All 76 questions

  1. What makes a good prompt, and how do you write one?

    Asked in 7 of 291 interviews · last asked Oct 21 · Concept · Mid-level

    Show answer

    A good prompt clearly states the task, gives relevant context, and defines what a useful answer should look like. I include constraints, the output format, and examples when needed. I test it on realistic inputs, check the results, and revise unclear instructions.

    • Give enough context to avoid guessing, but leave out unrelated details.
    • State requirements such as language, length, format, and software versions.
    • Use examples when the desired behavior is hard to describe.
    • Test and refine prompts; clear instructions do not guarantee correct output.
    Code
    Write a Python function that removes duplicate strings from a list.
Keep the first occurrence of each string, in its original order.
Use only the standard library. Do not change the input list.
Return the function and tests for empty input, duplicates, and unique values.

    What the interviewer checks: The interviewer is checking whether you can turn a vague goal into clear instructions and evaluate the results.

    Other ways it was asked
    • “How do you write prompts for AI tools to support software development?”
    • “How do you write effective prompts for AI systems?”
    • “How do you write effective prompts for generative AI tools, and how did you develop that skill?”

  2. What is the difference between one-shot, few-shot, and zero-shot prompting?

    Asked in 2 of 291 interviews · last asked Aug 19 · Concept · Mid-level

    Other ways it was asked
    • “What are zero-shot, one-shot, and few-shot prompting, and when would you use each?”

  3. Tell me about a work task where an AI tool produced useful output end to end. What input did you provide, and how did you validate and use the output?

    Asked in 2 of 291 interviews · last asked Oct 18 · Behavioral · Mid-level

    Other ways it was asked
    • “Tell me about a task where an AI tool produced a particularly useful result. What prompt or workflow did you use, and how did you use the output?”

  4. How would you design and manage the system prompt for an LLM agent?

    Asked in 2 of 291 interviews · last asked Jul 16 · Concept · Mid-level

    Other ways it was asked
    • “How would you prompt an LLM using a system prompt?”

  5. Write a prompt for a multilingual voice AI agent with agentic tool orchestration.

    Asked once · last asked Jul 27 · Mid-level

  6. How would you structure a four-turn prompting process to improve an executive KPI narrative without adding facts or changing KPI definitions?

    Asked once · last asked Sep 16 · Scenario · Mid-level

  7. Can you walk me through the process or approach you generally follow to craft a prompt from scratch to achieve a high-quality, specific output?

    Asked once · last asked Mar 5 · Tooling · Mid-level

  8. How would you design a complex, multistep prompt or chain-of-thought workflow?

    Asked once · last asked Mar 5 · Behavioral · Senior

    Other ways it was asked
    • “Can you describe a complex, multistep prompt or chain-of-thought workflow you have designed?”

  9. Can you think of a complex, real-world insurance scenario and draft a prompt with multiple requirements for a model acting as an insurance analyst?

    Asked once · last asked Mar 5 · Case · Mid-level

  10. If you had to write a 500-word, SEO-friendly blog, what prompt would you give ChatGPT or another LLM tool?

    Asked once · last asked Apr 8 · Tooling · Mid-level

    Other ways it was asked
    • “How would you prompt an LLM to write a 500-word, SEO-friendly blog on a topic provided to you?”

  11. How do you use prompt files to provide context or instructions to an AI coding assistant?

    Asked once · last asked Apr 14 · Tooling · Mid-level

  12. What context or style guidance do you give an AI coding assistant, such as repository code samples, and do you use ad hoc prompts?

    Asked once · last asked Apr 14 · Tooling · Mid-level

  13. If a model keeps repeating the same answer instead of generating improved or varied responses, how would you address that?

    Asked once · last asked Apr 20 · Scenario · Mid-level

  14. Could you name one or two techniques for ensuring that an LLM’s output is structured, such as valid JSON?

    Asked once · last asked Apr 27 · Concept · Mid-level

  15. Could you name two or three good prompt-engineering techniques, and give a use case and an example of when a particular technique is especially necessary?

    Asked once · last asked Apr 27 · Concept · Mid-level

  16. What makes a good mathematical prompt?

    Asked once · last asked May 19 · Concept · Mid-level

  17. How would you use viewer analysis to inform prompt design for AI-generated videos?

    Asked once · last asked Jun 25 · Scenario · Mid-level

  18. What is reflection prompting?

    Asked once · last asked Jul 16 · Concept · Mid-level

  19. What formats can be used for structured model outputs, and how do you choose among them?

    Asked once · last asked Jul 16 · Concept · Mid-level

  20. How would you prompt a model to use reasoning or the ReAct approach?

    Asked once · last asked Jul 16 · Scenario · Mid-level

  21. What is the best structure for a prompt to give an LLM so it produces a good outcome?

    Asked once · last asked Jul 22 · Concept · Junior

  22. How would you prompt an AI tool to recreate a movie or TV scene when the script is provided but regional settings are unavailable? What else would you specify?

