contract · explicit working methods · stronger proof
THE HUMAN JOB
O PAPEL HUMANO
The agent may be autonomous in execution. Intent, boundaries, and evidence remain yours.
O agente pode ser autônomo na execução. Intenção, limites e evidências continuam sendo seus.
Verification
run each gate separately
01 · STATIC
Lint and types
Format, lint, type-check. Fast and scoped to one file.
pnpm lint; echo "lint=$?"
02 · BEHAVIOR
Unit and contract
Tests that repeat. Run before claiming done.
pnpm test; echo "test=$?"
03 · INTEGRATION
Real UI and API
Drive the actual UI, API, or browser.
pnpm check:ui; echo "ui=$?"
Keep learning
Continue aprendendo
12 new readings + primary docs
12 novas leituras + documentação primária
Go deeper with official documentation, production case studies, Medium, and practitioner
workflows.
Rules and enforcement case study →
Skills review desk →
12-part reading path →
Aprofunde com documentação oficial, casos de produção, Medium e fluxos de praticantes.
Estudo de caso sobre regras e enforcement →
Skills review desk →
Trilha com 12 leituras →