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 Checks Existing UI Project and Creates a Screen Based on Request

The agent, after receiving a design request, checks the Stitch project and existing screens, then creates a new screen.

n8n

How it works

  1. Set up the connection to Google Stitch tools and provide the project to use or the requirements for the new screen.
  2. After reviewing the existing project and screens, run the tool to create a new project or screen according to the request.

Results

In the public example, the intended outcome is a screen created within the selected project.

Notes

This is a design implementation example using Google Stitch MCP. It is different from simply generating image prompts. The author reports that public settings and tool connections were checked, but the process was not executed directly.

Source

n8n 공개 워크플로 #13269 Original post ↗

Example prompt · n8n

Goal: Find a UI project through conversation and create a new screen.

Input/Environment: [Stitch connection], [project], [screen requirements], [device size].

Reference original: https://n8n.io/workflows/13269

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 materials to prepare: Set up the connection to Google Stitch tools and provide the project to use or the requirements for the new screen.

Agent actions to implement: After reviewing the existing project and screens, run the tool to create a new project or screen according to the request.

Scope of actions: This is a design implementation example using Google Stitch MCP. It is different from simply generating image prompts.

The result is a screen created in the selected project. Please also organize the necessary setup steps and actual execution methods. 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: Check that the wrong project is not selected, that the created screen can be reopened, and that the requested inputs and buttons are included. Clearly distinguish the inputs used for verification, the actual outputs, and any items that have not yet been confirmed.