in our first post, we talked about the problem. Supply chains are slow. Parts ship across the world. Weeks pass. Carbon burns. Sometimes the manufacturer doesn’t even exist anymore.
We asked: what if supply chain worked like Minecraft?
Now let’s show you what we mean. (no, its not the same picture)
Think about how Steve plays Minecraft.
Steve needs a diamond sword. He doesn’t call a supplier in another country. He doesn’t wait for a ship. He finds the recipe, gathers materials, walks to his crafting table, and makes it. If he needs something far away, he uses a portal – instant.
Now think about CraftPortal.
A customer needs a part. Instead of ordering and waiting for shipping, they log into the Portal and post a request: “I need this part, these specs.”
IP Owners see the request. We call them Wandering Traders. They don’t ship physical parts – they sell recipes. Digital blueprints. They bid on the request.
Customer picks a recipe. Downloads it through the portal. Instant – like Steve stepping through a Nether portal.
Now the customer has two options:
Option 1: They have their own 3D printer – their Crafting Table. They print the part locally. Done in hours.
Option 2: They can’t print it themselves. They order from a Manufacturer – a Villager with better equipment. The Villager crafts it for them from a local facility.
Either way: recipe travels through the portal, part gets made locally.
No ships. No planes. No weeks. No carbon.
The Tech Behind It
The Portal is Power Pages – the marketplace. Recipes live in Dataverse. Copilot and AI Builder handle automation and intelligence. Azure IoT connects the Crafting Tables. Model Driven App runs the back office. Teams keeps everyone talking.
And LogiQraft? We’re the Redstone Engineers. We build the wiring that makes it all work.
Hello Blog! We are so happy to be a part of this year’s ACDC Hackathon!
Sooo, on to our Early Delivery:
Our goal is to bring the Minecraft Fun to the physical world and get the players up on their feet, explore and mine(trying to help all hackers avoid health issues).
The miner finds a spawn point within the building, where they can scan and mine the resource, whoops if it is an actual resource.
We will have an information screen/dashboard where players can get an overview over the current statistics and where to find the resources. This will also include how much they have mined, and see if they are close to getting the prize.
To get valuable and quirky information about the data, we will use AI and this will be shown on our dashboard application. The dashboard will also contain lists, graphs and other information that will be valuable to the miners, and administrators of the realm.
Why This is not just for fun, this is to show how we can use data, AI, web applications and Power Platform to solve real world business problems, create real value and learn from each other.
We are using AI as a tool to develop with Warp, chatGPT, Claude, Vibe.powerapps.com aswell as a part of the product itself.
We building an intelligent, cloud backed in-game experience, the idea is simple: bring logic, AI, and data directly into the game, where players and admins interact with it in real time.
We’re implementing a custom minigame experience inside the game, with its own logic layer. This includes:
– Points and in-game currency
– Rewards and progression
– Player state and session tracking
Instead of hardcoding everything, the game logic is designed to be data driven, allowing us to evolve rules and mechanics without redeploying the game itself.
One of the key features is a game admin role. An admin can make live changes to an ongoing game session, such as:
Switching between day and night
Assigning weapons, items, or points to specific players
Influencing the session dynamically without restarting it
Communication between players, the game, and AI agents is handled using a Bot Framework skill.
We’re using Dataverse as our primary database for:
Game sessions
Player profiles
Points, currency, and rewards
Admin actions and game state
All in-game telemetry is streamed to a data lake. This includes events such as:
Player deaths and kills
Building actions
Monster spawns and movement
Environmental changes
The goal is to capture everything that happens in the game, at scale, without impacting gameplay performance.
We’re using it in three main scenario where AI is going to play a role:
Game Helper Bot:
Players can interact with a game helper bot through chat. Examples:
“Build a fortress”
“Build a wall around me”
“Create a safe zone”
The agent translates these requests into Minecraft commands that can be executed directly in the game, taking into account:
The player’s available points or currency
Game rules and constraints
Current game state
Player Prompt Improver
Players don’t always write perfect prompts that is why we use an LLM as a prompt improver, which:
Takes short or vague player input
Expands and adapts it to the game context
Produces a richer, more precise prompt for the helper bot
Data Insights Agent
Finally, we’re building a data insights agent on top of the telemetry stored in the data lake.
A part breaks. You need a replacement. The manufacturer is on the other side of the world. Traditional supply chain kicks in: order placed, part produced or pulled from stock, shipped across continents, customs cleared, finally delivered. Sometimes – the wrong part. Start over.
Weeks pass. Operations suffer. Carbon burns.
Or worse – the manufacturer went out of business ten years ago. No stock. No supplier. No solution. The machine stays broken.
This is modern supply chain. Global, fragile, slow.
