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.
66 results across 1 active filter
Page 2 of 3
Designs a narrow, typed, provider-supported schema that communicates the real downstream contract.
Combines product policy, input and output controls, context-aware handling, human escalation, appeals, and measurable safety quality.
Defines safe fallback, reduced capability, stale or cached behavior, and feature disablement without hiding changed guarantees.
Coordinates lifecycle rules across application state, provider storage, files, embeddings, caches, traces, evaluations, and backups.
Treats streams as event protocols with partial-output UX, cancellation, validation, moderation, and terminal outcome semantics.
Makes AI involvement, limitations, evidence, consequential decisions, correction, escalation, and accountability visible to users.
Creates a task-oriented model boundary that normalizes application outcomes without erasing useful provider capabilities.
Allocates per-stage deadlines and spend, controls tokens and fan-out, and optimizes for successful outcomes rather than cheap calls.
Judges claims against allowed evidence, separates correctness from support, and tests whether the system answers or abstains appropriately.
Treats the model-facing schema and downstream consumer contract as a versioned API with compatibility and rollout concerns.
Controls admission, concurrency, queues, tenant fairness, token budgets, and overload behavior before provider throttling cascades.
Uses stable operation identities, persisted states, deduplication, side-effect keys, and replay rules across requests and workers.
Separates durable application state from the model's bounded request context while preserving ownership, concurrency, and deletion.
Applies purpose limitation, selective retrieval, redaction, pseudonymization, and field-level policy before model calls.
Carries trusted tenant scope through retrieval, caches, memory, tools, traces, evaluations, and asynchronous execution.
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.
Separates user-visible progress from validated completion and prevents partial JSON or tool arguments from triggering side effects.
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.
Builds a provider-neutral model gateway that owns request deadlines, retry classification, budget enforcement, fallback policy, and versioned telemetry.
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.