Pick a focused question that fits your time, stack, and interview goal.
How much time do you have?
Show one-drill sessions you can finish now.
118 results across 1 active filter
Page 4 of 5
Contains compromised AI capabilities, preserves evidence, scopes derived data and actions, remediates boundaries, and verifies safe recovery.
Treats model changes as controlled releases using versioned configuration, fixed evaluations, shadow or canary traffic, monitoring, and rollback.
Uses explicit capability and risk policy to route by task while preserving evaluation, version attribution, budgets, and fallback semantics.
Tracks trust, versions, integrity, provenance, review, and rollback across models, adapters, prompts, datasets, tools, and parsers.
Establishes server trust, audience-bound authorization, least privilege, capability filtering, approval, and safe handling of untrusted results.
Protects knowledge ingestion with source trust, provenance, validation, quarantine, review, versioning, and rollback.
Classifies tools by consequence and applies distinct permissions, validation, confirmation, idempotency, and audit controls.
Combines deterministic invariants, severity-aware quality thresholds, slice protection, baseline comparison, and guarded rollout.
Maps assets, trust boundaries, untrusted content, model influence, actions, and abuse cases before selecting controls.
Maps risk tiers and policy statements to owned, versioned, testable runtime controls, evidence, exceptions, and review triggers.
Selects a production experiment based on user exposure, side effects, measurement needs, cost, and rollback risk.
Builds a resumable tool workflow that validates model proposals, authorizes every action, requires approval for side effects, and remains idempotent under retries.
Builds a provider-neutral model gateway that owns request deadlines, retry classification, budget enforcement, fallback policy, and versioned telemetry.
Instruments an AI workflow with correlated stage spans, low-cardinality versions, usage and outcome signals, and explicit content-capture controls.
Runs containment and recovery for an agent that ingested malicious instructions from retrieved content and attempted an unauthorized outbound tool call.
Reviews a managed AI proposal against data flow, identity, region, retention, quota, observability, portability, and recovery requirements.
Combines quality, reliability, cost, security, privacy, and recovery evidence into a realistic launch and incident game day.
Diagnoses schema-valid quality regressions across inputs, context, prompts, examples, models, schemas, tools, and downstream interpretation.
Separates product policy, orchestration, model access, data and tools, validation, state, and operations into explicit application-owned boundaries.
Distinguishes exact, provider, semantic, and intermediate caches while preserving identity, freshness, versioning, and correctness.
Defines hallucination as unsupported or incorrect model output and connects it to evidence, task design, evaluation, and user-visible uncertainty.
Explains RAG as a runtime retrieval boundary that supplies relevant, current, and governed evidence without changing model weights.
Defines AI evaluation as repeatable measurement of application behavior while preserving deterministic tests for code and contracts.
Separates what a model can perform from whether the complete AI feature behaves dependably under real inputs, failures, and constraints.