Termsslug: ontology

Ontology

本体

A formal specification of concepts and their relationships, often used in knowledge graph construction.

Curated Intelligence

8 items · Page 1/1
Hacker News AIT2·Open Source
58 pts
Sutra-OS Launches Self-Hosted Ontology Platform with Rule-Enforced Writes

Sutra-OS is an open-source, self-hosted ontology platform that unifies organizational data into a single typed model, where every write must pass server-enforced rules and proposal approval. Key design points include full data lineage, AI agents limited to proposing changes, branchable models and data, and credentials held by a separate egress agent. The project is in beta and ships a Python SDK, CLI and REST API.

腾讯技术工程 (微信公众号)T2·Agents
62 pts
Ontology and Memory Help Coding Agents Learn Projects Over Time

The article argues that making coding agents truly project-aware requires two complementary mechanisms: an ontology that explicitly encodes domain concepts, relations and validity conditions so models understand team conventions, and recursive self-improvement (RSI) that turns execution feedback into reusable knowledge, with memory handling storage and reuse. The authors ground this in their internal Loop practice, aiming to cut the time agents spend re-learning a project and to stop them repeating mistakes the team has already resolved.

TechCrunch AIT2·Agents
62 pts
Databricks Upgrades Genie Agent for Unsupervised Multi-Step Tasks

Databricks unveiled an upgraded version of its Genie AI agent, which uses a purpose-built ontology to supply context from customer data stored on the platform, enabling unsupervised completion of multi-step, long-running tasks. CEO Ali Ghodsi demonstrated real internal usage spanning employee-satisfaction analysis, sales-pitch postmortems and interview prep, and said agent costs can be capped via Unity Gateway usage limits and cheaper open-weight model swaps.

千问AI平台 (微信公众号)T2·Models
58 pts
Alibaba Applies Ontology to Structure Business Knowledge for AI-Generated SQL

The article argues that LLM-generated SQL is now syntactically reliable, yet table selection, field usage and metric-definition errors persist because business knowledge remains fragmented and unstructured. The author proposes applying ontology to convert tacit business knowledge into AI-readable, verifiable structured assets, detailing an automatic extraction pipeline, retrieval and iteration mechanisms, plus evaluation results.

量子位官网T2·Industry
16 pts
DataFun Shanghai Meetup to Focus on Data-to-Agent Deployment Pipeline

This is a registration promo for an offline technical roadshow rather than a technical disclosure. Scheduled for the afternoon of November 10 in Shanghai's Xuhui district, the event features five speakers from firms including Ant Digital Security, Intsig, and PwC covering ontology modeling, enterprise knowledge refresh, agent harness engineering, trustworthy financial agents, and data agents for querying. No methods, parameters, or verifiable results are provided; it is useful only as an event-calendar note.

Hacker News AIT2·Agents
78 pts
NVIDIA Open-Sources Auto Ontology for Agent Data Semantics

NVIDIA has released Auto Ontology, an open-source library designed to build a unified semantic context layer for enterprise agents. By exposing validated business definitions and data lineage via MCP, CLI, and API, it addresses accuracy issues caused by semantic ambiguity in database queries, supporting automatic ontology generation from metadata with continuous improvement.

InfoQ 中文T2·Models
45 pts
Financial Ontology Construction: Four Elements and Three-Question Validation

This article explains how to construct business ontologies in financial data query scenarios using four core elements—concepts, attributes, relationships, and constraints—to translate business knowledge into structured language understandable by AI. It proposes a 'Three-Question Validation' method (Can AI understand? Can systems execute? Can the ontology stay fresh?) as an evaluation standard, comparing five industry construction routes while emphasizing that selection must balance business fit and engineering feasibility.

Hacker News AIT2·Tools
42 pts
Netflix Builds Ontology-Driven Observability Knowledge Graph

Netflix engineers detailed their implementation of an ontology-driven observability knowledge graph to manage massive real-time streaming logs. This approach leverages semantic modeling to correlate system dependencies and accelerate root cause analysis in environments where traditional dashboards fail.