1. Prompt & Version Management advanced

    140 prompts live as string literals across nine services. You must move them into a central prompt registry with no quality regression and no big-bang cutover, while every team keeps shipping. What is the sequence, and where can it go wrong?

    3 min answer prompt-managementmigrationversioningevaluation
  2. Prompt & Version Management intermediate

    A platform's prompts are embedded in application code and changed frequently. What problems arise, and how should prompts be managed?

    2 min answer prompt-managementversioningevaluationreproducibility
  3. Prompt & Version Management intermediate

    An engineer wants to change the system prompt of a live customer-facing assistant at 16:00 on a Friday. Tell me what has to already be true for that to be a routine change and what you would ask before approving it.

    3 min answer prompt-managementrelease-engineeringrollbackevaluation
  4. Prompt & Version Management intermediate

    Answer quality degraded overnight. No code was deployed. What are the candidate causes?

    2 min answer llmchange-managementobservability
  5. Prompt & Version Management intermediate

    Review this. Prompts live in a database table and are edited through an internal web interface by product managers. There is no version history. An A/B test assigns users randomly between a `current` row and an `experiment` row. Outputs are logged with the user id and the response text. What would you remove, what would you change, and what would you leave alone?

    4 min answer prompt managementprovenanceversioningexperiments
  6. Prompt & Version Management beginner Multiple choice

    Three engineers run one assistant with six prompts. A vendor is offering a hosted prompt registry with live editing and a dashboard. Where should those six prompts live?

    3 min answer prompt-managementversioningpragmatismdeployment
  7. Pseudonymisation intermediate Multiple choice

    A product analytics team needs per-user aggregation over two years of events without holding data that re-identifies people if the warehouse leaks. Which approach actually delivers that?

    2 min answer pseudonymisationtokenisationhashingkey-custody
  8. Pseudonymisation advanced

    A travel metasearch of Expedia's shape replaces every traveller email with a deterministic HMAC token before the data reaches the analytics warehouse and before any file goes to an advertising partner. Two years later an audit finds that one partner can name individual travellers. The token vault was never breached. What failed?

    3 min answer pseudonymisationtokenisationlinkabilityre-identification
  9. Pseudonymisation advanced

    On 4 August 2006 AOL published about 20 million search queries from more than 650,000 users over three months, with usernames replaced by random numbers. Within days the New York Times had identified user 4417749 as a named individual from the content of her searches alone. What failed, which design assumption made it possible, and what would have prevented it?

    3 min answer aolre-identificationquasi-identifiersanonymisation
  10. Pseudonymisation advanced

    Pseudonymisation reduces regulatory obligations. What does it actually provide, and where is it commonly overstated?

    2 min answer pseudonymisationanonymisationre-identificationkey-separation
  11. Publish/Subscribe advanced

    A chat platform uses publish/subscribe to deliver messages to connected clients. What breaks when a channel has a million members, and what changes?

    2 min answer pubsubfan-outscalepresence
  12. Publish/Subscribe advanced Multiple choice

    A payments service publishes PaymentCaptured to a topic with four subscribers. A fifth team needs the same event plus the payer's full name and address, which the producer does not emit because those fields are restricted. The fifth team proposes subscribing and then calling the producer per event to fetch them - about 900 extra reads a second. Which design fits?

    3 min answer pub-subtopic designauthorisationpii