Structured Data news and analysis on Web Pulse: 342 curated articles tracking the latest Structured Data developments, tools, and research, updated continuously from vetted sources.
A developer at AI Flip Room built a three-gate validation pipeline that checks every AI-generated room render before it reaches users, combining a structured-output vision judge, 16 indoor and 9 outdoor preservation chec…
LM-Kit released LM-Kit Document Parsing, a document parsing engine for LM-Kit.NET and LM-Kit One that scores 86.0 on ParseBench, which the company says is the best result of any self-hostable method. The parser returns t…
Main Street Wealth launched an open-source hub of M&A tools for lower middle-market deals in HVAC, plumbing, roofing, pest, landscaping, pool, and electrical services, pairing valuation calculators, quality-of-earnings c…
Arda launched a marketing agent product that tracks and improves brand visibility across Google and AI answer engines including ChatGPT, Claude, Perplexity, and Gemini, publishing CMS-ready pages, on-page fixes, comparis…
A developer built LensLink, an AI camera and lens compatibility agent that answers whether a given lens works with a given camera by querying structured Sanity content instead of relying on generic model knowledge. The a…
A developer built StudentOS Opportunity Intelligence, an AI agent that combines structured Sanity content with a student's private context to answer whether they are ready for a given internship, hackathon, or fellowship…
A developer built Pit Wall, an F1 quiz app in which an AI agent writes each question alongside the GROQ query that answers it, while the server resolves correctness from Sanity race data rather than the model's own judgm…
A developer writing for tokviewer.app's editorial team published a guide showing how Excel's 15-significant-digit numeric precision limit silently corrupts 19-digit comment identifiers during CSV imports, causing distinc…
The Standards for Publisher Usage Rights (SPUR) coalition, whose members include the Guardian, the Financial Times, the BBC, Sky, The Times of London, MediaHaus and the AP, published version 1.0 of its content telemetry …
Google revised its generative AI content guidance page on Oct. 1, adding a warning that generative models "don't retrieve facts, but predict a likely sequence of words based on their training data" and that outputs "may …
A developer built Racksmith, an autonomous modular synthesizer planner that pairs a Gemini 3.8 Flash agent via the Vercel AI SDK with a Sanity Knowledge Lake through a Model Context Protocol (MCP) server. The agent queri…
Two developers who previously worked at several business-intelligence companies released Graphene, an open-source data analysis toolkit that gives coding agents a semantic layer, MDX-like dashboard files, and connectors …
A developer building AI Product Page Optimization, a Chrome extension that reads an open product page and returns marketplace-ready title, description, and image suggestions in about 30 seconds, described the extraction …
A developer built ClauseHound, a pet-insurance decision engine that answers four shopper questions — coverage, switching, denial, renewals and appeals — strictly from insurers' published policy text, citing the exact cla…
IBM Research Zurich's open-source Docling toolkit, now hosted under the LF AI & Data Foundation and released under an MIT license, converts inconsistent document formats into a unified structured representation for both …
NVIDIA released Kumo Tabular, a family of tabular foundation models in Small, Medium, and Large sizes spanning roughly 28M to 215M parameters that predict new rows in a single forward pass with no training, hyperparamete…
Google updated its Search Central guidance on using generative AI content on October 1, 2026, adding three sentences that state generative models "don't retrieve facts, but predict a likely sequence of words based on the…
A method for converting a company's blog archive into a retrieval-ready knowledge base calls for inventorying URLs from the XML sitemap plus a crawl, extracting claims, advice and examples into dated records, and tagging…
The CM team released the CM AI Docking Port, an early single-node MVP that gives AI agents a machine-readable manifest and a live "Reception" endpoint for querying availability at one real unit without a CM-specific plug…
Amazon Web Services announced that Amazon Aurora PostgreSQL can now directly query Apache Iceberg and Apache Parquet data in a data lake, eliminating extract, transform, and load (ETL) pipelines that duplicate data. The …