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

Marketing & DesignWalkthrough

Agent Drafts a New Post in the Same Tone by Searching the Author's Previous Posts

This is an example where an agent searches the author's past posts, uses related examples and tone as references, and drafts a new post.

n8n

How it works

  1. The user saves previous posts in Supabase as searchable data and provides the topic for the new post.
  2. The writing agent calls the Supabase search tool where the past posts are stored, retrieves relevant examples, and reflects them in the new draft.

Results

In the public example, the intended outcome is a draft of a new post that references the tone of existing posts.

Notes

This is a personalized retrieval-type agent. It is not a case of reinforcement learning that retrains the model or automatically improves with real feedback. The author reports that public settings and tool connections were checked, but the process was not executed directly.

Source

n8n 공개 워크플로 #10672 Original post ↗

Example prompt · n8n

Goal: Search your previous posts and write a new post in a matching tone.

Input & Environment: [Your previous posts], [Supabase connection], [New topic], [Posting channel].

Reference original: https://n8n.io/workflows/10672

Set up the configuration and connections so that a test environment can be created with the public setup 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: Save previous posts in Supabase as searchable data and provide the topic for the new post.

Agent behavior to implement: The writing agent calls the Supabase search tool where the past posts are stored, retrieves relevant examples, and reflects them in the new draft.

Scope of operation: This is a personalized retrieval-type agent. It is not a case of reinforcement learning that retrains the model or automatically improves with real feedback.

The result is a draft of a new post that references the tone of existing posts. Please also organize the necessary setup steps and actual execution methods. After checking the results returned by the tool, choose the next action, and separately note any data that could not be accessed or tasks that could not be executed.

Verification: Check whether the retrieved examples are relevant to the topic, and do not transfer the date or experiences of old posts as if they are new facts. Clearly distinguish the inputs used for verification, the actual outputs, and any items not yet confirmed.