BASF is a German multinational and one of many world’s largest chemical firms, recognized for its built-in Verbund manufacturing community, world scale, and broad portfolio spanning from primary chemical substances to superior agricultural options. With its robust basis in analysis and growth, BASF operates throughout numerous industries whereas constantly driving innovation and sustainability.
Certainly one of its key operational divisions is BASF Coatings, which focuses on growing, manufacturing, and advertising superior automotive and industrial coatings, together with ornamental paints. As a pioneer in eco-efficient floor applied sciences, BASF Coatings can also be on the forefront of digital transformation, leveraging AI-powered platforms to boost productiveness, innovation, reliability, and design.
In partnership with Databricks, BASF Coatings has carried out a production-ready, ruled, and business-impacting multi-agent resolution. This method not solely enhances cross-team collaboration but additionally permits smarter, quicker decision-making throughout vital enterprise features — setting a benchmark for a way superior analytics and AI can drive tangible enterprise outcomes.
The Problem: Deliver extra Modularity, Specialization and Management to Agent Programs
As a company with over 11,000 staff throughout greater than 70 websites worldwide, managing the rising complexity and enhancing effectivity of cross-department digitalization is a non-trivial activity. Extra particularly, turning huge, disparate organizational knowledge into actionable insights, and enabling real-time decision-making and productiveness has turn into the important thing. Fixing this downside mattered as a result of environment friendly digital collaboration and knowledge utilization immediately have an effect on market responsiveness, innovation velocity, buyer satisfaction, and operational reliability. The stakes have been significantly excessive in industries like coatings, the place agility and precision are essential amid quickly altering buyer calls for and sustainability pressures.
An agentic system – the place autonomous or semi-autonomous AI brokers proactively handle enterprise processes and knowledge flows – was one of the best resolution as a result of it might automate coordination and evaluation duties that beforehand required intensive guide effort. Agent techniques might empower organisations like BASF Coatings to:
- Seamlessly combine AI throughout domains, automating routine operations in gross sales, procurement, and provide chain administration.
- Present sensible, contextual suggestions and automate resolution flows, dramatically lowering bottlenecks and errors.
- Enhance consumer expertise by enabling “always-on” chat assistants for assist, Q&A, or workflow integration throughout departments.
- Drive adoption of on a regular basis AI instruments company-wide, making advanced digital capabilities accessible to enterprise stakeholders and fostering knowledge literacy.
As highly effective as an agent could possibly be, as we develop these techniques, they could develop extra advanced over time, making them tougher to handle and scale. For instance, an agent can have too many instruments at its disposal and make poor choices about which instrument to name subsequent, additionally the context grows too advanced for a single agent to maintain monitor of. There’s a want for a number of specialization areas within the system (e.g. supervisor, area orchestration, subject material knowledgeable, and so on.)
One other technique to view the problem is thru the variety of information that kinds the agent system’s data base. Many people are already acquainted with RAG (Retrieval-Augmented Era), a way that mixes giant language fashions (LLMs) with real-time knowledge retrieval to enhance response accuracy and relevance. Nevertheless, RAG techniques are primarily designed to deal with unstructured knowledge – Corresponding to paperwork, internet pages, PDFs, or different types of free textual content – slightly than structured tables with predefined fields and relationships. When working with structured knowledge, Textual content-to-SQL is the commonest method for pure language analytics. Nevertheless, it typically depends on pre-defined instance SQL queries and lacks built-in mechanisms for knowledge governance and permission management.
The Resolution: An Finish-to-Finish Multi-Agent Supervisor for Structured and Unstructured Info
To handle these challenges, we suggest breaking our software into a number of smaller, unbiased brokers and composing them right into a multi-agent system. This method will comply with a supervisor sample that coordinates the specialist brokers – particularly, Genie brokers and function-calling brokers – which work together with the Databricks Vector Retailer Retrieval instrument.
AI/BI Genie, one of the crucial widespread options inside Databricks, is designed to make structured knowledge akin to Delta tables and views immediately accessible to enterprise customers by leveraging pure language interfaces. It makes use of metadata from Unity Catalog, akin to desk descriptions, PK/FK relationships, and column names/descriptions. This metadata guides Genie in parsing consumer questions, setting up correct SQL, and delivering contextually related solutions – serving to to mitigate errors or hallucinations. As well as, Genie authors can improve the area by domestically modifying metadata, defining joins, including synonyms, and curating BASF-specific directions. This enables knowledge stewards to actively handle and preserve the standard of their Genie areas thus contributing on to the agent system with their invaluable enterprise area data.
