AI Agent Use Cases
Views —

AI Agent Use Cases

Added today

44All 189

Prompt to Prepare a Shopping Cart from a Recipe Photo

The author reports that Grok Bot receives a recipe photo, organizes the ingredients and quantities, and creates a shopping list by excluding ingredients already available at home.

Grok Bot
Life & Hobbies

1–20 of 189

Life & HobbiesWalkthrough

Agent That Recommends Movies Based on Both Liked and Disliked Titles

When the user mentions movies they like and want to avoid, the agent searches for candidates using a recommendation tool and reflects these preferences in the conversation.

n8n

How it works

  1. Connect the IMDB sample movie data to Qdrant and provide the liked and disliked conditions.
  2. The agent sends the liked and disliked conditions to the recommendation tool and incorporates the Qdrant search results into the conversation.

Results

In the public example, the intended outcome is movie recommendations that reflect the user's preferences.

Notes

This is based on sample data from the top 1,000 IMDB movies. It does not search all movies or check current streaming availability. The author reports that public settings and tool connections were checked, but the process was not executed directly.

Source

n8n 공개 워크플로 #2440 Original post ↗

Example prompt · n8n

Goal: Get recommendations that reflect both movies you like and movies you want to avoid.

Inputs/Environment: [Movies you like], [Movies to avoid], [Qdrant sample data], [Number of recommendations].

Reference original: https://n8n.io/workflows/2440-building-rag-chatbot-for-movie-recommendations-with-qdrant-and-open-ai/

Please prepare the settings and connections so that a test environment can be created using the public configuration from the original. If there are any missing sub-workflows, APIs, or account permissions, mark them as incomplete until they are actually connected.

Connections and data to prepare: Connect the IMDB sample movie data to Qdrant and provide the liked and disliked conditions.

Agent behavior to implement: The agent sends the liked and disliked conditions to the recommendation tool and incorporates the Qdrant search results into the conversation.

Scope of operation: This is based on sample data from the top 1,000 IMDB movies. It does not search all movies or check current streaming availability.

The result should be movie recommendations that reflect the user's preferences. Please also organize the necessary setup steps and the actual execution method. After checking the results returned by the tool, choose the next task, and separately note any data that could not be accessed or tasks that could not be executed.

Verification: Check whether the disliked conditions are actually reflected in the recommendations, and confirm that the tool does not fabricate titles not in the data or information about current viewing platforms. Show the inputs used for verification, the actual outputs, and clearly distinguish any items that have not yet been verified.