Match a job Paths Subjects Questions Quizzes Pricing
Overview Read Practice

Practice — LLM Application System Design (6 questions)

Pro content

Sign up free, then start a 14-day Pro trial — no card needed.

Advanced Open Free

Prompt, RAG or Fine-Tune? Permalink →

A B2B SaaS company wants an assistant that answers questions about its product. Three complaints have come in from a prototype built with a plain system prompt:

  • (a) It confidently describes settings that no longer exist since last quarter's release.
  • (b) Answers are in the wrong tone and ignore the required "Summary / Steps / Related links" layout about 30% of the time even with examples in the prompt.
  • (c) It gives generic advice about "your admin panel" instead of the customer's actual configuration.
  1. For each complaint, decide whether prompt engineering, RAG, or fine-tuning is the right lever, and justify it.
  2. Explain why fine-tuning is the wrong fix for complaint (a).
  3. Sketch the order in which you would apply the fixes and how you would know each one worked.

Share this question

Advanced Open Pro

Modelling Cost and Latency for an LLM Feature

Unlock this question →
Advanced Open Pro

Debugging a Low-Quality RAG System

Unlock this question →
Advanced Open Pro

Designing an Evaluation Plan Before Launch

Unlock this question →
Advanced Open Pro

Agent or Workflow? Refund Handling

Unlock this question →
Advanced Open Pro

Semantic Caching and Model Routing Trade-offs

Unlock this question →

We use cookies for product analytics to improve OmniAtlas. See our Privacy Policy.