The Inspiration
In Minecraft, Steve doesn’t wait for delivery. He finds what he needs, crafts locally, moves on. Instant. Simple.
What if real-world supply chain could learn something from this?
The Vision: CraftPortal
A portal. Vendors. Manufacturers. Customers. A Crafting Table.
Connected in a way that might just change how we think about getting parts from A to B.
The Tech
Built on Microsoft cloud: Power Platform, Azure, Copilot Agents, IoT, AI.
Hello fellow Steves, Crafters, Endermen, and Creepers 🧱⛏️We are the Cepheo Crafting Creepers
Today, we kick off ACDC 2026, and what a craftable treat we have in store for you.
We’d like to share the early delivery of this years project: an end-to-end integration between enterprise production planning and Minecraft… with automatic resource gathering.
The idea is simple and lazy, but also business applicable:
What if a production order in Dynamics 365 Finance & Operations didn’t just sit in a system and have to be given out to a worker, but was executed by an AI-controlled NPC inside a Minecraft world? Gathering materials and equipment to fulfill the task. This means you could have a robot mine and gather materials in dangerous places, while you focus on sipping your mushroom stew and enjoying a few buckets of milk as our AI friend does the work.
With the Early Delivery Creeper approaching fast, and this rookie blogger-graduate having to hurry and mine out the two early badges and showcase our idea for this year’s ACDC, we focused on proving the full flow from D365, Power Platform, ERP to game and back again into a nicely interactive Power BI report. Below is how it works.
🧱The System Crafting Table
Our solution revolves around treating Minecraft as a visual execution layer for real production logic.
Here’s the end-to-end idea:
Production Order Creation
A production order is created using Power Platform and Dynamics 365 Finance & Operations. The order contains a Bill of Materials (BOM) describing what needs to be produced.
Bill of Materials → Minecraft Tasks
The BOM is read and translated into Minecraft equivalents:
Raw materials → blocks and items
Quantities → resource counts
Operations → NPC task steps
We are creating our own Minecraft server using the Java engine, where we can send data to and from Azure and format it into FO.
NPC Worker Execution
An AI-controlled NPC worker is spawned in the Minecraft world. Based on the translated task list, the NPC:
Mines required resources
Harvests or gathers materials
Crafts the required items
Deposits finished goods into a chest
Status Back to ERP
Once the required items are completed and deposited, completion status is sent back to Dynamics 365, where the production order can be updated or closed.
And we can fully Power BI report what has been gathered, the time spent, total deaths?
We will host the server on a Raspberry Pi
🏁 Why We Deserve the Early Delivery Badge
This delivery qualifies for the Early Delivery badge because we have already defined and demonstrated the complete end-to-end solution, even though some components are still being implemented or refined.
🖼️ Architecture Overview (#ShowAndTell)
This sketch represents our Show And Tell artifact and documents the complete solution flow.
🚧 What’s Next
With the end-to-end flow established, the next phase focuses on turning the concept into a more concrete and observable system.
The upcoming steps include:
Setting up the Raspberry Pi Preparing the device to act as a physical integration point and control interface for parts of the solution.
Sending data through Azure with our Java Minecraft Server Routing data to and from Microsoft Azure, acting as the integration backbone between Minecraft, the Raspberry Pi, and Dynamics 365 Finance & Operations.
Integrating Finance & Operations Establishing reliable communication for reading production orders and writing back execution status.
Configuring and understanding our little AI villager friend Improving how the NPC interprets tasks, executes them, and reports progress in a predictable and inspectable way.
Creating links to Power Apps and Power BI visualizations Exposing production data and execution status through Power Apps and dashboards, enabling easy interaction and monitoring outside the Minecraft world.
Until next time, mine away and don’t get lost in a cave.
In Minecraft, you run around and gather resources while exploring biomes and identifying the best locations for valuable materials. Unfortunately, this does not directly translate to the real world. In real life, there are a couple of possible difficulties like competitors, property rights, laws and even locating and gathering these resources are not as straightforward.
Our solution will be targeted towards companies that have a need for geological- and geographical data, typically working in sectors of real estate development, agriculture, mining, demolition and public infrastructure. We want to gather this information, process it and deliver resource knowledge to our customers to help them improve their business by using useful geodata and gain an advantage on their competitors:
Reduced decision risk through standardized environmental data analysis
Lower operational cost by automating data collection and interpretation
Higher data accessibility across technical and non‑technical roles
Improved sustainability planning through better understanding of natural conditions
Faster project start‑up using ready‑to‑use geological insights
Technical overview
Geodata in Fabric
In Norway you can find a lot of geological- and geographical data as datasets on Geonorge, provided by a wide variation of suppliers like Norwegian Institute of Bioeconomy Research (NIBIO) or Norway’s national geological survey (NGU). We are planning to gather this data and storing it in Fabric using Lakehouse, allowing us to process it and synchronize it with Dataverse.
