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.
158 results across 1 active filter
Page 3 of 7
Chooses Vertex AI shared or reserved capacity using traffic shape, reliability, geography, cost, and workload prioritization.
Tunes evidence quantity and no-answer behavior from measured relevance rather than treating similarity scores as universal confidence.
Combines low-friction ratings, structured reasons, behavioral outcomes, review queues, and privacy-aware eval case creation.
Selects relevant, trustworthy, and budgeted context instead of treating the context window as storage.
Bounds expensive inputs, outputs, retrieval, tools, retries, concurrency, and fan-out while preserving fair service.
Uses provenance, content isolation, constrained authority, behavioral checks, and deterministic enforcement to contain hostile external instructions.
Turns a product outcome into observable quality, safety, and operational criteria before selecting convenient scores.
Builds a focused scoring guide, representative labeled examples, bias checks, and ongoing agreement monitoring for model-based evaluation.
Builds a repeatable path from governed source documents to parsed, chunked, embedded, traceable, and replaceable index records.
Combines bounded instructions, source context, a narrow schema, abstention, semantic validation, review, observability, and rollout.
Designs a bounded and reversible first AI feature with measurable value, controlled data, validation, evaluation, observability, fallback, and human oversight.
Defines a narrow capability with a clear name, decision-oriented description, typed inputs, and safe result semantics.
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.
Pauses durable execution with a clear action preview, verifies approver authority, handles expiry and changed state, and resumes idempotently.
Stores only useful, scoped, attributable memories with extraction, verification, retrieval, expiry, correction, and deletion.
Coordinates private endpoints, DNS, egress policy, dependent services, observability, and recovery without confusing network isolation with authorization.
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.
Separates traffic, data, dependency, model, prompt, and grader change while maintaining stable anchors and fresh evaluation.
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.