Best Practices for Implementing a Semantic Layer

If you want to understand why your data needs a semantic layer, look at what happens to AI without one. Without semantics, your best case is forcing a massive JSON payload into an LLM to explain what your data means. The worst case? AI blindly wanders through undocumented data, guessing based on statistical probability rather than actual logic. Neither outcome is acceptable for organizations building reliable, production-grade AI. As Meagan Palmer recently noted, the semantic layer has historically had two meanings: one from BI/data management, and one from the Semantic Web. Yesterday Jessica Talisman did a deep dive on the history of semantic layers cracking open the fine-grained detail. (See comments for links). To truly support AI, you must unify both types of semantics. Here's a Crawl → Walk → Run progression for evolving your metadata stack into a unified form: Crawl: Structure and Best Effort Semantics — Centralize metadata into JSON Schemas and glossaries. Move away from fragmented silos by adopting a unified metadata model capturing first-class entities like tables, dashboards, and pipelines. This establishes clearer definitions across your organization. But this is still just best effort semantics. Flat definitions create dangerous ambiguity AI cannot resolve alone. Ask what revenue means and Finance says "Net", Sales says "Gross", Marketing says "Attributed". Without explicit architectural meaning, AI fills that gap with probability — delivering confident but wrong answers. Walk: From Metadata Graph to RDF — Make your metadata machine-understandable. Translate JSON schemas into an RDF graph of subjects, predicates, and objects. Starting with schema.org means analysts work in familiar JSON while that structure translates into formal formats like JSON-LD without complex context switching. The result is a knowledge graph built on standard vocabularies like DCAT for datasets and PROV for lineage, layered with data quality, ownership, and usage context. This enables GraphRAG, SPARQL queries, and cross-system connectivity. Run: Ontologies and AI Reasoning — Evolve from a flat glossary to a full knowledge ontology. Instead of defining a customer as simply a person who buys goods, map exactly how that entity relates to domains, metrics, revenue streams, and orders. Connect that ontology to your physical data estate by tagging real tables and columns to concepts in your OWL ontology. The result: you move beyond context-driven approximations like vector similarity to a true semantics-driven system. AI agents consume structured semantic context to execute cognitive logic. Definitions and relationships are explicitly governed, so answers are precise, consistent, and explainable. Not statistical guesses. You've stopped standardizing metadata. You've started standardizing meaning. #DataStrategy #SemanticLayer #AIData #KnowledgeGraph #DataManagement #EnterpriseAI #Ontology #DataGovernance #RDF

(Part 4 of my series: The Boardroom Guide to AI-Ready Data Strategy) For years, organisations debated Data Lakes vs. Data Warehouses. But today, that debate is irrelevant. 1. Infrastructure has become a commodity. 2. Compute is cheap. 3. Storage is cheap. 4. Pipelines are automated. The real bottleneck to scaling AI isn’t technology. It’s meaning. If Marketing, Finance, Risk, and Product all define foundational terms differently , “Customer”, “Revenue”, “Churn”, “Exposure”, your AI systems will fail instantly. They will generate plausible-sounding nonsense based on conflicting definitions. This is why modern AI-driven organisations are shifting from infrastructure debates to semantic alignment. The 3 Architecture Priorities for AI-Ready Enterprises 1️⃣ Decouple Compute & Storage So you can scale elastically, control costs, and avoid vendor lock-in. 2️⃣ Build a Semantic Layer A unified business logic layer sitting above your physical data. It defines metrics, joins, relationships, and meaning — consistently across the enterprise. This becomes the “Rosetta Stone” for your LLMs and Agentic AI systems. 3️⃣ Move to Data Products Instead of fragile pipelines, build domain-owned, SLA-backed, well-documented data products. This accelerates cross-team adoption and eliminates ambiguity. You don’t fail at AI because your model is weak. You fail because your definitions are weak. If your organisation wants reliable GenAI, RAG, and autonomous agents, your first investment is not GPUs, it is the Semantic Layer. Don’t just modernise your stack. Modernise your logic. #DataArchitecture #SemanticLayer #DataProducts #DataMesh #AIStrategy #EnterpriseArchitecture #GenAI #ModernDataStack