Customer solutions in the Power platform
Once the geodata is stored in Fabric and Dataverse, we plan to use the Power platform to connect to the data and develop products for our customers. The idea is to use the applications in the platform to create a variety of functional mini-solutions that will be part of the main solution:
Power BI for visualizations, statistics and dashboards
Power Automate for automatization, data updates and triggering of alerts and other functions
Power Apps for end‑user interface to explore data or submitting information to retrieve information the customers have a need for
Copilot Studio to provide an AI‑powered conversational agent that can help customers with questions or generate text for reports regarding their requests.
Coordination in Teams
As data is stored and processed and the solutions within the Power platform is in place, we still need to communicate with our customers. For this, Teams will be our go-to solution as it allows us to provide them with an interface for the solutions in the Power platform, as well as a all-in-one solution for coordination.
End‑users interact with dashboards, insights and Copilot directly inside Teams
Field workers and analysts can communicate through integrated chats and channels
Administrators manage datasets, permissions and support requests
AI‑powered agents assist both employees and customers
Conclusion
We want to create a solution that helps bring the resource gathering experience in the real world closer to the simplicity of Minecraft by transforming how organizations discover, analyze and leverage geological and geographical data. The core of the solution we plan to create will be made using Microsoft cloud, with a special focus on the low-code possibilities this provides. Our end goal is to provide our customers with the knowledge to improve their business and gain an advantage on their competitors.
Here we seize the means of production, then we remove the human from the loop and automate it for the glory of the village.
We are building the complete five year plan in one Minecraft world. Orders. Production. Harvesting. Reporting. Customer wants bread. Gosplan approves. Factories run. Farms deliver. Dashboards illuminate.
And we do not farm by hand. There is no starving intern with a hoe in this republic. We deploy AI villager agents. Tireless. Obedient. Unblinking. Like Village Golem Pyotr.
They navigate the fields and harvest our sacred crops: wheat, potatoes, and beets. Always at quota.
We capture telemetry from every block and turn it into analytics and insight agents.
Why are we behind on wheat. Immediate answer. Who caused it. Immediate answer. Which lever to pull to restore the plan. Immediate answer.
Powered by SharePoint Framework, Microsoft Graph, and Power Pages, delivered as glorious dashboards for the committee.
CCCP. Seize the means of production, then publish them in Power Pages.
This document describes an end-to-end building permit process, from planning to decision, for a Minecraft server. The applications concern what players are allowed to build in the Minecraft world (multiplayer), and the solution is designed to handle submission, case handling, AI-based assessment, and formal decisions in a structured and traceable manner.
The solution is built on the Microsoft Power Platform, Dynamics 365, Copilot Studio, Microsoft Foundry, and Microsoft Fabric. Dataverse serves as the shared data foundation and single source of truth.
Problem Statement
On a Minecraft server with no rules, no zoning maps, and no building permit process, a player finally found the perfect place to build a cozy cabin: a bit of a view, some forest, far enough from spawn, and just the right amount of “wow.” He marked the area mentally, told himself “this will be home,” and logged off for five minutes to get coffee.
When he logged back in, the plot was gone. Not because someone stole it—but because someone had built a FULL volcano there, complete with lava, smoke, a giant “WELCOME” sign, and a small obsidian temple on top.
The player was left standing with a bucket of water, a dream in flames, and the sudden realization: without rules, process, and traceability, “planning” is just a suggestion.
What We Want to Demonstrate
We want to demonstrate that it is possible to make building permit processing faster, more predictable, and more traceable—without losing control.
Enderdogs will demonstrate a coherent, end-to-end process:
Area Planning
Application
Case Handling
Decision
Area Planning with Minecraft Zones and Rules
The area plan establishes the framework for building in the Minecraft world through zoning and rule sets, for example:
protected zones such as spawn areas, villages, temples, portals, or rare biomes
designated building areas for private constructions or shared projects
special rules such as maximum height, maximum footprint, distance to paths or rivers, or material requirements
Players may apply for plan changes by modifying zones or rule sets, or submit building applications within the current regulatory framework.
Application and Decision
When a building application is submitted, the following steps are executed:
application submitted via Power Pages
application data stored in Dataverse
case handling performed in Dynamics 365 Customer Service
AI used to validate requirements, documentation, and rules, as well as to perform risk assessment
a formal decision is issued with justification and full traceability, approved or rejected
Technical Overview
Main Components of the Solution
Power Pages for application submission
Dataverse as the data platform and single source of truth
Dynamics 365 Customer Service for case management
Power Automate for workflow and automation
Copilot Studio for conversational support and guidance
Microsoft Foundry Agents for multi-agent evaluation and research
Microsoft Fabric and Power BI for insights and reporting
Data Model
The data model is designed for traceability and extensibility.
