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 published an Apify actor, Webpage to JSON for AI Agents, that converts any URL plus a plain-English field description into typed JSON, attaching a source quote to each extracted value. The tool supports an ex…
A community-maintained dataset of DNS hostnames for generative-AI applications and APIs has been published to let organizations measure observed AI-service access from DNS, proxy and firewall logs. Each row maps a hostna…
A developer's Illumia Archive Intelligence case study documents a local Python and PostgreSQL retrieval tool, exposed through a browser interface and a Claude Desktop MCP connection, that keeps parent cases linked to the…
The .txt team released Outlines, an open-source library that guarantees structured LLM outputs during generation rather than fixing them afterward with parsing or regex, and it is trusted by NVIDIA, Cohere, HuggingFace a…
The independent Spanish municipal-data project Callejear has exposed a read-only MCP service for Madrid (INE code 28079) that lets AI assistants query 9,400 official street codes, of which 9,151 have validated reference …
A developer published a five-minute checklist for making websites readable by AI assistants such as ChatGPT, Claude and Perplexity, covering robots.txt user agents (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, CCBo…
Canonry launched as an AI visibility tracking platform that monitors whether ChatGPT, Claude, Gemini, Perplexity, Copilot, Grok, Meta AI, and DeepSeek name a brand, cite its site, or omit it, alongside the competitors th…
Google Dataset Search has returned no results for at least 24 hours, according to a report received from Manish, with queries including "artificial intelligence" and "llm prompts site:huggingface.co" returning the messag…
TypeSafe released Jev 1.14 on October 14, adding experimental image support that accepts images as multipart/form-data file parts byte for byte instead of Base64-encoded JSON, which TypeSafe's docs say makes each image a…
A developer published a step-by-step Python approach for handling malformed JSON returned by LLMs, which fails roughly one time in 20 in production. The technique strips markdown code fences and surrounding prose, extrac…
A developer outlined an approach to building a personal knowledge graph that powers a portfolio AI assistant, using a minimal ontology of entities like Person, Project, Technology, Role, Outcome and Source connected by t…
Databricks reported that spatial SQL and spatial joins on its Lakehouse//RT real-time data warehouse run up to 38X faster than a traditional cloud data warehouse at 50 concurrent users, and 3X faster on average with up t…
A developer building the FAF project concluded that AGENTS.md and similar markdown context files are meant for instructions, not project definitions, after a 2026 study (Gloaguen et al., arXiv 2602.11988) found that repo…
A study of the robots.txt files of 285 of the most visited websites, 261 of which returned readable files, found that 35% block training crawlers such as GPTBot while only 21% block search-oriented agents like OAI-Search…
Snowflake announced general availability of Postgres data mirroring, which continuously replicates Postgres tables into Snowflake in seconds with no external infrastructure to deploy or manage. The feature captures chang…
Drupal creator Dries Buytaert exposed his 20-year-old custom photo album module's operations as AI-callable tools using the contributed Tool module's Tool API, which generates JSON Schema from PHP attributes on plain PHP…
SEO veteran Jon Henshaw released the Coywolf Pack, a modular plugin for the EmDash website platform that adds publishing, SEO, and performance features, with tested pages scoring a perfect 100 on PageSpeed Insights. The …
Skyvern, an AI browser agent built by Skyvern, automates bank statement retrieval by logging into bank portals, downloading statement PDFs, and extracting transaction data into structured tables, according to the company…
DeepLumen announced Agentic Page on October 14, a middleware layer that structures merchant product catalogs into formats AI agents can parse, index, and recommend without requiring merchants to rebuild their sites. The …
Infino is building a retrieval engine that places its full-text and vector search index directly on object storage — supporting S3, GCS and Azure Blob Storage — rather than on local disk as Lucene-based engines do. Becau…