Self-checking AI: A trustworthy knowledge assistant for the energy sector with 90% user satisfaction

A man and a woman, both wearing safety helmets and high-visibility vests, are standing side by side in front of wind turbines, while a glowing AI chatbot icon and speech bubbles appear overlaid on the image | AI Chatbot SUNZINET

The Project

Overcoming information silos

Our customer, a major player in the energy sector, manages a vast, international customer base. Since energy and gas utilities are complicated services, there is a lot of pressure on customer-facing teams, including call centres, sales representatives, contract management, and claims departments. These teams are responsible for handling thousands of inquiries, contracts, and claims every month, all while lacking a centralized, single source of truth. 

All the employees especially the Service teams, relied on scattered, inconsistent sources to find the information they need, leading to:

Longer response times
❌ Increased workload

❌ Potential revenue loss

So, the customer contacted our AI Experts, to resolve these challenges.

A diagram showing the interconnected benefits of an AI system | AI Chatbot SUNZINET

The Goal of the Project

Smarter knowledge management with AI

The project aimed to create a Proof of Concept (PoC) version of an
AI assistant that would centralize knowledge and make it readily accessible.

Implementing the full version of this solution would increase productivity, enhance decision-making, and improve the overall customer experience, all while ensuring accuracy and security in information management.

The Key goals included:  

  • Provide instant and reliable access to critical knowledge – reducing reliance on scattered documents and colleagues for information retrieval.
  • Improve customer service efficiency – enabling first-line teams to resolve more inquiries independently, reducing escalations and handling times.
  • Minimize errors in contract verification and documentation – reducing rejected contracts and revenue loss due to incorrect paperwork.
A diagram illustrating the benefits of supporting AI adoption | AI Chatbot SUNZINET
  • Standardize knowledge sharing across departments – replacing informal processes with a structured, AI-driven knowledge base integrated into existing systems.
  • Accelerate onboarding and training – ensuring new employees can quickly access accurate information and minimize the need for 1:1 coaching
  • Support AI adoption and future scalability – lay the foundation for expanding AI support to both employees and customers over time. 

Key inefficiencies that our AI knowledge Management Solution Solved

 

Icon representing data segmentation, featuring a circular chart with divided sections | AI Chatbot SUNZINETKnowledge silos

Critical information is stored across USYS (ERP/CRM system), SharePoint, MS Teams, and Outlook emails, making searchability difficult. 

Icon representing expertise and education, featuring a presentation board with a graduation cap | AI Chatbot SUNZINETReliance on individual expertise

Employees frequently ask colleagues for answers instead of retrieving information from a structured database. This is particularly inefficient in remote work setups. 

Icon representing onboarding and team collaboration, featuring three people connected by curved lines | AI Chatbot SUNZINETHigh onboarding volume

With an annual turnover rate of 20-35% in the call centre, maintaining knowledge consistency and training new employees efficiently requires significant resources. 

Icon representing documentation, featuring a paper scroll with a pen symbol | AI Chatbot SUNZINET Documentation inconsistencies

Different teams maintain knowledge separately, resulting in errors, delays, and miscommunication between departments.

Strategy & Implementation

To ensure a successful deployment of the AI-powered knowledge assistant, SUNZINET followed a structured approach that combined a Proof of Concept (PoC), iterative testing, and rigorous evaluation metrics. 

  • A group of three colleagues is having a discussion in a meeting room, with a whiteboard full of notes in the background | AI Chatbot SUNZINET

    SUNZINET and the client collaboratively developed a PoC within a selected department to refine the AI knowledge assistant before scaling.

