Study guide — Databricks Generative AI Engineer Associate

Design Applications

• Design a prompt that elicits a specifically formatted response
  Ver resumen

  To get a specific format, combine clear instructions with few-shot examples of the desired output and, when the output must be JSON, use structured outputs: a json_schema response_format on Foundation Model APIs or responseFormat in ai_query. Simple, flat schemas generate better results, and a post-processing step can validate the format and apply a fallback response.

  Structured outputs on Databricks ↗Improve RAG chain quality ↗

• Select model tasks to accomplish a given business requirement
  Ver resumen

  Map each business requirement to a model task: classification with fixed labels, schema-based field extraction, summarization, translation, sentiment analysis, entity masking or embeddings for semantic similarity. Databricks recommends starting with the task-specific AI Functions and using ai_query when you need control over the prompt or model, or must query a custom or fine-tuned model.

  Transform unstructured data using AI Functions ↗Use ai_query ↗

• Select chain components for a desired model input and output
  Ver resumen

  A RAG chain combines query understanding (rewriting, filter extraction), retrieval (semantic, keyword or hybrid, with reranking and metadata filters), prompt augmentation, the LLM, and post-processing with guardrails. Each component is chosen from the desired input and output, and smaller models suit simple steps such as intent classification.

  Improve RAG chain quality ↗Agent system design patterns ↗

• Translate business use case goals into a description of the desired inputs and outputs for the AI pipeline
  Ver resumen

  Before building, agree with stakeholders which inputs the system will receive and who submits them, what the ideal response looks like, which criteria define a good response (accuracy, tone, citations, length) and which cost, latency and scale constraints apply. These define the input and output shape, such as source citations, custom fields or a batch job over tables.

  Agent development lifecycle ↗Author an agent and deploy it on Databricks Apps ↗

• Define and order tools that gather knowledge or take actions for multi-stage reasoning
  Ver resumen

  Agents use tools to gather knowledge (table queries, vector retrievers, Genie) and to take actions (external APIs, Unity Catalog functions). The logical order is gather data, reason, then act, with human approval for risky actions. Clear tool descriptions guide tool selection, and iteration limits prevent loops.

  Agent system design patterns ↗Create agent tools using Unity Catalog functions ↗

• Determine how and when to use Agent Bricks (Knowledge Assistant, Multiagent Supervisor, Information Extraction) to solve problems
  Ver resumen

  Knowledge Assistant builds a chatbot with citations over documents (volumes, tables or vector indexes) and improves with expert examples and guidelines. Supervisor Agent (multi-agent) coordinates Genie spaces, Knowledge Assistants, endpoints, UC functions and MCP servers according to each user's permissions. Information Extraction turns unstructured documents into tables with a defined schema and scales with ai_extract.

  Use Knowledge Assistant to create a high-quality chatbot over your documents ↗Use Supervisor Agent to create a coordinated multi-agent system ↗