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 5 of 5
Distinguishes model-directed execution from explicit application control and explains when each is appropriate.
Designs index records that support filtering, authorization, freshness, citations, diagnosis, and safe reprocessing.
Defines MCP as a client-host-server protocol for discovering and using tools, resources, and prompts without confusing interoperability with safety.
Treats model, prompt, schema, tools, routing, retrieval, policy, and evaluators as one observable behavior release.
Connects application, model, retrieval, tools, validation, retries, and outcomes while controlling sensitive telemetry.
Chooses the smallest execution model that satisfies the task while recognizing when explicit multi-step coordination adds real value.
Prefers typed APIs for reliable actions and reserves UI automation for constrained cases with stronger observation, approval, and recovery.
Chooses request-response, streaming, or durable background execution based on duration, user interaction, reliability, and side effects.
Uses pre-filtering for authorization and hard constraints while recognizing engine-specific recall and performance behavior.
Rejects agent complexity when rules, APIs, search, ordinary automation, or a bounded model call solve the task more safely.
Centralizes cross-cutting model access concerns when multiple applications or providers justify the added hop and operational ownership.
Uses a more precise second-stage ranker on a bounded candidate set while accounting for latency, cost, and authorization.
Uses task bounds and evaluation evidence to choose smaller models for lower latency, cost, capacity, privacy, or local execution.
Matches exact checks, model judgment, and human expertise to the behavior being measured instead of treating graders as interchangeable.
Uses pairwise judgments for relative change and absolute criteria for release obligations while controlling order and verbosity bias.
Chooses retrieval for ambiguous knowledge search while keeping authoritative structured operations behind deterministic services.
Uses examples to clarify ambiguous task behavior while accounting for token cost, bias, maintenance, and evaluation evidence.
Balances task quality, safety, reliability, latency, tokens, cost, refusals, repairs, and fallbacks by route and slice.
Separates structural validity from factual accuracy, evidence, authorization, and domain invariants.
Connects probabilistic decoding and changing service conditions to output variation, reproducibility limits, and appropriate testing.
Uses hierarchy and adjacency to recover context that flat chunks lose while avoiding indiscriminate document expansion.
Explains how generated text, markup, code, URLs, and tool arguments can become injection or integrity risks downstream.