    • Building the knowledge base: A test database with 100 curated Q&A pairs was structured into multiple segments: B2B vs. B2C; Frontline vs. Second-line teams (simple vs. detailed documents); Department-specific repositories.
    • Defining success metrics: Accuracy, usability, and efficiency thresholds were set with the client.
    • Cloud setup: The AI assistant was deployed in Azure OpenAI Service, ensuring security, compliance, and scalability.
  • A man and a woman are engaged in a conversation at a high table in a modern office setting | AI Chatbot SUNZINET
    • Selecting the AI model: Various Language Models were evaluated for accuracy, efficiency, and cost-effectiveness. 
    • Designing the query process: The AI assistant was optimized using a chain of prompts to ensure it interprets, processes, and retrieves relevant knowledge efficiently. 
    • Prompt engineering & response formatting: Commands were optimized to generate structured, easy-to-read responses tailored to real-world usage. 
  • Three men are sitting together on a sofa, looking at a laptop screen | AI Chatbot SUNZINET
    • Document structuring: Large documents were split into searchable segments.
    • Metadata enhancement: Documents were enriched with metadata for better indexing and retrieval. 
    • Database configuration: A vector database was implemented to enable semantic search capabilities, improving response relevance. 
    • Optimized retrieval: AI pulls the most relevant information efficiently.
  • A man is standing at a table, leaning slightly forward while working on a laptop | AI Chatbot SUNZINET
    • Test script execution: The AI assistant was tested against a scripted set of real-world questions.
    • Dual-layer evaluation:

    1. AI self-assessment on response accuracy.
    2. Human review of AI-generated answers.
  • A man and a woman are having a conversation in an office setting | AI Chatbot SUNZINET
    • User interface: Designed for easy employee interaction.
    • Feedback loop: Sales and service teams tested AI, refining accuracy.
    • Final report: Summarized AI performance, key learnings, and next steps for scaling.
A group of three colleagues is having a discussion in a meeting room, with a whiteboard full of notes in the background | AI Chatbot SUNZINET
A man and a woman are engaged in a conversation at a high table in a modern office setting | AI Chatbot SUNZINET
Three men are sitting together on a sofa, looking at a laptop screen | AI Chatbot SUNZINET
A man is standing at a table, leaning slightly forward while working on a laptop | AI Chatbot SUNZINET
A man and a woman are having a conversation in an office setting | AI Chatbot SUNZINET

Results & Impact

AI knowledge Management Chatbot - A Game changer for Service Teams

We deployed the PoC of the AI assistant successfully with the following functionalities:

  • An AI-powered chatbot that intelligently searches a knowledge base and delivers accurate answers. It was tested with predefined questions to ensure reliability before deployment.
  • Structured knowledge base managed by SUNZINET, ensuring it contains relevant, curated information for accurate responses. The data was preloaded before deployment, so the chatbot could provide instant answers without needing live data input.
  • User authentication system that controls who can access the AI assistant. Access permissions are managed to ensure that different users (e.g., support agents, managers) can only view or modify information based on their roles.

Value for the Customer

Key Performance Metrics

 

  • User satisfaction rate: Over 90% of testers said they like to use the tool in their daily work.
  • Incorrect answer rate: ~8%, with almost all incorrect responses flagged by the AI’s self-check.
  • Misleading answer rate: <1%, ensuring high reliability.

 

Project Highlight: Trust & Accuracy

 

The AI assistant’s ability to self-evaluate its responses sets this project apart. By verifying its own accuracy, and prompting for clarifications when uncertain, the tool increased user confidence, making it a highly trusted resource for employees.

This high-quality AI response system, combined with structured knowledge access, resulted in a successful PoC with strong adoption potential for full-scale implementation.

This trailblazing project underscores the AI assistant’s potential to enhance service efficiency, streamline knowledge management, and drive smarter decision-making across the organization.

Ready to optimize your knowledge management with AI?

Simply fill in the form to arrange an initial, no-obligation meeting and we will get back to you within 24 hours on working days.

In this first meeting, we will talk about your challenges and goals and suggest possible next steps!

Florian-von-Waldthausen-570x570 1

Florian von Waldthausen

Business Development

waldthausen.florian@sunzinet.com

+49 221 / 355 009 0