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

DevWalkthrough

Agent That Reads and Updates Response Rules Set in Conversation

The author reports that a conversational agent reads existing response rules and adds or modifies stored instructions according to user requests.

n8n

How it works

  1. The author connects a database for storing response rules and tools for viewing and editing the rules.
  2. The agent retrieves existing rules and, based on user modification requests, runs tools to add or update rules in the database.

Results

The author states that the intended outcome in the public example is stored response instructions that will be applied in subsequent conversations.

Notes

This is an implementation example that updates stored instructions, not one that retrains weights. The author confirms that public settings and tool connections were checked, but the process was not executed directly.

Source

n8n 공개 워크플로 #4694 Original post ↗

Example prompt · n8n

Goal: Maintain response rules set in conversation for future tasks.

Input/Environment: [Initial response rules], [Test DB], [Change request], [Rule application scope].

Reference original: https://n8n.io/workflows/4694

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 actually connected.

Connections and materials to prepare: Connect a database for storing response rules and tools for viewing and editing the rules.

Agent behavior to implement: The agent retrieves existing rules and, based on user modification requests, runs tools to add or update rules in the database.

Scope of operation: This is an implementation example that updates stored instructions, not one that retrains weights.

The outcome is stored response instructions that will be applied in subsequent conversations. 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 materials that could not be accessed or tasks that could not be executed.

Verification: After modifying the rules, check whether they are reflected in new conversations and how requests that conflict with existing rules are handled. Clearly show the input and actual output used for verification, and distinguish any items that have not yet been confirmed.