Official account of the DataFun community, dedicated to sharing big data and AI industry summit news and speaker talks, with regular downloadable resource packs.
The article analyzes the rise of fully automated “lights‑off” software factories, exposing how AI coding agents accelerate builds but introduce severe maintainability defects, inadequate benchmarks, and hidden long‑term costs that force engineers to re‑introduce planning and human code review.
The article analyzes how industrial AI must first build a unified business ontology—mapping fragmented data about engines, parts, orders, and maintenance into coherent business objects—before large models can reliably turn insights into actionable decisions, using GE's J85 engine program as a concrete case study.
A longitudinal study of 8.8 million users over 11 months demonstrates that while agentic marketing can sustain performance after human optimization stops, its gains eventually decay, highlighting the emerging “Agentic CDP” model where AI handles baseline decisions while humans drive growth.
The article analyses why the current wave of AI agents often “runs away” from business rules, proposes an ontology‑driven semantic base to make agents safely controllable, details three technical pillars—architecture constraints, context engineering, and feedback loops—and illustrates the Knora implementation with a concrete work‑order change workflow.
The article reviews a series of technical case studies—including Alibaba Cloud AI Search's Agentic RAG, Baidu's GRAB generative ranking, Huawei Noah's LLM‑enhanced recommendation, and Elasticsearch vector RAG—showing how multi‑agent AI architectures address high‑concurrency, multimodal, and multi‑hop query challenges while delivering measurable performance gains.
Palantir’s Agent Stack introduces Orchestrator, observability, and Ontology layers to make AI agents durable, interruptible, and governed, but enterprises remain reluctant because trust, state management, permission control, and continuous evaluation are required before agents can operate on real business processes.
Palantir’s 2026 roadmap shows the company moving beyond stronger AI models toward a comprehensive engineering system that lets enterprise agents safely access business data, execute permission‑guarded actions, and integrate into decision‑making processes—a shift that reshapes AI budgets and offers a clear lens on the competitive landscape, especially for Chinese firms.
Adding memory to agents is now straightforward, but when agents run for weeks across many interactions, the real challenge shifts from merely retrieving past data to determining which past information remains valid, how to manage its lifecycle, and how to govern cost, updates, and deletion, as highlighted by Oracle's technical report and benchmark evaluations.
The article analyzes the limitations of current AI agents, proposes an ontology‑driven semantic foundation for Harness Engineering, and details three technical pillars—architectural constraints, context engineering, and feedback loops—illustrated with the Knora platform and concrete workflow examples.
PostgreSQL is attracting renewed interest not because it magically becomes an all‑purpose AI database, but because AI applications in production demand a unified, consistent platform that can manage business records, vector embeddings, agent state, permissions and tooling, and PostgreSQL’s extensible ecosystem—pgvector, serverless architectures, branching, and MCP—offers exactly that blend of relational reliability and AI‑native capabilities.
