❓ Quiz — advanced/session-01

Program : Applied AI — Yann Isola Format: 10 MCQs (MCQ = Multiple Choice Questionnaire), certification level Claude Certified Architect Duration : 20 minutes — only one correct answer per question unless otherwise stated Threshold : 7/10

Q1 — Mandatory fields

Which fields are strictly obligatory in a query POST /v1/messages ?

HAS model , messages , system B model , max_tokens , messages C model , max_tokens , messages , temperature D model , messages — max_tokens has a default value

Q2 — stop_reason and HTTP code

A JSON extraction returns a document truncated halfway. The HTTP code was 200. What is the most likely explanation and where should it be detected?

HAS Error 500 hidden by the SDK; detect via SDK logs B stop_reason: "max_tokens" ; detect by inspecting the field stop_reason of the answer C stop_reason: "stop_sequence" ; detect via header anthropic-stop D The model judged the task completed (end_turn ) ; it's a prompt problem

Q3 — Prefilling

You complete the painting messages by {"role": "assistant", "content": "{"}. Which statements are accurate? (two answers)

HAS The model will continue its generation from {, favoring direct JSON output B The character { will be included at the beginning of the text returned by the API C The character { will NOT be included in the response; the client must re-prefix it D This request is invalid: messages must end with a role user

Q4 — System prompt

Why is the system prompt called a “privileged channel” rather than a “first message”?

HAS It is free: system prompt tokens are not charged B It is transmitted out of the table messages and processed by the model with particular priority for personas, rules and exit policies C It is end-to-end encrypted, unlike messages D It persists automatically between requests without being returned

Q5 — Context window and costs

An assistant conversation accumulates on average 40,000 history tokens returned each round, over 25 rounds. Which architect's statement is correct?

HAS Only new tokens of each round are charged; the total cost is marginal B Each turn re-invoices the entire entry: the cumulative cost of the conversation increases approximately quadratically with its length, hence the interest in summarizing, truncating or caching C The context window automatically empties the middle tokens (“lost in the middle”) D The cost is constant per round because the API compresses the history

Q6 — Prompt caching: economy

With prompt caching: which pair (write cost, read cost) is correct, as a percentage of the normal entry price? ⚠

HAS Write 100%, read 50% B Write 125%, read 10% C Writing 90%, reading 25% D Write 110%, read 0% (free read)

Q7 — Prompt caching: invalidation

What change does NOT invalidate the cache of a prefix placed on the system prompt via cache_control ?

HAS Modify a character in the system prompt before the breakpoint B Edit the definition of a tool (tools ) C Edit the content of the last message user (after the breakpoint) D Change model between two calls

Q8 — Token counting

Which statement about token counting is correct?

HAS The number of tokens of a text is identical for all models Claude and GPT (GPT = Generative Pre-trained Transformer), the tokenizer being standardized B The endpoint count_tokens generates a token response to estimate the total C Each model family has its own tokenizer; the dedicated endpoint count_tokens allows you to count a complete query (system + messages + tools) without launching a generation D We can only count the tokens after the call, via the field usage

Q9 — SSE Streaming

In an SSE flow (SSE = Server-Sent Events), in which event does the client find the stop_reason final and final count of exit tokens?

HAS message_start B content_block_stop C message_delta D message_stop

Q10 — API Batches

For non-urgent classification of 80,000 documents, what combination (discount, SLA, limit, correlation) correctly describes the Batches API? ⚠

HAS −25%; results in 1 hour guaranteed; 10,000 requests max; results returned in order of submission B −50%; 24-hour SLA (often much faster in practice); up to 100,000 requests per batch; mandatory correlation by custom_id because the order is not guaranteed C −50%; real time; 100,000 requests; correlation by array index D −90%; 24-hour ALS; unlimited queries; the batch shares conversational memory between requests

Quiz — Advanced Level, Session 1

“Claude API: Deep Dive”