All 56 questions
How would you manage growing conversation history and decide what context to keep, summarize, or drop?
Asked in 3 of 291 interviews · last asked Oct 6 · Design · Senior
Show answer
I would set a token budget, leaving room for the model’s reply and tool results. I would keep system instructions, recent messages, and facts needed for the current task. Before nearing that budget, I would summarize older decisions, constraints, and unfinished work, and drop repeated or irrelevant content. I would store older details separately and retrieve them when needed.
- Choose context by relevance, not just age; keep earlier facts the task still needs.
- Preserve user corrections and check that summaries do not change important facts.
- Shorten large tool outputs, keeping relevant results and references to the originals.
- Trigger summaries based on token usage, not only message count.
What the interviewer checks: The interviewer is checking whether you can control context size without losing information needed to finish the task.
Other ways it was asked
- “How would you manage context in a long-running chat with a user?”
- “How would you manage context in a long-running chat, including recent messages, summaries, and when to generate a summary?”
- “In a multi-turn agent, how would you keep the conversation useful as history grows, and how would you decide what to drop?”
How would you provide an AI agent with relevant data sources and context for a task?
Asked in 2 of 291 interviews · last asked Oct 21 · Scenario · Mid-level
Other ways it was asked
- “How would you provide an AI agent with the context it needs?”
How would you measure whether a summarization or pruning strategy is harming performance?
Asked once · last asked Oct 5 · Scenario · Senior
Other ways it was asked
- “How would you measure whether a summarization or pruning strategy is harming performance, and what offline or online metrics and tests would you use?”
How do you use prompt engineering with LLMs, and what are the key steps in building an AI agent?
Asked once · last asked Feb 17 · Concept
In LLM applications, how do you manage context and memory over a long interaction when the full context cannot fit in the model's context window?
Asked once · last asked Apr 28 · Design · Senior
How would you use feedback to help an AI agent avoid repeating incorrect results?
Asked once · last asked Jun 25 · Scenario · Senior
How would you store short-term, medium-term, and long-term memory in a multi-turn chatbot?
Asked once · last asked Jul 16 · Design · Senior
Other ways it was asked
- “How would a multi-turn chatbot decide which medium-term memory to retrieve?”
What memory types does LangChain provide, and when would you use each?
Asked once · last asked Jul 17 · Concept · Mid-level
How would you use multistep prompt chains with Zapier or Make, and how would you assess the outcomes?
Asked once · last asked Jul 20 · Tooling · Senior
Other ways it was asked
- “How have you used multistep prompt chains with Zapier or Make, and what outcomes did they produce?”
What separates an agent from a regular LLM chatbot?
Asked once · last asked Jul 22 · Concept · Mid-level
Do multiple AI agents run into context-window limitations, and how would you address them?
Asked once · last asked Jul 22 · Scenario · Senior
How would you design chat summarization, including prompts, key information, summary structure, and token limits?
Asked once · last asked Jul 28 · Design · Senior
Other ways it was asked
- “How would you summarize a long chat, and how would you prompt an LLM to extract the relevant information?”
- “How would you design a chat summarization process, including the prompt, key-information selection, summary structure and size, token limits, and use of the user's input?”
How would you build or optimize an LLM-powered or agentic application, including prompt design, tool use, and orchestration?
Asked once · last asked Aug 2 · Design · Senior
Other ways it was asked
- “How have you approached building or optimizing LLM-powered or agentic applications? Walk me through one example, including how you handled prompt design, tool use, or orchestration.”
Would you include a feedback loop or safety mechanism, such as an LLM-as-a-judge pattern, in an AI marketing workflow?
Asked once · last asked Aug 5 · Design · Senior
What validation would you add to an AI agent system?
Asked once · last asked Aug 7 · Design · Senior
How would you incorporate user feedback into the ticket-handling agent system?
Asked once · last asked Aug 7 · Design · Senior
How would you prevent a tool from getting stuck in an infinite loop in an LLM agent?
Asked once · last asked Aug 13 · Scenario · Senior
How would you validate tool outputs and enforce stop conditions in a LangGraph workflow, including the checks or guards you would implement?
Asked once · last asked Aug 16 · Tooling · Mid-level
Other ways it was asked
- “How exactly did you validate tool outputs and enforce stop conditions in your LangGraph flow? What checks or guards were in place?”
How is context assembled for the assistant prompts? What information is included, where does it come from, and who decides what gets included?
Asked once · last asked Aug 22 · Design · Senior
When you use tool-calling agents, what reliability techniques do you implement to prevent bad tool arguments, infinite loops, and inconsistent JSON outputs?
Asked once · last asked Aug 24 · Design · Senior
How do you design short-term versus long-term agent memory so it remains useful without causing context bloat or privacy issues?
Asked once · last asked Aug 24 · Design · Senior
How would you design an AI agent with read/write access to data or code to prevent cascading hallucinations and infinite loops?
