Factory Copilot AI Chatbot for Smart Manufacturing

Akveo integrated an AI-powered chatbot into the Factory Intelligence platform, enabling operators to query real-time telemetry data and production KPIs through natural language.

Automation

Germany

5 months

AI Development

Web Development

[ Client ]

About the Client

Our client is one of the largest consulting firms. Their proprietary SaaS product, the Factory Intelligence Platform, helps manufacturers digitize operations and automate business processes. The platform analyzes real-time telemetry data directly from plant-level devices to deliver end-to-end data transparency and unlock actionable insights for manufacturing teams.

50%

Faster Data Retrieval

5mo

Project Timeline

3

Core AI Capabilities Built

[ Challenge ]

Locked Data and High IT Dependency

Plant managers and floor operators faced severe bottlenecks when trying to access actionable manufacturing insights.

While operational data was continuously generated across the plant, retrieving it was difficult because critical information was fragmented across disconnected systems, SQL databases, REST APIs, and thousands of PDFs.

To get an answer, users had to manually navigate complex dashboards or file a report ticket with IT and wait for a response.

The Factory Copilot AI assistant had to meet several strict requirements:

Real-time retrieval and user experience. The goal was to develop a solution capable of real-time data retrieval delivered through an intuitive Angular-based UI. It was expected to streamline KPI analysis, production order tracking, device configuration help, and machine status monitoring.
Natural language processing. We needed to build a chatbot that would enable natural language queries across SQL databases, PDF documents, REST APIs, and SAP systems simultaneously.
Security and scalability. It was critical to implement role-based security and encryption, paired with an architecture built to scale for large-scale industrial deployments.

[ Solution ]

Building the Solution

Following the provided requirements, Akveo developed Factory Copilot, an AI-powered chatbot seamlessly integrated into the Factory Intelligence platform.

Leveraging Azure OpenAI's GPT-4, Semantic Kernel, and Azure AI Search, Factory Copilot acts as a conversational layer over the platform's central orchestrator. As a result, it enables manufacturing teams to instantly access key production insights, sensor data, and documentation in plain English.

The solution is equipped with the following features:

Real-time KPI analysis. Operators can ask natural-language questions like "What was the KPI for machine Y last week?" to pull metrics generated by Azure IoT Hub streams and embedded Power BI analytics.
Role-based security. It ensures that users can only retrieve data and reports aligned with their specific permissions and roles.
Production order tracking. The chatbot can retrieve recent production orders and monitor activity across interconnected process chains.
Device configuration assistance. Users can request setup guidance for specific equipment. The answers are pulled directly from equipment manuals and technical PDFs.
Machine status and predictive maintenance monitoring. The predictive maintenance algorithm can detect a problem and suggest early maintenance. Thanks to this, operators can always check device conditions and alerts in real time.
Data integration across sources. Factory Copilot interacts simultaneously with SQL databases, PDF documents, Azure IoT Hub telemetry pipelines, embedded Power BI reports, and REST APIs to deliver comprehensive responses directly inside the UI application. Apart from this, the solution is also connected to SAP, which means that it also has access to the ERP data.

Microservice Architecture

The Factory Intelligence platform is built on a modular microservice architecture. This approach helps ensure high performance and scalability.

Independent services handle distinct platform tasks and communicate through an Azure Service Bus event system. When an event (such as a new machine alert) occurs, multiple services can listen and react instantly without slowing down or blocking each other.

The table below contains a short overview of the platform's services.

Service	Key Function
UI Service	Frontend application
API Service	Core backend logic
Admin Service	Users, permissions, and settings
Activity Service	Event tracking and message bus
Detection Service	AI fault detection (Cognitive Services)
Simulation Service	IoT telemetry simulator
Socket Service	Live WebSocket updates to browser
Maintenance Service	Maintenance scheduling and task routing
Power App and Proceedix execution provider	Third-party maintenance integrations
Sync Service	Scheduled SQL-to-MongoDB downtime sync

All services reference a centralized MongoDB database. As a result, plant data remains consistent and immediately available across the entire system.

Technical Implementation

Factory Copilot is designed to handle highly complex data tasks while keeping the user experience simple. To make this possible, we implemented the following technical solutions:

We indexed the plant's specific industrial vocabulary (alert rules, signal metadata, and equipment hierarchies) inside Azure Search. The bot resolves these exact terms first to ensure accuracy before running any backend API queries. This prevents hallucinated or misrouted queries.
Our team built a tool engine based on a Directed Acyclic Graph (DAG). It automatically plots the most logical path for pulling and aggregating data from multiple fragmented sources at the same time.
The platform allows users to manage and query plant documentation, telemetry, alert statistics, and embedded Power BI datasets through a chat agent. If an operator submits an ambiguous request or references a vague machine name, the bot initiates a built-in clarification flow to verify exactly what they need before processing the query.
We also created a dynamic visual presentation layer. It evaluates the incoming data payload and dynamically selects the best chart or visual format to display to the plant operator.
The chatbot is powered by role-based security and encryption. It integrates with the platform's user permissions and roles to ensure that operators only access data and analytics they are authorized to see.

[ Results ]

Impact that Matters

Factory Copilot significantly improved manufacturing operational efficiency across the shop floor. It gives operators and plant managers instant access to real-time telemetry, alert statistics, configuration manuals, and Power BI production datasets. As a result, it eliminates traditional data bottlenecks without requiring IT involvement.

Unified cross-silo data access

The assistant breaks down corporate data silos by simultaneously querying SQL databases, PDF documents, live REST APIs, and SAP ERP systems through a natural-language interface.

50% faster data retrieval

Operators and managers get instant answers in seconds instead of minutes, which cuts search time in half and removes manual navigation across multiple dashboards.