Avoiding Agentic Mess with Data Products And Knowledge Graphs Andrea Gioia CTO & Founder @ Quantyca/Blindata Mauro Luchetti AI Center of Excellence Lead @ Quantyca 

Mind the agentic gap 

Agency vs Autonomy Autonomy is the freedom to choose while Agency is the ability to act. An Agent is anything that have agency. Agents can have different degrees of autonomy. A thermostat is an example of an agent without autonomy. It’s a reactive agent. No Agency Full Agency No Autonomy Full Autonomy AUTONOMY AGENCY Detached Intelligence (es. LLM) Passive Tools (es. Hammer) Autonomous Agent (es. Humans) Reactive Agent (es. Termostat) Agentic Systems Autonomy Gap 

Why agents are cool again? Rule Engine Symbolic AI Agent ENVIRONMENT AI Winter 1960 1980 2010 2022 2024 LLM Language AI Agent ENVIRONMENT ✅ Scalable: Design and train is outsourced, adaptation require low manual efforts ✅ Practical: Task-independent, easy to generalize ❌ Low Domain Accuracy: May hallucinate in domain specific contexts ❌ Low Transparency: Opaque decision-making, hard to interpret or trace reasoning Examples: Voyager, Manus, DeepSearch, Operator ❌ Not Scalable: Intensive manual efforts to design and train, adaptation is hard even for experts ❌ Not Practical: Task-specific, hard to generalize ✅ High Domain Accuracy: Performs exceptionally well in narrowly defined, rule-based domains ✅ High Transparency: Reasoning process is traceable and decisions are explainable Examples: Deep Blue, Watson, MYCIN, DENDRAL, XCON 🤓 🤯 🤒 

Mind the Gap Building an impressive AI Demo has never been easier ✅ turning the demo in a reliable production-ready AI Product remains challenging ❌ LLM ENV ENV LLM LLM LLM LLM DEMO PRODUCTION … BUT … 

Avoid the agentic mess 

How agents think Language agents explicitly organize knowledge into multiple memory modules, each containing a different form of knowledge. These include short-term working memory and several long-term memories: episodic, semantic, and procedural. 📌 Cognitive Architecture For Large Language Agents by Y. Shunyu et al. Know How Know Why Know That Know When Know What 

Agent Decision Loop Planning Reasoning: update working memory Retrieval: read long-term memory Executing Learning: write long-term memory Grounding: execute external actions and process environmental feedback into working memory ENVIRONMENT ENVIRONMENT 📌 Cognitive Architecture For Large Language Agents by Y. Shunyu et al. 

Communication is all you need Most of the time when an agent is not performing reliably the underlying cause is not that the model is not intelligent enough, but rather that the needed knowledge about the context have not been communicated properly to the model. “The single biggest problem in communication is the illusion that it has taken place.” George Bernard Shaw 📌 Communication is all you need by LangChain 

Agent information architecture To communicate effectively and efficiently the context to the agent, facts (data and metadata) alone are not enough; concepts and their relations are also needed (knowledge). Properly modeling the information architecture (concepts and how they relate to data and metadata) of an agent simplifies retrieval, reasoning, learning, and ultimately improves its actions DATA Understand KNOWLEDGE INTELLIGENCE Act Comprehend INFORMATION Processing Cognizing Reasoning Sensing Collect 

Adhocracy creates an agentic mess IA IA AI AI IA Customers have opened N tickets this week Customers have purchased N items this week We have shipped N items to customers this week When they talk about customers, are they referring to exactly the same thing? Siloed ad-hoc Context (aka Information Architecture) RAG AI 

IA Enterprise Enterprise information architecture Customers have opened N tickets this week Customers have purchased N items this week We have shipped N items to customers this week AI 12 RAG RAG RAG RAG 

Invest in your enterprise information architecture 

The enterprise knowledge graph Enterprise Ontology DATA KNOWLEDGE INFORMATION Processing Cognizing Reasoning Sensing An enterprise knowledge graph is an elegant way to represent the entire information architecture in a single model that is ● Shared ● Formal ● Computable Upper ontology Domain ontology Physical Data Subdomain ontologies 

Add semantic to data product Federated Governance Federated Modelling Team Self-serve platform Schema Constraints API Enterprise Ontology Data Contracts Data Data Product Defines Populate Links to Semantic interoperability Syntactic & tech. interoperability Uses Enforces Promotes Data Product Team 

Building the EKG Ontology Data products Knowledge Graph Linking Knowledge Plane Concepts + Relationships Information Plane Data + Metadata Data Management Solution Deploy Deploy Iterate Business Cases/Questions Modeling Team Data Product Team Business Analysis Knowledge Modeling Data Product(s) Implementation 

Knowledge Mesh 17 Self-serve Platform X as a Product X Domain Ownership Computational Governance Knowledge Mesh Data Mesh Socio Technical 

One last thing… 18 

DATA INFORMATION KNOWLEDGE Data Product Developer Platform Data Product Catalog Knowledge Product Developer Platform XOps Platform 19 

Blindata Data Product Developer Platform Data Product Catalog Knowledge Product Developer Platform 

Blindata reasoning MCP Server 

Thanks! Come to our stand D91 for chat or a fantastic Blindata demo! 📌 blibdata.io