Records practices, thoughts, and pitfalls on the data grunt-work journey, sharing content on data platforms, data analysis, data processing, data governance, knowledge graphs, and more. Less theory, more hands‑on, making complex data technologies simple.
The article argues that industry AI requires a semantic platform to connect large models, data platforms, and business scenarios by structuring business objects, processes, states, rules, evidence, and action contracts, enabling verifiable, traceable agent execution and continuous model-data resonance.
This article argues that AI pilots require predefined graduation criteria across business value, system quality, operational readiness, and governance to move beyond PoC, using phase-gate reviews to decide whether to expand, adjust, or stop investment, illustrated with an equipment temperature alert agent example.
The article distinguishes ontology semantics (AI understanding business objects, states, rules) from ontology intelligence (explainable decisions, contract-constrained actions, auditable loops), outlining seven engineering capabilities needed to close the loop and emphasizing a minimal viable loop around high-value decisions.
This article introduces the Ontology Intelligence series, explaining why enterprise AI agents fail in production without unified business semantics, current object state, explainable decisions, controlled actions, and continuous governance—outlining a five-layer framework and scenario-based criteria for adopting ontology-driven architectures.
This article outlines a four-step framework for converting employee expertise into reusable enterprise agent capabilities: distilling tacit knowledge into organizational knowledge, encapsulating stable task methods as Skills, connecting data and tools via MCP, and packaging them into governed capability bundles with versioning, permissions, and evaluation assets for controlled reuse and continuous improvement.
The article argues ontology is not a new technology but a modeling mindset that defines business objects, relationships, states, rules, and actions to create a machine-understandable semantic layer, enabling AI agents to act within explicit business constraints rather than just generating responses.
The article explains how AI programming is shifting from single-task loops to graph-based orchestration, where multiple loops are organized as explicit runtime graphs with typed dependencies, state transitions, and evidence gates to manage parallel tasks, failures, and verification across roles.
This article defines AI Data Engineering as a data supply system for large models and agents, extending traditional data engineering with semantic modeling, RAG, controlled data services, permission governance, and feedback loops to make data understandable, retrievable, callable, and auditable for reliable enterprise AI deployment.
This article argues that true enterprise AI transformation goes beyond deploying chatbots, requiring AI to reshape employee workflows, integrate into business processes as controlled agents, and embed into products to deliver new customer value, all built on a shared foundation of context, data, tools, governance, collaboration, and feedback loops.
This article presents a framework for selecting high-value AI pilot projects by evaluating both business value (impact, urgency, consensus) and feasibility (data evidence, process clarity, controllable boundaries, verifiable results), using entry criteria to filter out risky scenarios and a decision card to align stakeholders on scope, metrics, and stop conditions.
