Databricks-GenAI-Assoc Design Applications Practice Question
An engineer is building a multi-turn GenAI assistant on Databricks. The assistant must answer follow-up questions that reference earlier turns, such as 'what about its warranty?', while keeping each request within the model's context limit. Which design should the engineer implement?
⚠ Common exam trap
The trap here is assuming the serving endpoint retains state between requests, which leads to designs that either omit prior turns entirely or replay unbounded history.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Maintain the conversation in a Delta table, then on each turn build a prompt from a bounded recent window of turns plus a summary of older turns, along with retrieved context.
Bounding prompt size while preserving conversational antecedents is achieved by keeping a recent window of turns and summarizing older ones, with per-turn retrieval for grounding. Stateless endpoints, untrimmed history replay, and vector-encoded history all fail to give the model usable prior context within the context limit.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Send only the current user message to the model on every turn and rely on the model's built-in memory of prior requests.
Why it's wrong here
Model Serving endpoints are stateless, so the model has no memory of previous requests. Sending only the current message would strip the antecedent that 'its' refers to, producing answers unrelated to the earlier product. This design cannot support follow-up questions that depend on conversation history, regardless of the model's size or capabilities.
- ✓
Maintain the conversation in a Delta table, then on each turn build a prompt from a bounded recent window of turns plus a summary of older turns, along with retrieved context.
Why this is correct
Combining a recent-turn window with a rolling summary of older turns preserves the antecedents needed for follow-up questions while bounding prompt size. Retrieving relevant context per turn keeps answers grounded. This design directly meets both requirements: coherent handling of references like 'its warranty' and staying within the model's context limit as the conversation lengthens.
- ✗
Persist the conversation in a Delta table and, on each turn, resend the entire raw history along with retrieved context, trimming nothing.
Why it's wrong here
Resending the full raw history grows the prompt with every turn and will eventually exceed the model's context limit, causing failures or truncation by the runtime. It also wastes tokens on stale content and increases latency. Persisting history is useful, but replaying it untrimmed does not satisfy the requirement to stay within the context window.
- ✗
Encode the entire conversation history into a single embedding and prepend that vector to the prompt so the model can reconstruct prior turns.
Why it's wrong here
Language models consume text tokens, not raw embedding vectors, so prepending a vector does not convey prior conversational content. Even if the vector were passed through a projection layer, it would not preserve specific antecedents such as which product was discussed, so follow-up questions would remain ambiguous and the approach would not meet the requirement.
About these practice questions
One of 330 original Databricks-GenAI-Assoc practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Databricks exam blueprint
This Databricks-GenAI-Assoc practice question is part of Courseiva's free Databricks certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the Databricks-GenAI-Assoc exam.