BASF is a German multinational and one of many world’s largest chemical firms, identified for its built-in Verbund manufacturing community, world scale, and broad portfolio spanning from primary chemical substances to superior agricultural options. With its sturdy basis in analysis and growth, BASF operates throughout numerous industries whereas constantly driving innovation and sustainability.
Considered one of its key operational divisions is BASF Coatings, which focuses on creating, 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 reinforce productiveness, innovation, reliability, and design.
In partnership with Databricks, BASF Coatings has applied a production-ready, ruled, and business-impacting multi-agent answer. This strategy not solely enhances cross-team collaboration but in addition allows smarter, sooner decision-making throughout crucial 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 Techniques
As a corporation 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 process. Extra particularly, turning huge, disparate organizational knowledge into actionable insights, and enabling real-time decision-making and productiveness has grow to be 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 pace, buyer satisfaction, and operational reliability. The stakes had been notably 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 answer as a result of it may automate coordination and evaluation duties that beforehand required intensive guide effort. Agent methods may empower organisations like BASF Coatings to:
- Seamlessly combine AI throughout domains, automating routine operations in gross sales, procurement, and provide chain administration.
- Present good, contextual suggestions and automate choice flows, dramatically decreasing bottlenecks and errors.
- Enhance consumer expertise by enabling “always-on” chat assistants for help, 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 methods, they may develop extra advanced over time, making them more durable to handle and scale. For instance, an agent can have too many instruments at its disposal and make poor selections about which device to name subsequent, additionally the context grows too advanced for a single agent to maintain observe of. There’s a want for a number of specialization areas within the system (e.g. supervisor, area orchestration, subject material professional, and many others.)
One other solution to view the problem is thru the range of knowledge that varieties the agent system’s information base. Many people are already conversant in RAG (Retrieval-Augmented Technology), a method that mixes giant language fashions (LLMs) with real-time knowledge retrieval to enhance response accuracy and relevance. Nevertheless, RAG methods are primarily designed to deal with unstructured knowledge – Comparable to paperwork, internet pages, PDFs, or different types of free textual content – moderately than structured tables with predefined fields and relationships. When working with structured knowledge, Textual content-to-SQL is the most typical strategy 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 Answer: An Finish-to-Finish Multi-Agent Supervisor for Structured and Unstructured Info
To deal with these challenges, we suggest breaking our utility into a number of smaller, impartial 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 device.
AI/BI Genie, probably the most fashionable 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, establishing 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 permits knowledge stewards to actively handle and keep the standard of their Genie areas thus contributing on to the agent system with their invaluable enterprise area information.
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 via establishing a multi-agent system utilizing Mosaic AI Agent Framework along with Genie. These examples leverage LangGraph (an open-source agent orchestration library) and show easy methods to compose workflows the place Genie is one specialised agent amongst a number of.
An outline 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 varieties of customers, together with enterprise stakeholders who’re much less conversant in knowledge platforms – by embedding conversational deployment endpoints immediately inside the Groups interface. Clear, reusable accelerators exist for provisioning cloud sources (Azure Bot Service, App Service) and connecting endpoints to Groups.
Actual Enterprise Impression
Whereas BASF Coatings is creating AI brokers that may improve its enterprise processes, the primary touchdown zone challenge, Marketmind, focuses on the Gross sales & Advertising division. The use case allows 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 accessible within the type of Delta tables and views, whereas the remainder exists as free-text information and PDF paperwork, every arriving at totally different speeds and being up to date at various frequencies. Moreover, the info is managed by totally different groups and stewards. For instance, structured tables are primarily supplied by BASF’s central Enterprise Knowledge Lake (EDL) group, with Gross sales & Advertising enterprise specialists enriching them with domain-specific metadata. In distinction, unstructured knowledge is primarily processed via 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 challenge and used the template pocket book as our place to begin. We created a Genie area for structured knowledge, enriching it with curated tables, detailed column descriptions, Genie-local be a 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 assessments as new knowledge got here in to guage its general 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, guaranteeing 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 challenge started its scoping part in April this yr, adopted by a 5–6 week proof of idea (PoC). We then moved into the complete implementation part, accompanied by technical upskilling workshops, structure opinions, and product and have discussions with the Databricks’ Mosaic AI product group. We performed a one‑month pilot with 25 key customers, and are actually within the ultimate refinement stage earlier than go‑dwell 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 incessantly.
Marketmind is already altering how BASF Coatings’ gross sales groups put together, interact, and comply with up with their prospects. As an alternative of looking for leads via scattered notes and folders, gross sales representatives obtain customized notifications alongside advised 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 under illustrates this shift. Indicators from the market are offered 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 in addition obtain proactive adaptive playing cards with the newest market traits on a weekly foundation. Customers can discover subjects of curiosity in higher element by clicking the hooked up URL, which redirects them to the unique knowledge supply. To additional improve the agent’s high quality, we have now additionally built-in a voting mechanism that enables customers to rapidly give a thumbs up or down, or present extra detailed written suggestions within the backside area. This suggestions is captured within the mannequin inference desk and built-in with the present payload knowledge.
“Marketmind turns our area interactions into well timed, AI-driven actions—nudging good follow-ups, surfacing related alternatives, and connecting friends going through comparable challenges. The end result: sooner 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 important benefits for enterprises like BASF that look to leverage AI successfully of their enterprise contexts. We conclude the important thing power into the next features:
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 enables 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, sooner decision-making throughout numerous enterprise features. By integrating AI endpoints to MSFT Groups as a chat interface, we enable 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 absolutely ruled surroundings.
Shut group work between BASF, Databricks and companions: From challenge begin, BASF Coatings, Databricks account and product groups, and associate Accenture proactively engaged in workshops,. which helped align enterprise aims, technical necessities, and product imaginative and prescient, setting a powerful basis for profitable implementation. Proper on time, hands-on periods created fast suggestions loops. Knowledgeable steerage was constantly supplied by Databricks product group, serving to to customise the answer for the advanced, evolving wants of BASF and guaranteeing enterprise-grade high quality.
Wanting Ahead: Multi-Layered Orchestration and Agent Bricks
With the success of the Marketmind multi-agent supervisor answer, the corporate is now increasing the enterprise influence 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 best stability: it allows division-scoped knowledge and power entry management, preserves flexibility in agent growth, and helps a Coatings-wide “Ask Me Something” functionality.
Considered one of our future enhancement objectives is the adoption of Agent Bricks, launched this yr on the Knowledge & AI Summit. Whereas our present Mosaic AI–based mostly answer helps multi-agent orchestration, it stays code-first and requires a extra hands-on strategy with added complexity in deployment and administration. Agent Bricks gives a streamlined solution to construct and optimize domain-specific, high-quality AI agent methods 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 have now not but been capable of absolutely check its capabilities on account of restricted regional availability, we view Agent Bricks as a visionary route and plan to allow integration as soon as it turns into accessible, accelerating division-specific multi-agent supervisor growth.