    Asked once · last asked Jul 23 · Tooling · Junior

  23. What practices do you use to ensure the quality of tasks and prompts?

    Asked once · last asked Jul 24 · Behavioral · Mid-level

  24. How would you use prompt engineering to improve an LLM application's performance?

    Asked once · last asked Jul 25 · Scenario · Mid-level

  25. How would you develop prompt specifications and schema structures, including decision logic, tuning, and wording?

    Asked once · last asked Jul 27 · Concept · Senior

    Other ways it was asked
    • “What approaches have you used to develop prompt specifications and schema structures, including decision logic, tuning, and wording?”

  26. How would you use Claude to accelerate coding, debug errors across different code bases, and ensure you do not mix up the requirements of the projects when managing three projects simultaneously?

    Asked once · last asked Aug 10 · Tooling · Senior

  27. Design a single prompt that makes an AI produce a production-ready fairness evaluation memo for a high-stakes binary classifier. Specify the objective, context, constraints, required sections, evaluation criteria, and exact output format.

    Asked once · last asked Aug 11 · Senior

  28. How would you diagnose and improve an LLM prompt that produces a poor review summary?

    Asked once · last asked Aug 17 · Scenario · Senior

  29. If you need a response back from an LLM in JSON format, how would you design the prompt?

    Asked once · last asked Aug 19 · Scenario · Mid-level

  30. Can you give one or two examples of rules you give AI tools about what they should and should not do?

    Asked once · last asked Aug 20 · Tooling · Mid-level

  31. When a model is given conflicting instructions, such as “be concise” and “include all details,” what process should it follow to decide what to include and what to omit?

    Asked once · last asked Aug 25 · Scenario · Mid-level

    Other ways it was asked
    • “If you give a model a set of conflicting instructions—for example, “be concise” and “include all details”—what exact process do you follow to decide what to do and what to omit?”

  32. If an AI assistant generates failing test scenarios, how would you prompt it to fix the code and make the tests pass?

    Asked once · last asked Aug 25 · Scenario · Mid-level

  33. How would you implement prompt constraints and domain rules in an AI agent system?

    Asked once · last asked Aug 26 · Scenario · Mid-level

  34. How do you brief and prompt AI tools to create direct-response ads?

    Asked once · last asked Sep 14 · Scenario · Mid-level

  35. What is an example of a prompt you would write for ChatGPT or Claude to help with a coding task?

    Asked once · last asked Sep 15 · Tooling · Mid-level

    Other ways it was asked
    • “What is an example of a recent prompt you wrote for ChatGPT or Claude to help with a coding task?”

  36. What structured format do you ask the assistant to produce, for example a bullet summary or a table of clauses, and why does that format reduce your review time?

    Asked once · last asked Sep 15 · Tooling · Mid-level

  37. When you start a new session, how do you prompt to ensure the assistant preserves exact terms like exclusion, deductible, defined terms, and numbers, and doesn't paraphrase them?

    Asked once · last asked Sep 15 · Tooling · Mid-level

  38. Design a single AI prompt to generate a six-page memo recommending whether to launch usage-based pricing for a B2B SaaS product.

    Asked once · last asked Sep 19 · Tooling · Mid-level

  39. How would you turn a dietary analysis or clinical nutrition workflow into a challenging prompt for an AI?

    Asked once · last asked Sep 21 · Case · Mid-level

  40. When using AI tools for a software task, how do you provide enough context and break the work into prompts to avoid overly broad changes?

    Asked once · last asked Sep 22 · Tooling · Mid-level

  41. How would you add dynamic prompt templates that evolve over time to an AI orchestrator?

    Asked once · last asked Sep 24 · Design · Mid-level

  42. How would you make an AI model follow given rules more reliably when it does not follow them consistently?

    Asked once · last asked Oct 2 · Scenario · Senior

  43. How would you enforce a strict output format, such as exactly three bullets and a word cap, at scale when models occasionally drift?

    Asked once · last asked Oct 5 · Scenario · Senior

  44. What structured output formats can you use in an LLM application, and how do you choose between them?

    Asked once · last asked Oct 6 · Concept · Mid-level

  45. How would you work with GitHub Copilot to get structured outputs from LLMs?

    Asked once · last asked Oct 8 · Tooling · Mid-level

  46. What prompt would you give an AI assistant to convert a Windows Forms application into a web page?

    Asked once · last asked Oct 9 · Scenario · Mid-level

  47. If repeated failures lead you to recommend prompt improvements, what template would you use to report the issues, root causes, and proposed prompt revisions?

    Asked once · last asked Oct 9 · Scenario · Mid-level

  48. What techniques do you use for enhancing the naturalness and tone of AI-generated responses?

    Asked once · last asked Oct 9 · Concept · Mid-level

  49. How would you use a vision-language model to interpret complex engineering drawings?

    Asked once · last asked Oct 14 · Scenario · Senior

  50. Given that LLMs tend to produce consensus-based, average answers rather than unique insights, how do you think you could work around that?

    Asked once · last asked Oct 14 · Scenario · Senior

  51. What challenges arise when creating a reusable AI prompt to support Oracle-to-PostgreSQL migrations across 10 to 15 applications?

