Search
We track 43 posts about Search from 25 engineering blogs. Most active: Vercel, Elastic, Etsy. Latest post: Oct 8, 2026.
Companies writing about Search
Recent posts
Cloudflare Web Search API for AI Agents: Build a Grounded Worker (opens on the source site)
Build a Cloudflare Worker that grounds AI agents with live web results using the Web Search API (beta), and evaluate the trade-offs between AI Gateway, direct providers, and aggregators. Continue reading Cloudflare Web Search API for AI Agents: Build a Grounded Worker on SitePoint.
JSON-LD for Developers: Building Structured Data That Search and AI Systems Can Parse (opens on the source site)
null Continue reading JSON-LD for Developers: Building Structured Data That Search and AI Systems Can Parse on SitePoint.
Elastic named a Leader in the 2026 Gartner® Magic Quadrant™ for Enterprise AI Search (opens on the source site)
Elastic ·
Elastic was named a Leader in the 2026 Gartner® Magic Quadrant™ for Enterprise AI Search. We ranked #1 in the AI Automation Use Case in the companion Critical Capabilities report.
A Practical Way to Check Your AI Search Visibility (opens on the source site)
Last month, I built an AI agent that could search the web before answering a question. While working on the article around that project, I got another project idea and that was around the visibility of a website in the world of AI-powered search. The idea essentially revolves around the fact that whether the AI-powered search mentions your website in its answer or not or whether it cites your website as a source or not, and lastly, compare these resulst with the regular Google search results. Does your website show up when AI-powered search answers questions related to the topics it covers?…
AI Gateway adds Browserbase Search and Fetch tools (opens on the source site)
Vercel ·
Browserbase Search and Fetch are now available through AI Gateway. Give your models access to current information, find relevant pages, and retrieve their contents, alongside Browserbase's existing AI SDK and Vercel Marketplace integrations. AI Gateway lets you use Browserbase's tools across model providers with one API key. Add web search and page retrieval to any model that supports tool calling, and keep the same tools when you switch models. These helpers are available in AI SDK 7.0.116 and later. Update with pnpm add ai@latest and set your AI_GATEWAY_API_KEY. To add search and fetch,…
Search trace spans from the Vercel CLI (opens on the source site)
Vercel ·
You and your coding agents can now search a project’s trace spans from the terminal with vercel traces search. Each span represents one step in a request, helping you investigate errors, latency, and security-related behavior without opening the dashboard. By default, vercel traces search returns up to 100 spans from the last hour, newest first, so you can search without first finding a request or trace ID. Filter results by environment, service, span name, status, deployment ID, request ID, trace ID, or span ID, or narrow the time range with --since and --until: For filters without a…
Building Faster Prefix Search With the Trie Data Structure (opens on the source site)
Toptal ·
Returning suggestions after every keystroke is expensive when a system stores millions of entries. Find out how the trie data structure narrows each search and the most effective ways to build a working implementation in Java.
Search domains without authentication (opens on the source site)
Vercel ·
You can now discover domain names and check availability and pricing without signing in to Vercel or providing an access token. This works through the Vercel CLI and Domains Registrar API. With the Vercel CLI, search by keyword or domain fragment: With the Domains Registrar API, check up to 200 exact domain names in one request. The response shows whether each can be registered and, when available, its registration and renewal prices: Authentication is still required to buy or manage domains. Try the public domain search, or learn how to claim a free domain with Pro. Read more
Elastic announces GA of cross-project search on Serverless, enabling teams to query across all linked projects without moving a byte (opens on the source site)
Elastic ·
Cross-project search is now GA on Elastic Cloud Serverless. Link multiple projects and query all of them from a single Discover or ES|QL session: no certificates, no remote cluster config, and three clicks to set up. Available from September 1, 2026.
Have it both ways: stay discoverable in search while disallowing AI training (opens on the source site)
Cloudflare is giving site owners a way to stay discoverable while disallowing AI training. New controls and an Accountable designation establish a shared model with Apple, Google, and Microsoft.
Power Up Your AI Agent With Live Web Search, for Fewer Tokens (opens on the source site)
Give your AI agent live web search with a tool-calling loop, then cut your token cost by feeding it Markdown instead of raw JSON search results. Continue reading Power Up Your AI Agent With Live Web Search, for Fewer Tokens on SitePoint.
