Multiple Choice

What is the right permission model for an agent with read-docs, run-SQL, and Slack-send tools?

How should an agent degrade gracefully when a third-party API tool with 99% uptime is unavailable?

How do you enforce a $0.50 per-task LLM budget at runtime beyond setting max_tokens?

How should a long-running agent task persist state so it can resume after a crash or deployment?

How should you score a multi-step agent where final answer accuracy is 15% but most steps are correct?

What does 'persona prompting' (or role-based prompting) actually do and where does it stop being useful?

What does a model's 'context window' mean and what does it include?

In a production prompt for generating a single SQL query, what's the right way to make sure the model returns only the SQL without trailing commentary?

You're shipping a prompt change to production. What is the strongest reason to treat prompt-template version IDs (e.g. v1.7.2) as first-class artifacts, separate from your code release version?

You're migrating a production prompt from Claude Opus 4.7 to GPT-5.5 to cut cost. What's the most reliable indicator that you can or cannot move the prompt as-is?

What does the max_tokens parameter control in an LLM API call?

You have 500KB of relevant documentation that exceeds the 200K-token context window of your production model. How should you choose between context stuffing (fit what you can) and RAG retrieval?

Your team is comparing a vanilla LLM chatbot against a RAG chatbot. What is the single most important difference between them at query time?

Your team is tuning top-k for the retriever in a production RAG system. What is the strongest reason NOT to just push top-k to its highest possible value?

What is the core mechanism that distinguishes Self-RAG (Asai et al. 2023) and Corrective-RAG (CRAG, 2024) from a standard single-shot retrieve then generate pipeline?

Why does hybrid retrieval (BM25 plus dense vectors) typically outperform either alone in production RAG?

You are tuning chunk size in a RAG pipeline. What is the core tradeoff between very small chunks (e.g. 128 tokens) and very large chunks (e.g. 2000 tokens)?

Naive safety FT failed: model now refuses 'how does anesthesia work?'. Best fix?

Prompt-tuning vs LoRA: pick the architectural reason LoRA tends to win

ORPO vs DPO: which architectural difference enables 'single-stage' training?

Multi-GPU FT: pick the right sharding strategy for a 70B full FT on 8 H100s

Why does fp16 fine-tuning need dynamic loss scaling but bf16 doesn't?

Misconception: 'higher LoRA rank always wins on benchmarks'

Misconception: 'LoRA is just a quantization technique'

Best architecture for a chatbot over a frequently-updated company knowledge base?