AI Search news and analysis on Web Pulse: 728 curated articles tracking the latest AI Search developments, tools, and research, updated continuously from vetted sources.
A hands-on tutorial walks developers through building "Sherlock PDF," a LangChain application that searches text-based scientific PDFs and returns the best-matching passages with filename and page number, using OpenAI's …
A developer demonstrated with a self-contained SQLite FTS5 example that a RAG pipeline can retrieve the correct document ID while the text passed to the model omits the answer, because a fixed character prefix and a quer…
DeepSeek released the V4.1 Flash 1017 update, which improved all 11 of the model's published benchmarks, including Terminal-Bench 4.0 rising from 31.2% to 42.3% and DeepSWE v1.1 reaching 77%, at roughly one-sixteenth the…
SAG2, an embedding-free multi-hop retrieval architecture built on a single SQLite database, BM25, and JEV contextual evidence decisions, achieved the highest Recall@5 and Recall@10 among compared methods on 1,000-questio…
A developer ran 320 web-search sessions with Claude Code (Opus 5.5) and Codex CLI across five languages to measure whether AI coding agents search in the user's language. For local topics, Claude Code searched in the loc…
DeepSeek opened its own search engine to public access through a Search and Fetch API on 17 October 2026, returning an authority tier from 0 to 4 and a rerank_score from 0 to 3 for every result, and saying it filters SEO…
DeepSeek opened its web search and page-fetch APIs to developers on 17 Oct 2026, pricing each at $0.75 per 1,000 successful requests, with failed requests, empty search results and timeouts unbilled. DeepSeek's own searc…
A developer outlined a citation-tracing retrieval architecture for a Node.js changelog search service that keeps a cheap lexical inverted index in front of semantic reranking, storing immutable evidence IDs (doc_id, revi…
Hangzhou DeepSeek Artificial Intelligence Basic Technology Research Co. Ltd. released DeepSeek-V4.1-Flash-1017, a "minor update" to its V4.1-Flash model that the company says "reduces task execution time and output lengt…
TinyFish has made its web search capability free for AI agents, according to MarkTechPost, removing the per-request retrieval charge that search and fetch APIs typically bill. The report frames the remaining cost as mode…
Company of Craft released an IP lookup API that returns a verdict of human, proxy, bot, ai_crawler, search_bot or spoofed_crawler for a visitor's IP and request headers, letting site operators verify whether traffic clai…
A developer outlined a method for getting AI assistants and answer engines to describe a company's product accurately, centered on publishing a single clear source-of-truth page and making every other web mention agree w…
The Aachen Regional Court ruled on September 24 that Google is liable for false statements produced by its AI Mode search feature, banning Google Ireland from repeating text that wrongly stated a professor and former neu…
The Aachen Regional Court held Google liable for false statements in its AI overviews, applying the same reasoning as an earlier Munich ruling that Google had appealed and then settled, The Decoder reported. The Aachen c…
A new study analyzing 158,099 answers and 468,037 citations collected over 90 days, from 24 June to 21 September 2026, finds that AI citations in engines like ChatGPT, Gemini and Perplexity are driven mainly by what the …
Google search results and OpenAI's Responses API together surfaced only 26.2% of the pages ChatGPT cited under the GPT-5.5 Instant setting and 48.7% of the sites behind those citations, according to an arXiv preprint pos…
DeepSeek launched a Search API and a Fetch API that give agents and RAG applications access to live web content, priced at $0.75 per 1,000 successful requests. The Search API, powered by DeepSeek's in-house search engine…
DeepSeek launched its own web search engine and two API endpoints on 17 October 2026, moving its search stack off third-party providers such as Bocha and onto an in-house crawler and index that DeepSeek says covers hundr…
A first-party audit of one website's Cloudflare logs from 30 September to 17 October 2026 found that no verified AI or search crawler fetched the site's llms.txt file in 17 days, while plain HTML pages drew 15,431 reques…
A checklist published on the author's site lays out eight steps for making a website readable and citable by AI crawlers and agents, each paired with a shell-command test, drawing on 18 days of the site's Cloudflare logs…