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 Moves, Gathers, and Builds According to Goals in Minecraft

This is an example where a model reads the state of Minecraft and selects action tools to move, gather resources, and achieve building goals.

How it works

  1. Connect Mindcraft and Mineflayer to a test game server, and set up the model account and goals.
  2. The LLM calls Mineflayer action tools based on the game state to perform goals such as resource gathering, movement, and building.

Results

In the public example, the intended outcome is a game bot that acts according to the given goals.

Notes

This is an open-source implementation example. The author did not run it on an actual game server or measure its success rate.

Source

Mindcraft 공개 저장소 Original post ↗

Example prompt · Mindcraft

Goal: Assign goals in Minecraft and have actions carried out.

Input/Environment: [Test game server], [Model connection], [Bot setup], [Execution goals].

Reference original: https://github.com/mindcraft-bots/mindcraft

Prepare the setup and connections so that you can create a test environment using the public configuration from the original source. If there are any missing sub-workflows, APIs, or account permissions, mark them as incomplete until actual connection is made.

Connections and materials to prepare: Connect Mindcraft and Mineflayer to a test game server, and set up the model account and goals.

Agent behavior to implement: The LLM calls Mineflayer action tools based on the game state to perform goals such as resource gathering, movement, and building.

Scope of operation: This is an open-source implementation example. It has not been run on an actual game server or had its success rate measured.

The outcome is a game bot that acts according to the goals. 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 data that could not be accessed or tasks that could not be executed.

Verification: Test situations where the path is blocked or materials are missing, and compare with the game state to ensure failed actions are not reported as successful. Show the input used for verification, the actual output, and clearly distinguish any items that have not yet been confirmed.