Beyond Prompts: Why Your AI Strategy Needs a "Semantic Layer" In my last article, I argued that the biggest hurdle for AI is human, not technical. We focused on building "Change Fitness"—the organizational muscle to adapt. We discussed literacy, redesigned workflows, and a culture of experimentation. But what happens when your newly "fit" organization starts deploying multiple AI agents? When your marketing chatbot, your sales forecast agent, and your product design co-pilot all need to work together on a single customer journey? You hit a new, silent wall. The problem isn't processing power or model capability. It's meaning. Today, we move from building the team to building the system that allows the team to think together. The critical infrastructure for this isn't found in your cloud provider's dashboard. It's the Semantic Layer: the shared language and understanding that allows humans and AI agents to collaborate with purpose, not just exchange data. Without it, you don't have an intelligent enterprise. You have a tower of Babel filled with very fast, very confused machines. The "Lost in Translation" Problem at Scale Imagine a simple cross-department goal: "Increase high-value customer retention." To your CRM agent, "high-value" might mean "purchased a premium plan in the last 90 days." To your support bot, it might flag "any user who opened more than 3 tickets," seeing them as at-risk. To your product analytics agent, it might define them as "users with a weekly session duration > 1 hour." Three agents, three conflicting definitions, working at machine speed. The result? Chaotic, contradictory actions. The marketing agent offers a discount to a user the support agent just flagged as abusive. The system is data-rich but meaning-poor. This is the chaos of a missing Semantic Layer. It’s not a software bug; it’s a strategic and communicative failure. The Three Pillars of a Strategic Semantic Layer Building this layer is not an IT task. It is the core strategic communicator's next mandate. It involves defining: 1. The Lexicon of Intent This moves beyond a simple data dictionary. It's a living document that defines core business concepts with nuance, context, and strategic intent. Don't just define "Customer Churn." Do define "Voluntary Churn vs. Product-Gap Churn," along with the business logic for why the distinction matters and the different actions each should trigger in your AI ecosystem. This lexicon becomes the common source of truth that every AI agent is trained and aligned against. It encodes your company's strategy into a machine-readable format. 2. The Protocols for Collaboration How do agents "talk" to each other? It's more than an API call. It's about passing context, confidence, and intent. A workflow shouldn't just be: Support Agent → [Flagged User] → CRM Agent → [Sends Coupon]. More in link.

Spoke to the head of analytics last week. They moved to Snowflake, cleaned up their pipelines, and built 200+ dashboards. But users were still arguing over which “Revenue” number to trust. The stack got modern. The numbers? Still confusing. Here’s the real gap: Data infra ≠ Shared definitions. Yes, Shared Definition! You can have the best of Databricks, Snowflake, and dbt. But if Finance, Ops, and Product define “Active User” differently, dashboards just turn into debate rooms. Revenue. Retention. On-time delivery. All slightly different. All "valid." None consistent. That’s why the semantic layer matters. It’s the layer most people overlook but it’s the one that actually builds trust. When done right, metrics are defined once and used everywhere. Looker, Tableau, notebooks, APIs same logic, same result. No last-minute SQL rewrites. No silent metric drift. No "who made this dashboard" moments. The best stacks I’ve seen recently? They don’t just invest in compute and storage. They invest in clarity. Quietly. Deeply. And funny enough, that clarity usually starts with one decision: We define metrics in one place. And we stick to it. Everything else follows. #dataengineering #semanticlayer #dataplatform #analytics #snowflake #databricks #revenueops

