Skip to content
English
Contact us
  • There are no suggestions because the search field is empty.

Overview zapAgent Team Wickie + Wilma

Introduction to the Agent Team Wickie + Wilma

1. General Introduction

The Agent Team Wickie + Wilma combines two specialized agents to support SAP data analysis from data extraction to business-oriented interpretation of results.
 
Wickie extracts SAP data via RFC, prepares it in a structured format, and performs data processing and preparation steps required for further analysis. Depending on the selected Content Bundle, these analyses can be executed as one-off or continuous runs. Wickie may also use controlled external data access where required for specific analysis steps (such as VAT ID verification). All data processing takes place within zapAnalytics.
 
Wilma builds on Wickie’s results and supports users in analyzing and interpreting findings within their business context. Using a LibreChat interface, users can explore results, ask follow-up questions, and generate insights based on predefined prompts and analytical tools.
 
Both agents operate exclusively within your locally installed zapHome instance. A prerequisite for using Team Wickie + Wilma is the technical setup of zapHome OnPrem AI Search.
 
This article provides an overview of how to work with the agent team and links to relevant setup and solution-specific content.

1.1 Project Workflow

This article outlines the structured project process used at zapliance. Each phase is clearly defined to ensure a consistent, efficient and successful project execution.
 
The described workflow provides a guidance, clarifies responsibilities and ensures allignment across all stakeholders throughout the project lifecycle.
 
The project workflow applies to the following zapliance solutions:
  • Digital Audit Preparation
  • Finance Benchmarking
  • ICS Assessment
  • Cash Recovery AI

Detailed information on the project workflow can be found here:                                                                      Project Workflow for Digital Audit Preparation, Finance Benchmarking and ICS Assessment            Project Workflow for Cash Recovery AI

 

2. Technical Onboarding

The technical foundation for this agent team is zapHome OnPrem AI Search. It is deployed via Docker on a Linux-based virtual machine or server. zapHome OnPrem AI Search provides a framework for:
  • Local execution of all agents within your IT environment
  • Full data privacy (no external data access, no SaaS applications)
  • SAP data analysis and seamless integration with your Azure OpenAI Services, including targeted web search capabilities for data validation

The following article provides an overview of the platform and includes links to all relevant technical topics, such as VM/server setup: General Setup zapHome OnPrem AI Search

 

3. Functional Onboarding

This section shows how the agent team supports your day-to-day work - from data extraction to analyzing and interpreting results.
 
 

3.1 Project Setup (Depending on Content Bundle)

The specific project setup is defined according to the selected Content Bundle. Key organizational aspects include: 
  • Objective: What is the goal of the project?
  • Data Scope: Which data needs to be analyzed (SAP client, company codes, fiscal years) and what analysis should be performed?
  • Timeline: What are the start and end dates of the project, and which milestones are planned?
  • User Access: Who needs access to which tools?
    • zapAnalytics
    • Power BI
    • LibreChat
 

3.2 Data Extraction and Analysis

Wickie performs the core analysis in zapAnalytics. Key steps:
  • User uploads Content Bundles that define extraction scope, analysis logic and result formats
  • Wickie executes data extraction and performs analysis 
See: zapAnalytics User Guides
See: Content Bundles
 
 

3.3 Analysis Results

Once Wickie has completed data processing, the results can be utilized in two ways: via structured Power BI dashboards for visual analysis, and through Wilma's interactive, chat-based interface for dynamic exploration.
 
Power BI (Reporting & Visualization)
 
Data is exported as source files (.parquet), which are used to create dashboards in Power BI. This allows you to explore results in a structured, visual format.
 
 
Wilma (Interactive Analysis)
 
Wilma connects directly to the result database via MCP. You can interact with the results via chat, e.g. to ask questions, explain findings, and derive conclusions. This allows you to explore and interpret data specifically within your business context.
 
 

3.4 Available Content Bundles

The Agent Team supports Content Bundles for the following solutions:
  • Tax ICS
  • Cash Recovery AI (CRAI)
  • ICS Assessment
  • Digital Audit Preparation (DAP)
  • Finance Benchmarking (FB)
Detailed information on each Content Bundle can be found here: Content Bundles
 
 

 

4. Governance Onboarding

General governance-related topics include:
  • Data protection
  • Information security
  • Access management
All general information is available in this section: Data Protection & Information Security

 
Solution-specific governance information is available in the respective subsections.