Tako Search is free on AI Gateway through September 30th (opens on the source site)
Vercel ·
Tako Search is free exclusively on AI Gateway through September 30th. Tako Search is a model-agnostic search tool that works with any model on AI Gateway. You can switch models while keeping the same search integration, without a separate Tako account or API key. Tako Search combines its curated knowledge graph with the live web in one response, giving models source-grounded data cards, citations, and visualizations. You can search curated data, the live web, and narrow web results by domain and publication date. To use it with the AI SDK, add gateway.tools.takoSearch() to the tools object in…
You can now read and search changelogs from the CLI (opens on the source site)
Vercel ·
You and your agents can now read and search the Vercel changelog feed from your terminal using vercel changelog. Coding agents can use this command to discover new Vercel products and features, find updates relevant to your project, and read full announcements to inform their recommendations. vercel changelog returns the latest five changelogs with full Markdown content. You can also set the number of results, search all changelogs using a keyword, and access JSON output for scripts and agents. # return the latest 5 changelogs vercel changelog # set the number of results vercel changelog…
v0 adds one-click integrations for email, auth, search, and databases (opens on the source site)
Vercel ·
We're working toward bringing parity across Vercel integration and v0, starting with Resend, Amazon OpenSearch, MongoDB Atlas, Algolia and Clerk. Prompt v0 with what you want to build, and when your prompt requires a provider, v0 renders a connect card in the chat. With Marketplace integrations in v0, you get: Connect as you build: Prompt v0 with what you want to create, and connect the required provider inline. Automatic setup: Once connected, v0 handles the required environment variables and configuration. Provider skills loaded automatically: When you connect a provider that publishes…
Elastic and Tencent Cloud deepen strategic partnership to power AI-era search foundation (opens on the source site)
Elastic ·
Tencent Cloud and Elastic announced an expanded strategic collaboration in Shenzhen in August 2026. The companies will deepen their technical and product collaboration to help enterprises establish dedicated AI search for the AI era.
AI Visibility Tools for B2B Marketers: Track – and Improve – Your Visibility in AI Search (opens on the source site)
Compare 10 AI visibility tools for B2B marketers - HeyAmos, Peec AI, Profound, Scrunch, and more, to track and improve visibility in AI search. Continue reading AI Visibility Tools for B2B Marketers: Track – and Improve – Your Visibility in AI Search on SitePoint.
The search multiplier: Driving revenue, productivity, and AI at scale (opens on the source site)
Elastic ·
An independent IDC study found organizations deploying the Elasticsearch Platform for enterprise search and agentic AI deliver AI products faster, drive higher revenue, boost productivity, and strengthen operational resilience across the business.
Did Your Last Campaign Work? Why You Need Both Social and Search Data to Know for Sure (opens on the source site)
Every campaign ends the same way: campaign managers put together a deck showing reach numbers, engagement rates, and impressions for leadership. They might even include sentiment analysis or share of voice to wow the room. But there are two questions most post-mortems never actually cover, according to Taylor Dickson, Principal Consultant at Brandwatch: Did it change how people felt? Did it change what people did? And the only way to answer these questions honestly is by looking at both social conversations and traditional search behavior together. Why most campaign measurement misses the…
Build an AI Agent with Real‑Time Web Search in JavaScript (opens on the source site)
Large language models (LLMs) are great at answering questions, but they have an important limitation: they don’t inherently have access to what’s happening on the web right now.
Cloudflare AI Search: give your agents a search engine for your data (opens on the source site)
AI Search makes search easier than ever, with no Cloudflare primitives to stitch together. Point it at your data to create a search for your own files and websites. We're also sharing a preview of our new pricing model.
Amazon DynamoDB now supports real-time vector search at any scale (opens on the source site)
AWS ·
DynamoDB now supports native vector search with single-digit millisecond latency at 99%+ recall. It is designed for any scale, even trillions of vectors and requires zero infrastructure management.
