Skip to main content

Introduction

SAP Research Agent is built for pre-implementation research that suggests solutions after verifying against your unique system configuration.

This means:

  • Accurate configuration assessments: Configuration checks reflect your installed components and active settings.
  • Contextual specs creation: Generated documentation references your custom objects, existing enhancements, and naming conventions.
  • Relevant results: Searches return objects that exist in your system, not theoretical possibilities.
tip

Check out the free and open version where the results are validated against the 18 million standard objects in ECC 6.0 EHP 7 and 27 million standard objects in S/4HANA 2023.

Key Use Cases​

  1. Check Configuration Options

Find standard SAP capabilities that will satisfy your requirement, thus avoiding unnecessary custom code development

  1. Write Functional and Technical Specification Documents

Create comprehensive functional and technical specifications for configuration changes and custom code.

  1. Find SAP Objects

Instantly locate relevant objects from your ERP system. Search across programs, function modules, tables, data elements, and more with results filtered to your system's active components.

How does SAP Research Agent work?​

Core Architecture​

  • AI Backend: SAP Research Agent uses over 40+ Large Language Models with specialized configuration for SAP research tasks. More details here

  • Vector Database: The attached ERP system has been indexed into a ChromaDB vector database. It contains 18 million standard objects of ECC 6.0 EHP 7 and 27 million standard objects of S/4HANA 2023 like:

    • Transaction codes, programs, classes
    • Tables, views, data elements
    • BAdIs, enhancements, function modules
    • Menu paths, documentation, and more

Which models are being used?​

SAP Research Agent uses a combination of:

  • Internally fine-tuned models
  • Public frontier models

Depending on the subtask, an appropriate combination of models is chosen dynamically.

Model ProviderNo. of models used
Adri AI4
Google9
Mistral6
Meta8
OpenAI7
Anthropic4
Cohere4
Total42

Note: Counts are as of November 2025

Key Capabilities​

  1. System Validation

SAP Research Agent queries the attached SAP system by writing ChromaSQL queries. ChromaSQL is a SQL-inspired domain specific language created by Adri AI.

  1. Web Search

SAP Research Agent also has the capability to search the internet for SAP solutions, best practices, and similar use cases.

  1. Document Processing

SAP Research Agent can read the uploaded attachments and optionally index them for future reference.

Typical Workflow​

  1. User asks a research question (text + optional attachments)
  2. Depending on the question, the SAP Research Agent may think of a solution from its own knowledge base or search the web for relevant resources.
  3. The solution is then validated against your SAP system's capabilities using the vector database.
  4. The agent creates detailed implementation plans with specific T-codes, ABAP objects, and configuration steps.
  5. The agent provides alternatives and visual diagrams when helpful.

Connected systems​

If you are on Adri AI's Enterprise Plan, you can connect SAP Research Agent to your SAP environment to enable system-aware recommendations.

You can also check out the free and open version where the results are validated against the 18 million standard objects in ECC 6.0 EHP 7 and 27 million standard objects in S/4HANA 2023.

Installed Components​

You can view the installed components in the attached ERP system.

Installed Components in ECC 6.0 EHP 7 system
Installed Components in ECC 6.0 EHP 7 system

You may search the components in the attached system using the SAP Research Agent or by writing SQL-like queries (using ChromaSQL). More on ChromaSQL here.

info

Have any other questions? Check our FAQs.