Databricks · Databricks Generative AI Engineer Associate
Chains, Tools, and Agents
Databricks Generative AI Engineer Associate · Lesson 2 of 17 · 8:49
YouTube loads only after you press play. This chapter opens at its timestamp in the full course. Watch on YouTube ↗
In this lesson
Prepare for the Databricks Certified Generative AI Engineer Associate exam. In this lesson: the components of a chain (prompt template, retriever, model, output parser), function calling (the model asks, your code runs the tool), ordering tools so that knowledge comes before action, the least complex design first and agents when the steps change, and the Agent Bricks agents named by the guide (Knowledge Assistant, Supervisor Agent, Information Extraction), now legacy offerings. Includes three original practice questions.
Preview the topics
- Copperline wants a pipeline that takes a customer question and returns an answer grounded in the product manuals, as plain text. Which set of chain components fits?
- Copperline’s agent must handle a complaint about a late order: it can search the shipping policy, look up the order status, and open a support case. In which order should these steps run?
- Copperline receives thousands of supplier invoices as PDF files, and finance wants a table with the supplier, the date, and the total of each invoice, without writing code. Which Agent Bricks agent fits?