Claude Architect · Lezione

Formato e valutazione basati su scenari

Scenari a scelta multipla, 720/1000 per superare l’esame, nessuna penalità per le risposte casuali.

Lezione 3 di 413 passaggi

Formato e valutazione basati su scenari è una lezione Claude Architect gratuita su CoddyKit. Questa è la lezione 3 di 4. Puoi leggere la lezione completa qui gratuitamente — poi esercitati direttamente nel browser con un editor di codice integrato e un tutor IA disponibile 24/7. Fa parte del percorso di apprendimento Claude Architect, e i tuoi progressi si sincronizzano tra il web e l'app CoddyKit. Il corso Claude Architect include 4 lezioni in totale.

Parti di questa lezione non sono ancora state tradotte e vengono mostrate in inglese.

What the Exam Looks Like

The exam is scenario-based multiple choice: read a realistic situation, then pick the best of 4 options where exactly 1 is correct. No code to write, no essays.

How Scoring Works

Your result is a scaled score from 100 to 1000, with the pass mark at 720. Scaling keeps different exam forms comparable — just aim well above 720 for safety.

# Scaled score range, not a raw percentage
MIN_SCORE = 100
MAX_SCORE = 1000
PASS_SCORE = 720

my_score = 760
print("PASS" if my_score >= PASS_SCORE else "FAIL")

4 of 8 Scenarios

The exam draws from 8 core scenarios, but any single sitting shows you 4 of them — and you won't know which in advance. The takeaway: study all 8.

The 8 Scenarios at a Glance

The 8 scenarios each map to a real pattern: customer support, code generation, multi-agent research, developer productivity, CI/CD, data extraction, conversational AI, and agentic tools.

No Penalty for Guessing

There's no penalty for guessing — a wrong answer costs the same as a blank: zero. So never leave one empty. Eliminate what you can, then pick the best of the rest.

# No guessing penalty -> always answer
# Expected value of guessing 1-of-4 is strictly positive
blank_value = 0
guess_value = 1 / 4  # > 0, so guessing beats leaving blank
print("Answer every question:", guess_value > blank_value)

Who the Exam Is For

The audience is solution architects with 6+ months of production Claude experience. That's why questions are scenario-based — they test the judgment that comes from shipping, not memorized facts.

The 5 Domains and Their Weights

Questions spread across 5 weighted domains: D1 27%, D2 18%, D3 20%, D4 20%, D5 15%. D1 carries the most weight, so agent design and orchestration deserve the deepest study.

DOMAIN_WEIGHTS = {
    "D1 Agent Architecture & Orchestration": 27,
    "D2 Tool Design & MCP": 18,
    "D3 Claude Code Config & Workflows": 20,
    "D4 Prompt Engineering & Structured Output": 20,
    "D5 Context Management & Reliability": 15,
}
print(sum(DOMAIN_WEIGHTS.values()))  # 100

Why Scenarios Beat Trivia

A trivia question asks what stop_reason returns; a scenario drops you mid-loop and asks what to do next. You're given a real situation and must choose the architecturally correct response.

Distractors Are Often Anti-Patterns

Wrong options are written to be tempting — many are classic anti-patterns: parsing text for 'done', iteration caps as the main stop, or enforcing rules with prompts not hooks. Spot one, rule it out.

Read for the Strongest Answer

Often more than one option is technically valid; the exam wants the strongest for the context. Anchor on principles: terminate on stop_reason, use hooks for critical rules, pass context to subagents.

# Correct agentic-loop termination: driven by stop_reason
while True:
    resp = client.messages.create(model=MODEL, max_tokens=1024,
                                  messages=history, tools=tools)
    if resp.stop_reason == "tool_use":
        history.append({"role": "assistant", "content": resp.content})
        history.append(run_tools(resp))   # append results, continue
        continue
    break  # end_turn / max_tokens / stop_sequence -> stop here

A Smart Test-Taking Strategy

A smart strategy: answer everything, eliminate anti-patterns to shrink 4 options to 2, weight prep toward D1, study all 8 scenarios, and aim past 720 with margin.

Quick Check: Format & Scoring

Apply what you've learned about the exam's format and scoring rules.

Recap: Format & Scoring

Recap: scenario-based MCQ (4 options, 1 correct), scaled 100-1000, pass 720, 4 of 8 scenarios, no guessing penalty. Domains D1 27% to D5 15%. Eliminate anti-patterns, then pick the strongest.

Gratis per iniziare

Impara Python con un tutor IA — gratis

Scrivi ed esegui vero codice nel tuo browser, ricevi aiuto istantaneo da un tutor IA disponibile 24/7, e riprendi da dove hai lasciato sul web o nell'app.

Corsi
26
Lezioni
104

Domande Frequenti

La lezione «Formato e valutazione basati su scenari» è gratuita?

Sì — il testo completo di «Formato e valutazione basati su scenari» è gratuito qui sul web. Per esercitarvi in modo interattivo (un editor di codice integrato e un tutor IA 24/7) e sbloccare il resto del corso Claude Architect, passa a CoddyKit PRO. Il corso Claude Architect include 4 lezioni in totale.

Cosa imparerò in «Formato e valutazione basati su scenari»?

Scenari a scelta multipla, 720/1000 per superare l’esame, nessuna penalità per le risposte casuali. Eserciti Claude Architect con codice pratico che esegui direttamente nel browser, e un tutor IA 24/7 risponde alle tue domande mentre lavori sulla lezione.

Ho bisogno di esperienza per iniziare Claude Architect?

Non è richiesta alcuna esperienza precedente. Claude Architect su CoddyKit è strutturato per principianti e studenti avanzati, quindi puoi iniziare da qui o dall'inizio e procedere al tuo ritmo. Questa è la lezione 3 di 4.

Quanto tempo richiede la lezione «Formato e valutazione basati su scenari»?

La maggior parte delle lezioni CoddyKit richiede circa 5–10 minuti. Ogni lezione è breve e interattiva, quindi fai progressi costanti e riprendi esattamente da dove hai lasciato su web e app.

Posso scrivere ed eseguire codice in questa lezione Claude Architect?

Sì. Ogni lezione Claude Architect include un editor di codice integrato, quindi scrivi ed esegui codice reale direttamente nel tuo browser e ricevi feedback istantaneo dall'IA — nessuna configurazione locale necessaria.

Tutte le lezioni di questo corso

  1. La certificazione in breve
  2. Le cinque aree d’esame
  3. Formato e valutazione basati su scenari
  4. Chi dovrebbe sostenere questo esame
← Torna a Claude Architect