Enabling Agentic AI to Talk to Your Data

From Data Mesh to Data Access

The customer, a major player in the automotive industry, had already embraced a Data Mesh architecture, with data products managed across many domains. Data ownership is decentralised, metadata is catalogued and the technical foundation is built on an established data platform. Data Mesh itself had been architected and co-developed with mmkdigital.

However, while the organisational and technical groundwork for scalable data management was in place, accessing that data remained a challenge. Business users who needed insights (whether for production planning, configuration analysis or cross-domain reporting) still had to rely on analysts writing SQL queries. This created a familiar bottleneck: requests piled up, turnaround times stretched to days and data access, while technically possible, remained limited by analyst availability.

The question became: How can we bring the power of Data Mesh directly to the people who need the answers?

Data Mesh gave the organisation ownership and structure. The missing piece was giving non-technical users a direct line to that data without compromising quality or governance.

Johannes BitschPrincipal IT Architect

Data Available, But Not Accessible

Data Mesh had solved the problem of data ownership and quality at scale. But a new friction point had emerged: the last mile between structured, governed data and the business users who needed it.

Analysts served as intermediaries: receiving requests, translating them into SQL, running queries across one or more data products and delivering results. For simple lookups this was manageable, but for cross-domain queries (combining data from different data products of various organisational units and domains) the complexity grew quickly. Queries often required joins across multiple data products, deep knowledge of the data model and careful handling of edge cases such as distinguishing between model variants or excluding specific configuration codes.

The result: time-to-insight was measured in days and required a ticket. Business users lacked autonomy, analysts were overloaded with repetitive requests and the full potential of Data Mesh remained locked behind technical expertise.

Over the past 20 years, the team has always needed highly skilled data engineers that are highly involved in the business operations and every time one of the experts left into retirement, the pain to fill this gap became more imminent.

Product Owner Data AnalyticsClient

Portable, Reusable, LLM-Agnostic

The goal was clear: enable business users to query data products using natural language, enabling self-service and minimising time-to-insight.

But beyond the immediate use case, mmkdigital and the customer defined a set of strategic design principles:

• Platform independence: the solution must not be locked into a single LLM, agent framework or cloud provider. Core logic and data access should be reusable across environments.
• Separation of concerns: data discovery (finding the right data products) and data querying (retrieving actual results) should be cleanly separated to allow independent evolution and reuse.
• Context efficiency: the agent must intelligently select only relevant data products to avoid overloading the LLM’s context window, which would degrade response quality.
• Leverage existing infrastructure: the solution should build on the established data platform and data catalogue rather than introducing parallel systems.
• Observability: agent behaviour and latency must be traceable and monitorable for debugging and continuous improvement.

When we started talking to the business and understanding their pains, it became clear rather quickly that an agentic solution will be a huge relief for them. We had to get this right.

Alexander RengersSenior IT Architect

Architecture, Prototyping and Proof of Portability

mmkdigital was responsible for the end-to-end architecture design as well as the POC and prototype implementation. The solution centres on an AI agent built with the Strands Agents SDK using Claude Sonnet 4.6 on AWS Bedrock as the underlying LLM and Chainlit as the conversational frontend. This technology stack provides a mature foundation for enterprise-ready agentic systems. Users can interact with the system through natural-language questions, while the agent automatically identifies the relevant metadata, interprets the user’s intent and generates the corresponding SQL query. Before execution, the query is presented with explanations to the user for review and approval, ensuring full transparency and control. Once confirmed, the query is executed and results are returned within seconds. Observability is provided through Phoenix tracing, enabling full transparency into agent reasoning and execution paths, while Plotly is available as a custom tool for generating business-friendly visualisations directly from query results.

From the user perspective it goes like this: The user asks the agent a question. The agent automatically identifies the relevant metadata, interprets the user’s intent and generates the appropriate SQL query based on the available data structure. Before execution, the query is presented to the user for review and confirmation through a handoff step. Once approved, the query is executed, allowing the user to receive accurate results shortly after.

The core architectural innovation lies in the two-MCP-server pattern.

Additional MCP servers for Datasphere and DuckDB extend the architecture for multi-platform querying capabilities.

Proof of portability: When the customer’s AI strategy evolved to adopt Copilot Studio as the standard agent platform, mmkdigital ported the solution by reusing the same MCP servers and adapting the system prompt. Despite switching from Claude Sonnet 4.6 to GPT-5, the results were near-identical, validating the architecture’s independence from any single LLM or framework.

The port to Copilot Studio was the ultimate validation. Same MCP servers, different LLM and framework, and the agent still delivered answers of comparable quality.

Efstratios BaxivanelisProfessional IT Architect

From Days to Minutes

The most immediate impact is measured in time: queries that previously required analyst involvement and took up to two days can now be answered directly. The agent handles the complexity of data discovery, query construction and cross-domain joins: tasks that previously demanded deep technical knowledge.

Apart from the increase in speed, the solution shifts the operating model. Analysts are freed from repetitive query work and can focus on higher-value analysis. Business users gain autonomy and can explore data iteratively, asking follow-up questions, refining queries and drilling into results in a conversational flow.

The successful port to Copilot Studio demonstrated that the architecture delivers on its portability promise. The organisation is not locked into a single technology stack, and as LLMs and agent frameworks evolve, the core investment in MCP servers, metadata indexing and query logic remains fully reusable.

The first version of the agent is now approaching production readiness.

Moving beyond the proof-of-concept stage, the solution provides immediate value. With a foundation engineered for long-term scalability.

Johannes BitschPrincipal IT Architect

Conclusion

What began as a challenge of data accessibility in a mature Data Mesh environment has become a blueprint for how generative AI can create tangible business value without vendor lock-in.

mmkdigital architected and implemented a solution that brings the power of over 40 data products directly to business users through natural language. By separating data discovery from data querying with separate MCP servers, the architecture achieves a clean separation of concerns that pays dividends in flexibility, maintainability and portability. The RAG-based discovery layer ensures that the agent operates efficiently even as the number of data products grows, while the query engine handles the complexity of cross-domain joins and nuanced filtering logic.

To maintain transparency and user control, the system follows a human-in-the-loop approach: before execution, the generated SQL query is presented to the user with explanations for review and approval.

The proof of portability is perhaps the strongest testament to the architecture’s design: the same MCP servers ran with both the Strands Agents SDK (Claude Sonnet 4.6) and Copilot Studio (GPT-5) with near-identical results. This demonstrates that the real value lies not in any single LLM, but in its augmentation through highly efficient context engineering combined with a well-structured data access layer.

For the customer, the outcome is measurable: faster access to data, empowered business users and an AI architecture that is ready for what comes next. To mmkdigital, it is a validation of a core belief: that great AI solutions are built on great architecture, and great architecture is built to last, regardless of which model or platform powers it.

Your challenge,our passion.

Tell us where you are starting from and where you want to go. Together, we design a suitable solution and deliver it.