Multi-select

Which of the following are augmentation sub-decisions in a production RAG pipeline? Select all that apply.

Which of the following are components of a production-grade prompt beyond 'just instructions'?

Which of the following content types belong in the SYSTEM message (not the user message) in a production chat-style prompt?

Which of the following are MEANINGFUL defenses against prompt injection in a production LLM application?

Which statements correctly describe the MCP primitive types?

Which criteria indicate a high-quality MCP server tool definition?

Which of the following are categories in the community-maintained OWASP MCP / Agentic AI risk taxonomy (2025)?

Which practices represent good host-side approval UX for MCP tool calls?

Which of the following are established MCP client implementations?

Which of the following are items on the MCP 2026 roadmap?

Which user-visible failure modes should trigger escalation from automated eval to human review?

Which properties correctly describe the complementary roles of the three LLM evaluation modes?

Which properties characterize a well-designed LLM eval rubric?

Which statements correctly describe the four RAGAS metrics?

Which statements correctly describe the benefits and limitations of a panel of judges eval setup?

Which proxy signals are valid indicators of potential quality drift in a production LLM system?

Which quality controls are essential when using an LLM to generate eval test cases?

Which methods are practical approaches for detecting train-eval data leakage in LLM benchmarks?

Which strategies reduce LLM-as-judge evaluation cost at scale without sacrificing reliability?

Which considerations are uniquely important for A/B testing LLM systems vs standard UI testing?

Which of the following are canonical stopping conditions for an agent loop?

Which conditions favour a multi-agent architecture over a single-agent system?

Which events must every agent execution trace capture to enable debugging of production failures?

Which runtime safeguards prevent an agent from looping indefinitely?

Which of the following are valid strategies for mitigating context pollution in a long-running agent?