Asked once · last asked Aug 26 · Design · Senior
How can iterative loops, deterministic unit tests, agent feedback loops, maximum-iteration limits, and fallback strategies improve AI agent reliability?
Asked once · last asked Aug 26 · Concept · Senior
How would you manage context and domain rules across sessions in an AI agent system?
Asked once · last asked Aug 26 · Design · Senior
How can an LLM application customize an agent's prompt or context with user-specific information?
Asked once · last asked Sep 2 · Design · Senior
How would you orchestrate an LLM pipeline for classification, and when would you use one call versus multiple calls?
Asked once · last asked Sep 2 · Design · Senior
Other ways it was asked
- “What other calls might an LLM-based classification pipeline make?”
What context would you provide to an AI agent, and how would you inject it?
Asked once · last asked Sep 8 · Behavioral · Mid-level
Other ways it was asked
- “What context did you provide to the AI agent, and how did you inject it?”
What guardrails would you add to an AI agent workflow to prevent infinite loops?
Asked once · last asked Sep 8 · Scenario · Senior
How would you manage conversation history, memory, and context windows in a chatbot?
Asked once · last asked Sep 10 · Design · Senior
How would you handle a chatbot conversation that exceeds the model's context window?
Asked once · last asked Sep 10 · Scenario · Senior
How would you store and trim conversation context when a chat history has grown to 300 messages?
Asked once · last asked Sep 18 · Design · Senior
How would you implement an intent classifier for routing requests in an agentic LLM system: as a separate machine learning model or as an LLM prompt?
Asked once · last asked Sep 22 · Scenario · Senior
Why might multi-agent system failures stem from context management rather than model capability?
Asked once · last asked Sep 28 · Concept · Senior
What is the difference between a normal LLM API call and an AI agent?
Asked once · last asked Sep 30 · Concept · Mid-level
How can you document technical decisions as a specification that an AI system can consult later?
Asked once · last asked Oct 2 · Scenario · Senior
Why can keeping all rules in a single file be a poor practice when working with AI models?
Asked once · last asked Oct 2 · Concept · Mid-level
How would you prevent AI instructions from becoming outdated and keep the context small enough for a model to use effectively?
Asked once · last asked Oct 2 · Scenario · Senior
How does a model's behavior differ when an instruction is provided as a rule rather than as a skill?
Asked once · last asked Oct 2 · Concept · Senior
How would you determine whether incomplete output resulted from a token or context limit versus another failure mode?
Asked once · last asked Oct 5 · Scenario · Senior
What proxy signals would you use to infer that a model is nearing its context limit from request or response structure or model behavior?
Asked once · last asked Oct 5 · Concept · Senior
Where would you store prompts and tool definitions for AI agents?
Asked once · last asked Oct 8 · Design · Mid-level
How would you manage and test agent context to prevent a supervisor from becoming overloaded?
Asked once · last asked Oct 14 · Design · Senior
How would you identify context that was missing from an AI agent's initial run?
Asked once · last asked Oct 21 · Scenario · Mid-level
What are the most important issues to look for in an AI agent's first output?
Asked once · last asked Oct 21 · Scenario · Mid-level
How would you use findings from an initial AI-agent run to improve the next iteration?
Asked once · last asked Oct 21 · Scenario · Mid-level
After revising an AI agent between runs, how would you identify and address remaining issues?
Asked once · last asked Oct 21 · Scenario · Mid-level
What's the difference between context compaction and reset? When would you use each?
Asked once · last asked Oct 21 · Concept · Senior
What token or context-window limitations can arise when using an AI agent for testing?
Asked once · last asked Oct 22 · Scenario · Senior
How would you organize Markdown instruction files for an AI coding agent?
Asked once · last asked Oct 22 · Tooling · Senior
Can you explain context drift normalization?
Asked once · last asked Apr 24 · Concept · Senior
What is truncation in the context of language models, and when would you use it?
Asked once · last asked Jul 16 · Concept · Junior
What is a sliding window in the context of language models, and when would you use it?
Asked once · last asked Jul 16 · Concept · Mid-level
Is a LangChain flow guaranteed to succeed every time?
Asked once · last asked Jul 17 · Concept · Mid-level
What do you mean by context window?
Asked once · last asked Aug 6 · Concept · Junior
What kinds of harnesses can be used to run or evaluate AI agents?
Asked once · last asked Aug 26 · Concept · Mid-level
What is LangChain?
Asked once · last asked Sep 21 · Concept · Junior
More Generative AI and LLM interview questions
- All Generative AI and LLM interview questions
- Generative AI and LLM Basics Interview Questions
- Prompt Engineering Interview Questions
- RAG Interview Questions
- LLM Evaluation and Benchmarking Interview Questions
- LLM Hallucinations, Safety and Security Interview Questions
- Generative AI System Design 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.
Or add the Chrome extension