To ease using Genie inside agent orchestration frameworks, there are frameworks supporting devoted Python wrappers for constructing Genie brokers (test right here for reference). As well as, Databricks product group options instance notebooks that stroll our customers by way of organising a multi-agent system utilizing Mosaic AI Agent Framework along with Genie. These examples leverage LangGraph (an open-source agent orchestration library) and exhibit tips on how to compose workflows the place Genie is one specialised agent amongst a number of.
An summary of our structure is as follows. We undertake Databricks’ Mosaic AI framework to simplify the complexities of managing AI agent lifecycles, providing instruments and fast multi-agent coordination prototyping, rigorous analysis, and efficient real-time operational monitoring. Notably, we additionally combine the deployed supervisor endpoint with Microsoft Groups for real-time agent execution, and make AI-powered insights available to all forms of customers, together with enterprise stakeholders who’re much less acquainted with knowledge platforms – by embedding conversational deployment endpoints immediately throughout the Groups interface. Clear, reusable accelerators exist for provisioning cloud sources (Azure Bot Service, App Service) and connecting endpoints to Groups.
Actual Enterprise Influence
Whereas BASF Coatings is growing AI brokers that may improve its enterprise processes, the primary touchdown zone undertaking, Marketmind, focuses on the Gross sales & Advertising and marketing division. The use case permits superior quantitative and qualitative evaluation by consolidating inner Salesforce buyer go to experiences and market consumption insights with exterior market traits together with S&P 500 information. A few of this knowledge is already processed and obtainable within the type of Delta tables and views, whereas the remaining exists as free-text recordsdata and PDF paperwork, every arriving at completely different speeds and being up to date at various frequencies. Moreover, the info is managed by completely different groups and stewards. For instance, structured tables are primarily offered by BASF’s central Enterprise Knowledge Lake (EDL) group, with Gross sales & Advertising and marketing enterprise specialists enriching them with domain-specific metadata. In distinction, unstructured knowledge is primarily processed by way of code-first ETL pipelines developed and maintained by the Coatings Knowledge & AI workplace group.
Given the complexity of the info panorama, we adopted the multi-agent supervisor structure for the Marketmind undertaking and used the template pocket book as our start line. We created a Genie area for structured knowledge, enriching it with curated tables, detailed column descriptions, Genie-local be part of relationships, and worth sampling. To enhance accuracy, we added SQL examples and clear directions to information Genie’s responses, and we carried out common Benchmark exams as new knowledge got here in to judge its total efficiency.
For unstructured knowledge akin to Salesforce go to experiences and market information, we constructed vector search indices for every supply utilizing embeddings to allow context-aware similarity search. We then created Unity Catalog features that wrap Mosaic AI Vector Search queries, making certain enterprise-ready governance, discoverability, and computerized MLflow tracing. Lastly, we developed a operate tool-calling agent that invokes vector retrieval instruments to deal with task-specific requests handed alongside by the supervisor.
Our Marketmind undertaking started its scoping section in April this 12 months, adopted by a 5–6 week proof of idea (PoC). We then moved into the complete implementation section, accompanied by technical upskilling workshops, structure critiques, and product and have discussions with the Databricks’ Mosaic AI product group. We carried out a one‑month pilot with 25 key customers, and at the moment are within the remaining refinement stage earlier than go‑reside and rolling out to North America by the tip of October . As soon as launched, greater than 1,000 gross sales representatives worldwide shall be utilizing Marketmind, with inputs up to date ceaselessly.
Marketmind is already altering how BASF Coatings’ gross sales groups put together, interact, and comply with up with their clients. As an alternative of looking for leads by way of scattered notes and folders, gross sales representatives obtain customized notifications alongside recommended actions and methods based mostly on present occasions available in the market. If additional data is required, Marketmind gives the choice to dig deeper into the underlying knowledge and experiences utilizing an easy-to-use chat interface. The screenshot beneath illustrates this shift. Alerts from the market are introduced in an actionable, conversational interface inside Microsoft Groups, so Coating’s gross sales group can shift their focus from “What occurred?” to “What ought to I do subsequent?” with out switching instruments.