Crowdsourced taxonomy verification: A feedback-driven framework for refining knowledge graph relationships via online search interactions (opens on the source site)
Grab ·
Introduction The efficacy of semantic search relies on the accuracy of the underlying Knowledge Graph (KG). In high-velocity domains like on-demand food delivery or e-commerce, the catalog of entities like dishes, products, and merchants changes rapidly. Current methods for KG construction and maintenance face three critical challenges: Inaccuracy and hallucination from Large Language Models (LLMs): Automated models often infer relationships based on statistical text co-occurrence rather than semantic reality. For instance, an LLM might incorrectly classify “Pho” as a child of “Italian Noodle…
Blinkit at OpenSearchCon India 2026 (opens on the source site)
Grofers ·
A few weeks ago, we spoke at OpenSearchCon India about how we make search fast and reliable at scale at Blinkit.I’m Harshit, from the Search Engineering team at Blinkit, and this year we got to speak at OpenSearchCon India at the Jio World Convention Centre in Mumbai. In this post, I’ll walk you through our talk, the conversations that followed, and what our team took away from being part of the OpenSearch community in a more active way this year.First Day : Keynote by BlinkitThe highlight of this year’s conference for our team was the opportunity to deliver a keynote session at…
Personalizing Airbnb search by learning from the guest journey (opens on the source site)
Airbnb ·
How we built a Transformer-based sequence model that encodes years of guest behavior to surface the right listings at the right time.By: Daochen Zha, Chun How Tan, Xin Liu, Bin Xu, Han Zhao, Xiaowei Liu, Jun Shi, Tracy Yu, Hui Gao, Huiji Gao, Liwei He, Michael Kinoti, Stephanie Moyerman, and Sanjeev KatariyaIntroductionPlanning a trip on Airbnb rarely happens in a single session. A guest searching for a place to stay in San Francisco might browse dozens of listings over several days, leaving behind a trail of views. Typically, over a period of years, that same guest will have accumulated many…
Distilling Long-Tail User Behavior into Scalable Embeddings for Job Search (opens on the source site)
Indeed ·
Authors : Marsan Ma, Nikhil Lopes, Raj Amrit, Hong Lu, Dipankar Biswas, Trent KyonoLeadership: Iris Wang, Madhu Kurup Recommendation and ranking systems power many of the most important experiences on large internet platforms. Yet the models that run in production are rarely the largest models we can train. They are usually compact, latency-sensitive supervised models […]
From 48 Seconds to 130 Milliseconds: Vector Search in Tinybird (opens on the source site)
Tinybird ·
A customer needed semantic search over 20 million embeddings. Their first attempt timed out. Three changes turned it into sub-200ms queries. Here's what we learned.
Interpolation search for SST index blocks (opens on the source site)
RocksDB ·
For workloads with uniformly distributed keys, RocksDB now supports interpolation search for SST index blocks as an alternative to the default binary search. The idea Binary search always splits the remaining range in half: 1 mid = low + (high - low) / 2 That’s Θ(log n) probes regardless of the data. Interpolation search instead estimates where the target should land based on its value relative to the current boundaries: 1 probe = low + (target - key[low]) * (high - low) / (key[high] - key[low]) On uniformly distributed keys, that’s expected O(log log n) probes. The canonical example: for an…
How Vinted Serves Personalised Search Autocomplete (opens on the source site)
Vinted ·
At Vinted, more than 20% of all search sessions now start with a click on an autocomplete suggestion. A few years ago, that number was below 8%. Autocomplete not only saves typing effort - it helps people discover listings they didn’t know existed, and guides them toward successful searches. Today, across 24 languages and 50+ country-language combinations, we have a pool of 125 million different queries ready to suggest to users. Our service, svc-suggestions, runs on Vespa and matches and ranks 4,700 queries per second at 31 ms P99.
How Etsy Uses LLMs to Improve Search Relevance (opens on the source site)
Etsy ·
Ever searched for something specific, only to be met with results that are close, but not quite? On Etsy’s Search Relevance team, that frustration is exactly what we are tackling. Our goal is simple yet ambitious: to help buyers find exactly what they’re looking for, and to help sellers reach the people seeking their special products. Search plays a central role in that mission. Historically, Etsy’s search models have relied heavily on engagement signals – such as clicks, add-to-carts, and purchases – as proxies for relevance. These signals are objective, but they can also be biased: popular…
How Etsy Uses LLMs to Improve Search Relevance (opens on the source site)
Etsy ·
Ever searched for something specific, only to be met with results that are close, but not quite? On Etsy’s Search Relevance team, that frustration is exactly what we are tackling. Our goal is simple yet ambitious: to help buyers find exactly what they’re looking for, and to help sellers reach the people seeking their special products. Search plays a central role in that mission. Historically, Etsy’s search models have relied heavily on engagement signals – such as clicks, add-to-carts, and purchases – as proxies for relevance. These signals are objective, but they can also be biased: popular…
Related topics
This page is generated automatically from the engineering blogs we follow. Every post links to its source, where it was published. See all sources.