Some products and features are in the process of being renamed. Generative playbook and flow features are also being migrated to a single consolidated console. Seethe details.
Stay organized with collectionsSave and categorize content based on your preferences.
The movie expertplaybook-based prebuilt agentcan answer a wide range of movie-related questions.
The agent references both a BigQuery dataset containing metadata about
movies and an unstructured data store of movie plot
summaries sourced from Wikipedia.
Sample dialogs
The following sample dialogs demonstrate common scenarios
handled by this prebuilt agent.
Plot Summary and Database Search
The user asks the agent for a summary of Avatar.
The agent retrieves the movie plot for Avatar from the data store,
and summarizes it for the user.
The user asks how much profit Avatar made.
The agent searches the database for Avatar's revenue and budget,
and uses this information to answer the user's question.
The user asks what the highest-earning non-English movie was in the month
that Avatar was released.
The agent searches the database,
filtering by date and language, and answers the user's question.
User input
Agent response
Hi
Hi there, welcome to Cymbal Movies! I'm here to help with your movie-related questions. Ask away!
Tell me more about Avatar
The plot of the movie "Avatar" is as follows:
In 2154, humans have depleted Earth's natural resources, leading to a severe energy crisis. The Resources Development Administration (RDA for short) mines for a valuable mineral --- unobtanium --- on Pandora, a densely forested habitable moon orbiting the gas giant Polyphemus in the Alpha Centauri star system. Pandora, whose atmosphere is poisonous to humans, is inhabited by the Na'vi, a species of 10-foot tall (3.0 m), blue-skinned, sapient humanoids that live in harmony with nature and worship a mother goddess named Eywa.
Is there anything else I can help you with?
How much profit did it make?
Avatar had a budget of $237 million and grossed $2.79 billion, making a profit of $2.55 billion. Is there anything else I can help you with?
What was the highest-earning non-English movie in the month that Avatar was released?
The highest-earning non-English movie in the month that Avatar was released was 3 Idiots, which grossed $70 million. Is there anything else I can help you with?
This agent includestoolsthat are
used to integrate with external services.
The service will automatically create the dependent BigQuery dataset
named "Movies" with two tables named "movies_data" and "credits".
The movie metadata will be imported into the newly created table,
and thebq-searchOpenAPI tool is built on that data.
In addition, a new Data Store named "Movie Expert-data-store"
will be created and the required documents will be imported,
which is used by the "cymbal-movie-plots" Data Store tool.
Steering
Thecymbal-movie-plotstool connects to a data store pointing
to a Cloud Storage bucket containing movie plot summaries.
Search Movie Database
Thebq-searchOpenAPI tool connects to the BigQuery API, inputs the SQL query
generated by the agent,
executes it on the BigQuery table containing metadata on movies,
and returns the query outputs to the agent as a JSON object.
You need to configureService Account authenticationfor this tool,
and provide a service account which you have granted
the BigQuery Job User and BigQuery Data Viewer roles.
Complete
Your agent and its integrations should now be set up and ready to test.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-09-04 UTC."],[[["\u003cp\u003eThis document introduces a prebuilt "movie expert" agent that can answer a variety of movie-related questions using a BigQuery dataset and unstructured movie plot summaries from Wikipedia.\u003c/p\u003e\n"],["\u003cp\u003eThe agent can retrieve movie plot summaries from a data store and provide details on a movie's financial performance, including revenue and profit, by searching its connected databases.\u003c/p\u003e\n"],["\u003cp\u003eThe prebuilt agent's setup requires importing the agent, and configuring provided tools to integrate with external services via the provided tool installer.\u003c/p\u003e\n"],["\u003cp\u003eThe agent utilizes two main tools: \u003ccode\u003ecymbal-movie-plots\u003c/code\u003e to access movie plot summaries from Cloud Storage, and \u003ccode\u003ebq-search\u003c/code\u003e to query a BigQuery table for movie metadata.\u003c/p\u003e\n"],["\u003cp\u003ePre-GA products and features such as this agent are available "as is" and might have limited support as stated in the "Pre-GA Offerings Terms", which are subject to change.\u003c/p\u003e\n"]]],[],null,["# Movie expert prebuilt agent\n\nThe movie expert\n[playbook-based prebuilt agent](/dialogflow/cx/docs/concept/playbook/prebuilt)\ncan answer a wide range of movie-related questions.\nThe agent references both a BigQuery dataset containing metadata about\nmovies and an unstructured data store of movie plot\nsummaries sourced from Wikipedia.\n\nSample dialogs\n--------------\n\nThe following sample dialogs demonstrate common scenarios\nhandled by this prebuilt agent.\n\n### Plot Summary and Database Search\n\nThe user asks the agent for a summary of Avatar.\nThe agent retrieves the movie plot for Avatar from the data store,\nand summarizes it for the user.\nThe user asks how much profit Avatar made.\nThe agent searches the database for Avatar's revenue and budget,\nand uses this information to answer the user's question.\nThe user asks what the highest-earning non-English movie was in the month\nthat Avatar was released.\nThe agent searches the database,\nfiltering by date and language, and answers the user's question.\n\nBasic setup\n-----------\n\nTo set up this prebuilt agent:\n\n1. [Import the prebuilt agent](/dialogflow/cx/docs/concept/playbook/prebuilt#import).\n2. Leave the **Create dependent resources** checkbox checked.\n\nTool setup\n----------\n\nThis agent includes [tools](/dialogflow/cx/docs/concept/playbook/tool) that are\nused to integrate with external services.\nThe service will automatically create the dependent BigQuery dataset\nnamed \"Movies\" with two tables named \"movies_data\" and \"credits\".\nThe movie metadata will be imported into the newly created table,\nand the `bq-search` OpenAPI tool is built on that data.\nIn addition, a new Data Store named \"Movie Expert-data-store\"\nwill be created and the required documents will be imported,\nwhich is used by the \"cymbal-movie-plots\" Data Store tool.\n\n### Steering\n\nThe `cymbal-movie-plots` tool connects to a data store pointing\nto a Cloud Storage bucket containing movie plot summaries.\n\n### Search Movie Database\n\nThe `bq-search` OpenAPI tool connects to the BigQuery API, inputs the SQL query\ngenerated by the agent,\nexecutes it on the BigQuery table containing metadata on movies,\nand returns the query outputs to the agent as a JSON object.\n\nYou need to configure\n[Service Account authentication](/dialogflow/cx/docs/concept/playbook/tool#openapi_tool_api_authentication)\nfor this tool,\nand provide a service account which you have granted\nthe BigQuery Job User and BigQuery Data Viewer roles.\n\nComplete\n--------\n\nYour agent and its integrations should now be set up and ready to test."]]
