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

Learning & CareersWalkthrough

Agent That Selects and Answers Using Knowledge Resources from Relevant Books

This is an example where an agent, connected to knowledge resources from multiple books, selects the appropriate book's lookup tool to answer a question.

n8n

How it works

  1. The author connects each book's InfraNodus knowledge graph and lookup tool, then provides a question for comparison.
  2. The conversational agent selects expert tools from different books, retrieves information, and composes an answer.

Results

The intended outcome in the public example is an answer that reflects the evidence from the selected book.

Notes

This is a lookup-type example using InfraNodus GraphRAG. The use of a graph alone does not guarantee answer accuracy. The author reports that public settings and tool connections were checked, but the process was not executed directly.

Source

n8n 공개 워크플로 #4485 Original post ↗

Example prompt · n8n

Goal: Select the appropriate knowledge graph from multiple books to answer a question.

Input/Environment: [Knowledge graph for each book], [InfraNodus connection], [Question], [Citation format].

Reference original: https://n8n.io/workflows/4485

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

Connections and resources to prepare: Connect each book's InfraNodus knowledge graph and lookup tool, and provide a question for comparison.

Agent behavior to implement: The conversational agent selects expert tools from different books, retrieves information, and composes an answer.

Scope of operation: This is a lookup-type example using InfraNodus GraphRAG. The use of a graph alone does not guarantee answer accuracy.

The output should be an answer that reflects the evidence from the selected book. Please also organize the necessary setup steps and actual execution method. After checking the results returned by the tool, select the next task, and separately note any inaccessible resources or tasks that could not be executed.

Verification: Test with questions that require the content of a single book and questions that require comparison across multiple books, and check whether the source of the answer matches the selected book. Clearly distinguish the inputs used for verification, the actual outputs, and any items that have not yet been confirmed.