SAP taps Mistral AI to help customers migrate legacy software

2026-05-21 · Source: The Decoder · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Novice, quick

Summary

SAP is using Mistral AI models to facilitate customer migration to S/4HANA, its core enterprise software for accounting, procurement, and logistics. Swiss Federal Railways (SBB) exemplifies this with a multilingual RAG chatbot assisting 30,000 employees during their software switch. This chatbot accesses internal documentation, understands technical abbreviations, and routes unresolved queries to human experts, whose responses are then automatically integrated back into the system. The AI operates on SAP's European infrastructure, ensuring no data crosses regional borders. The partnership began in June 2024 and expanded in October. However, SAP user groups indicate that most customers are still in early AI exploration phases, citing limited cloud adoption and complex licensing as significant obstacles.

Key takeaway

For IT Directors and consultants managing large-scale enterprise software migrations, this initiative demonstrates AI's practical value in accelerating complex transitions like S/4HANA. You should evaluate RAG chatbot solutions for internal knowledge management and employee support, prioritizing platforms that ensure strict data residency. Be prepared to address common adoption barriers such as limited cloud infrastructure and intricate licensing models when planning your AI integration strategy.

Key insights

SAP utilizes Mistral AI models to streamline S/4HANA migrations, demonstrated by SBB's RAG chatbot for employee support.

Principles

• AI can accelerate complex enterprise software transitions.
• RAG chatbots enhance internal knowledge access.
• Data residency is crucial for enterprise AI deployments.

Method

The RAG chatbot pulls from internal documents, interprets technical abbreviations, escalates complex questions to human experts, and continuously learns by integrating expert replies into its knowledge base.

In practice

• Implement RAG chatbots for internal support.
• Prioritize AI solutions with robust data residency.
• Establish feedback loops for AI knowledge improvement.

Topics

• SAP S/4HANA
• Mistral AI
• RAG Chatbots
• Enterprise Software Migration
• Data Residency
• AI Adoption Barriers

Best for: CTO, VP of Engineering/Data, Executive, Director of AI/ML, IT Professional, Consultant

Related on AIssential

• Former Palantir employees raise $60M for AI enterprise startup Conduct — AI agents require legible, operable enterprise systems to deliver results, especially with opaque legacy ERPs.
• Frontier AI for manufacturing. - Mistral AI — Mistral AI provides an integrated AI stack for manufacturing, accelerating product lifecycle from design to operations with physics AI and agentic workflows.
• AI Chatbot Development Services for Enterprise Data-Sensitive Processes — Custom generative AI chatbots are becoming functional infrastructure for enterprises handling sensitive data and complex workflows.
• AXA revolutionizes the future of insurance with AI. - Mistral AI — AXA integrates Mistral AI to empower employees and develop responsible, tailored use cases in financial services.
• Mistral AI launches Vibe, expands into industrial AI and announces data center push to challenge OpenAI — Full-stack ownership and vertical specialization are key to providing sovereign enterprise AI solutions.
• Mistral Small 4: The One Model That Codes, Reasons, and Chats — Mistral Small 4 unifies chat, reasoning, and coding via MoE architecture for efficient, multimodal AI.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by The Decoder.