Core Tables in Dataverse
Data Model (Dataverse) – High-Level Overview
Planning and Map Data
adv_AreaPlan Area plan for the Minecraft world (framework, zoning, and rules)
adv_Property Property/area on the map (Gnr/Bnr or plot), linked to AreaPlan and coordinates
Application
adv_BuildApplication Building application submitted via Power Pages (building type, description, bounding box, status, applicant)
Requirements and Processing
adv_ApplicationRequirement Requirement checklist for the application (documentation, rules, distances, etc.)
adv_ReviewStep Case processing steps and status per step (received, validation, assessment, decision)
Actors
Account / Contact (standard Dataverse) Used for players, server administrators, and optional moderators, including communication
Actors
Actors are modeled as accounts in Dataverse:
server administration
player / applicant
optional moderator role for role separation and responsibility
Each account may have multiple contacts, with a primary contact for communication.
AI Support and Multi-Agent Assessment
The solution utilizes two AI layers with clearly defined responsibilities.
Copilot Studio
Copilot Studio is used for dialogue and operational support:
portal agent for guidance during submission and completeness checks
case handler support for summarization, checklist suggestions, and draft text generation
Microsoft Foundry Agents – Multi-Agent Evaluation
Microsoft Foundry Agents are used for structured evaluation of building applications. The agents operate as a team with specialized roles and deliver a consolidated decision basis.
Example Agent Roles:
rules agent – evaluates compliance with zoning and building regulations
placement and conflict agent – evaluates coordinates, distances, and conflicts with protected zones
documentation agent – evaluates attachments, completeness, and consistency
risk agent – evaluates deviations and factors requiring manual review
decision agent – consolidates findings and produces a recommended decision with justification
Decision Types and Control Levels
The solution demonstrates three control levels:
low risk: automatic decision with logged and traceable justification
medium risk: AI recommends a decision; human decision-maker issues the final decision
high risk: case is flagged and routed for manual handling
This is governed by policy, for example a risk score combined with fixed rules that always require human review.
Power Automate Flows
Automation binds the process together:
submission creates a case and requirement checklist
multi-agent workflow starts and writes recommendations back to Dataverse
low-risk cases may be automatically decided and logged
other cases are routed to a case handler with a complete decision basis
notifications are sent for missing information and status changes
Analysis and Insights
Microsoft Fabric and Power BI are used for reporting and management insights, such as:
number of submitted cases
share automatically approved
share flagged for manual handling
most common reasons for rejection
processing time per step
Appendix A – Solution Illustration
The illustration below shows the full lifecycle of the solution: area planning, political processing, neighbor notification, and decision.
Appendix B – Area and Zoning Map
The map below shows the area plan used in the POC. The area consists of multiple land and plot numbers (Gnr/Bnr) included in a shared area plan. The map forms the geographical foundation for zoning, neighbor notification, building applications, and visualization in Minecraft.
Legend:
each color represents one property (adv_Property)
the area is part of one area plan (adv_AreaPlan)
purple areas represent proposed plots for leisure housing
the map is used to determine neighbors, affected parties, and planning status
Link to Data Model and Process
each property in the map is created as an adv_Property record in Dataverse
when a property applies for rezoning or construction, neighbors are automatically identified
When planning HogWorkplace, we initially didn’t know what it should look like. To get a clearer idea, we decided to sketch it by hand. Our goal was to create an intranet on a SharePoint site for both Hogwarts and the other house common rooms. We wanted to incorporate AI and CoPilot Studio, which led us to develop DobbAI. DobbAI is available on all SharePoint sites within HogWorkplace.
We aim to create a PowerApp that visualizes Hogwarts and the Hogwarts Express, making it clickable to navigate to different features on the SharePoint site. We sketched these drawings and pictures to visualize our thinking.
Hogwarts: The main SharePoint site, showcasing Hogwarts, the Hogwarts Express, and DobbAI.
Visual Design: A more detailed design of the castle, DobbAI, and the train.
Features: Showcasing the rest of the features on the Hogwarts SharePoint site, including a button to find your common room, conversation posts from Viva Engage, and a Hogwarts Academic Calendar that displays the yearly calendar. Clicking on an element in the calendar provides additional information.
DobbAI Interaction: Demonstrating how DobbAI will look once you interact with it. It’s a chatbot where DobbAI answers your questions based on its knowledge. We’ve integrated all the SharePoint sites, documents, lists, etc., of HogWorkplace into its knowledge base. You will only receive answers and access to information that your signed-up user has permission to read, ensuring no sensitive data is shared. When you get an answer, you also receive the source of the information and, in some cases, a navigation link to the relevant location if it suits the prompted question.