    Asked once · last asked Oct 16 · Scenario · Senior

  52. For a specific task, how would you use an AI tool to produce a high-quality result, including defining the goal, choosing a prompt or workflow, and evaluating the output?

    Asked once · last asked Oct 17 · Tooling · Mid-level

    Other ways it was asked
    • “Tell me about one specific task where one of these tools did an especially good job. What was the goal, what prompt or workflow did you use, and what made the output good?”

  53. What specific prompting or workflow pattern would you use when you need higher factual reliability?

    Asked once · last asked Oct 17 · Tooling · Mid-level

  54. What specific prompting or workflow patterns do you use to force citations, quote exact passages, or clearly mark uncertainty?

    Asked once · last asked Oct 17 · Tooling · Mid-level

  55. How would you design a repeatable prompt template for case summaries that forces a strict schema and explicitly flags unknown or not-in-source fields?

    Asked once · last asked Oct 18 · Design · Senior

  56. How should an AI-agent prompt specify the output format and quality standards?

    Asked once · last asked Oct 21 · Concept · Mid-level

  57. How can you identify important omissions in an AI-agent prompt?

    Asked once · last asked Oct 21 · Scenario · Mid-level

  58. What concrete constraints do you add to a question to prevent hand-wavy answers while still keeping it answerable verbally?

    Asked once · last asked Oct 21 · Scenario · Senior

  59. How do you decide the minimum set of assumptions to state in the prompt to avoid ambiguity without over-constraining the question into a trivial lookup?

    Asked once · last asked Oct 22 · Scenario · Senior

  60. When you use an AI coding agent to implement a small Spring Boot feature, what specific context do you provide upfront—codebase files, constraints, and examples—and how do you verify the output before merging?

    Asked once · last asked Oct 22 · Tooling · Mid-level

  61. When the agent proposes a multi-file refactor in a Spring Boot codebase, how do you scope it down and structure the prompts so it stays safe and reviewable?

    Asked once · last asked Oct 22 · Tooling · Senior

  62. How would you use prompt engineering in a project, and what tasks could it support?

    Asked once · last asked Mar 28 · Concept · Mid-level

    Other ways it was asked
    • “How did you use prompt engineering in a project, and what tasks did it support?”

  63. What is prompting?

    Asked once · last asked Apr 28 · Concept · Junior

    Other ways it was asked
    • “What are some prompting techniques?”

  64. What is a system instruction in an AI agent?

    Asked once · last asked Jun 9 · Concept · Junior

  65. How would you use AI for question answering, prompt creation, or content generation?

    Asked once · last asked Jun 25 · Scenario · Mid-level

  66. How do you provide context and instructions to Claude to get useful results?

    Asked once · last asked Jul 16 · Tooling · Mid-level

  67. Explain LLMs and write a Python program demonstrating dynamic programming.

    Asked once · last asked Jul 17 · Write code · Junior

  68. How would you prompt an AI to build a drug-alias lookup from a CSV?

    Asked once · last asked Jul 24 · Tooling · Mid-level

  69. Why is a prompt/spec engineer an important role in developing an AI system?

    Asked once · last asked Jul 27 · Concept · Mid-level

    Other ways it was asked
    • “Why is a prompt/spec engineer an important role in an AI system like this?”

  70. What is chain of thought in prompt engineering?

    Asked once · last asked Aug 19 · Concept · Mid-level

  71. When you write a prompt, what structure does it have?

    Asked once · last asked Aug 25 · Concept · Mid-level

  72. How would you write a prompt constraint for a specific AI agent use case?

    Asked once · last asked Aug 26 · Scenario · Mid-level

  73. How do you develop and refine prompts for an LLM application?

    Asked once · last asked Sep 2 · Scenario · Mid-level

  74. What is a structured output parameter when interacting with an AI model?

    Asked once · last asked Oct 13 · Concept · Mid-level

  75. What types of prompts can you use when interacting with AI?

    Asked once · last asked Oct 13 · Concept · Junior

  76. How would you design reusable AI prompts that multiple team members can use?

    Asked once · last asked Oct 16 · Scenario · Mid-level

More Generative AI and LLM interview questions

How this list is made

Every question here was asked by a real interviewer in a real job interview that a candidate ran MeetAssist in. After the call, the interviewer's questions are pulled from the transcript. Practice sessions, tests, exams and anything that was not a job interview are dropped.

Questions are rewritten so they make sense on their own: names of people, employers and clients are removed, and speech-to-text mistakes are fixed. Small talk, logistics and questions about one candidate's own résumé are left out. Rephrasings of the same question are merged, and the count is the number of different interviews it came up in.

The interviews come from candidates who use MeetAssist, so they lean towards software, data and AI roles: the shares describe these interviews, not every Generative AI and LLM interview. Answers to the most asked questions are written and checked by an editor; a "common mistake" is shown only when reviews of real answers in these interviews show it, with the count.

291 interviews, 178 candidates, Feb 2026 to Oct 2026. Updated every month with new interviews.