📌 The Future of Agentic Analytics in BI There’s a growing misconception right now... That layering AI into your dashboards will magically transform your analytics. There’s a lot of hype around AI agents in analytics: ⤷ Natural language interfaces. ⤷ Auto-generated insights. ⤷ Chat-based dashboards. You might’ve even heard of the term Agentic Analytics The promise is that business users will be able to “ask anything” and get instant answers from data. But here’s the problem no one’s talking about: Most organizations aren’t ready for AI agents yet. Not because the tech isn’t mature. But because their data context is broken. → If your KPIs are misaligned across teams… → If your semantic layer is missing or incomplete… → If no one trusts how metrics are calculated… Then all an AI agent will do is generate faster wrong answers. You’ll get output but not outcomes. Before you invest in Agentic Analytics, ask yourself: 1) Do we have a single source of truth for our KPIs? 2) Is our semantic layer well-structured and governed? 3) Are stakeholders confident in the meaning behind the metrics? 4) Can business users explore data on their own? If not, the priority isn’t AI. It’s trust, structure, and shared understanding. That’s why the recent Salesforce acquisition of Informatica makes perfect sense. While the market chases the next flashy analytics tool, Salesforce is investing in the fundamentals: → Data integration → Metadata → Governance Because they understand this: AI is only as effective as the context it runs on. Here’s what I’ve seen work in the real world: 1️⃣ 𝐒𝐭𝐚𝐫𝐭 𝐰𝐢𝐭𝐡 𝐲𝐨𝐮𝐫 𝐬𝐞𝐦𝐚𝐧𝐭𝐢𝐜 𝐥𝐚𝐲𝐞𝐫 Define your KPIs, dimensions, and filters like you’re building a product. 2️⃣ 𝐃𝐨𝐜𝐮𝐦𝐞𝐧𝐭 𝐛𝐮𝐬𝐢𝐧𝐞𝐬𝐬 𝐥𝐨𝐠𝐢𝐜 Explain what each metric means and where it comes from. 3️⃣ 𝐀𝐥𝐢𝐠𝐧 𝐚𝐜𝐫𝐨𝐬𝐬 𝐝𝐞𝐩𝐚𝐫𝐭𝐦𝐞𝐧𝐭𝐬 Marketing, sales, ops should all speak the same data language. 4️⃣ 𝐁𝐮𝐢𝐥𝐝 𝐝𝐚𝐭𝐚 𝐭𝐫𝐮𝐬𝐭 Through consistency, transparency, and usage-based feedback. 5️⃣ 𝐃𝐞𝐩𝐥𝐨𝐲 𝐀𝐈 𝐀𝐠𝐞𝐧𝐭𝐬 Then and only then you can explore AI as a layer on top of a solid foundation. BI without context is just noise. And AI without structure is just risk at scale. If you’re serious about improving decision-making in your business, fix your foundations first. The tools will come and go. Context is what makes them useful. #DataStrategy #BusinessIntelligence #DataGovernance

Semantic Layer Strategy for Agentic Systems 🗼 Semantic layers represent a critical foundation for agentic AI systems, serving as the interpretive bridge between raw data and meaningful action. Current agentic systems operate with inherent limitations that restrict their effectiveness: bounded contextual awareness (fixed context windows), interpretive deficiencies (struggling with ambiguity), and reactive rather than proactive intelligence. These limitations come from a computational paradigm that fundamentally misaligns with the nature of intelligence. The solution requires a three-tier architecture: Foundation Tier: Meaning Infrastructure - Comprising ontological frameworks, taxonomies, relationship models, and contextual mapping frameworks that define core concepts and relationships Mediation Tier: Knowledge Processing - Including entity extraction, relationship inference, context interpretation, and selective activation algorithms Application Tier: Agentic Interface - Featuring prompt augmentation, response verification, memory management, and learning loops This architecture supports a progressive implementation approach, from domain-specific ontologies to enterprise-wide meaning infrastructure, allowing organizations to evolve their semantic capabilities incrementally. As agentic systems evolve from simple tools to autonomous actors, the sophistication of their semantic underpinnings becomes increasingly determinative of their capabilities and limitations. There is a paradigm shift from treating semantic understanding as a layer applied atop existing data architectures to positioning meaning as the foundational infrastructure. This inversion principle recognizes that intelligence fundamentally operates on meanings rather than data, requiring computational systems to do the same if they are to overcome current limitations. A structured maturity model emerges, progressing from basic metadata management to comprehensive meaning infrastructure. This progression correlates with evolving agentic capabilities, from deterministic tools to autonomous actors. The Novo Nordisk case study demonstrates how organizations can implement ontology-based data management as a practical pathway toward semantic maturity. Knowledge graphs emerge as superior foundations compared to data graphs for semantic layers, providing critical capabilities for handling uncertainty, representing contextual meaning, capturing temporal evolution, and supporting advanced reasoning patterns. The Basic Formal Ontology (BFO) approach illustrates how grounding semantic layers in ontological realism provides agentic systems with a framework that reflects reality rather than arbitrary conceptualizations. This reality-anchoring function becomes essential in high-stakes domains where decisions affect real people, processes, or transactions.