As proven above, gross sales groups can’t solely ask ad-hoc inquiries to the Marketmind chatbot immediately in Groups, but additionally obtain proactive adaptive playing cards with the most recent market traits on a weekly foundation. Customers can discover subjects of curiosity in larger element by clicking the hooked up URL, which redirects them to the unique knowledge supply. To additional improve the agent’s high quality, we’ve got additionally built-in a voting mechanism that permits customers to rapidly give a thumbs up or down, or present extra detailed written suggestions within the backside discipline. This suggestions is captured within the mannequin inference desk and built-in with the prevailing payload knowledge.
“Marketmind turns our discipline interactions into well timed, AI-driven actions—nudging sensible follow-ups, surfacing related alternatives, and connecting friends dealing with comparable challenges. The consequence: quicker prep, sharper buyer conversations, and extra time promoting the place it counts.” — Adrian Fierro, Head of World Market Intelligence at BASF Coatings
Why It Labored
Multi-agent structure with Genie as an agent gives a number of vital benefits for enterprises like BASF that look to leverage AI successfully of their enterprise contexts. We conclude the important thing power into the next points:
Specialised agent capabilities with excessive scalability and modularity: inside a multi-agent system, numerous brokers can deal with their particular domains or duties, enabling deeper experience in dealing with numerous queries and datasets. Furthermore, organisations like BASF can broaden their gateway to AI options with an structure that permits every enterprise division to function independently whereas being centrally orchestrated. This modular design helps handle complexity over time.
Enhanced collaboration and improved consumer expertise: brokers can share data and context with each other, permitting for extra complete responses that combine knowledge from a number of sources. This facilitates smarter, quicker decision-making throughout numerous enterprise features. By integrating AI endpoints to MSFT Groups as a chat interface, we permit customers to work together with brokers utilizing pure language, making it extra accessible to non-technical stakeholders.
Governance and compliance: Defending private and buyer knowledge is the Commented basis of Marketmind and stays our highest precedence. Each interplay is constructed on strict compliance with BASF’s knowledge safety requirements, leveraging Databricks’ enterprise-grade governance capabilities akin to Unity Catalog for fine-grained entry management, lineage monitoring, and auditability. This ensures that whereas Marketmind accelerates insights and actions, it does so inside a safe, clear, and totally ruled atmosphere.
Shut group work between BASF, Databricks and companions: From undertaking begin, BASF Coatings, Databricks account and product groups, and companion Accenture proactively engaged in workshops,. which helped align enterprise targets, technical necessities, and product imaginative and prescient, setting a robust basis for profitable implementation. Proper on time, hands-on classes created fast suggestions loops. Professional steerage was constantly offered by Databricks product group, serving to to customise the answer for the advanced, evolving wants of BASF and making certain enterprise-grade high quality.
Wanting Ahead: Multi-Layered Orchestration and Agent Bricks
With the success of the Marketmind multi-agent supervisor resolution, the corporate is now increasing the enterprise impression throughout broader operations, together with Provide Chain, Procurement, Chemetall (Floor Expertise subsidiary), and Folks & Tradition. Along with our product group, we’re exploring a extra scalable multi-layered structure, the place every division operates its personal multi-agent supervisor, whereas a higher-level Coatings-wide orchestrator serves all customers. This hierarchical system – a “supervisor of supervisors” – strikes the fitting stability: it permits division-scoped knowledge and gear entry management, preserves flexibility in agent growth, and helps a Coatings-wide “Ask Me Something” functionality.
Certainly one of our future enhancement targets is the adoption of Agent Bricks, launched this 12 months on the Knowledge & AI Summit. Whereas our present Mosaic AI–based mostly resolution helps multi-agent orchestration, it stays code-first and requires a extra hands-on method with added complexity in deployment and administration. Agent Bricks gives a streamlined technique to construct and optimize domain-specific, high-quality AI agent techniques for frequent use instances, together with multi-agent setups. With options akin to computerized optimization, price and high quality effectivity, and user-driven suggestions mechanisms, it simplifies agent implementation and permits groups to deal with core challenges – knowledge, metrics, and problem-solving. Though we’ve got not but been capable of totally take a look at its capabilities on account of restricted regional availability, we view Agent Bricks as a visionary course and plan to allow integration as soon as it turns into accessible, accelerating division-specific multi-agent supervisor growth.