Many ask themselves, «Why would I use a semantic layer? How to build one?». But a better question is: How many times have you implemented the same revenue calculation differently across your company's dashboards, reports, and apps? This is why semantic layers exist. With a semantic layer, your revenue KPI or other complex company measures are defined once in a single source of truth—no need to re-implement them over and over again. In my latest article, we'll have a look at the simplest possible semantic layer, which uses a simple YAML file (for the semantics) and a Python script for executing it with Ibis and DuckDB.  The goal is not to build a full-blown semantic layer, but rather to understand the value of such layers. We query 20 million NYC taxi records with consistent business metrics executed using DuckDB and Ibis. By the end, you'll know precisely when a semantic layer solves real problems and when it's overkill. It's a topic that I'm passionate about as I've been using semantic layers within a Business Intelligence (BI) tool for over twenty years, and only recently have we gotten full-blown semantic layers that can sit outside of a BI tool, combining the advantages of a logical layer with sharing them across your web apps, notebooks, and BI tools. ✨ Some of the Chapters and Insights: - When you DON'T need a Semantic Layer - Why use a semantic layer with the differentiation of «Datasets vs. Aggregations» - think of it this way: » dataset ≠ aggregations » table columns ≠ metrics » physical table ≠ logical definition If you find yourself needing the concepts on the right side, that's when you need a semantic layer, either for building into a BI tool or implemented separately. - A practical example with DuckDB, Boring Semantic Layer (by Julien Hurault and Hussain S.), and Ibis. Building a Domain-specific language (DSL) for our Metrics and KPIs. - Round up with common questions about the Semantic Layer, such as can't we use a database, or a database View for it? Should we use MCP, and what are the popular semantic layer tools? I hope you enjoy. Read the full essay here: https://lnkd.in/edB7uGVr. Happy to discuss further. Exciting times ahead for BI and for the semantic layer. PS: It's on the front page of Hackernews right now (30 position), but peaked yesterday evening :)

Most “semantic” strategies are missing one critical layer. And without it, your business meaning evaporates. It’s the mapping layer. I define semantics as Technical metadata + Mapping metadata + Business metadata. This definition has sparked many AHA moments for folks: - Many teams think they have semantics but only have technical metadata. They swap in “business terms” without realizing the mapping step is missing. - Mapping metadata is buried in application logic. It works inside that app, but the moment you try to reuse it elsewhere… it’s lost. - Without explicit mapping, you’re left with oversimplified one-to-one replacements, or worse, no real business meaning at all. When all three are explicit and connected, the lightbulbs start going off: - You can have multiple valid definitions of something like “Net Revenue” - You can document each version, along with how it maps to the technical data. - You preserve the why behind each definition, not just the what. That’s when the lightbulbs go off: semantics become reusable, and meaning becomes portable across contexts. Question for you: In your organization, is mapping metadata something you make explicit… or is it hiding in the shadows of your application logic?

"SAP Analytics Cloud should consume, not compute." This single principle transformed how we approach SAC + Datasphere integrations. The problem? Most teams push too much logic into SAC—calculations, complex KPIs, heavy transformations. The result? Slow reports. Frustrated users. Maintenance nightmares. The fix? Build a rich semantic layer in Datasphere. Keep SAC thin. I wrote a practical guide covering: ✓ Layered modeling approach ✓ Where to define calculations ✓ Performance optimization tactics ✓ Common pitfalls and how to avoid them #SAPDatasphere #SAPAnalyticsCloud #SAP #Analytics #DataArchitecture