Urgent.News

What's breaking now, across thousands of outlets.

AI

Developers ask AI which tool to use. Here’s how we track the answer.

We asked Claude “Which CMS platforms support MCP integration?” It searched the web and put Webflow in its first group, The post Developers ask AI which tool to use. Here’s how we track the answer. appeared first on The New Stack .

Developers ask AI which tool to use. Here’s how we track the answer.

We asked Claude and several other AI engines which Content Management System (CMS) platforms support Multi-Channel Publishing (MCP) integration. Claude provided the most detailed response, which mentioned Webflow in its first group of headless and SaaS CMS platforms with hosted MCP servers. We ran the same question four times over a week, and Webflow appeared in 49 out of 100 responses.

However, the frequency varied greatly depending on the AI engine used, ranging from 4 out of 25 responses on Claude to 22 out of 25 on Perplexity. When an AI engine failed to mention Webflow, it meant that the developer asking the question would not have seen the recommendation, and the interaction would not be tracked on our site.

We track the responses using Webflow's AEO (AI Expected Output) system, which allows us to measure how often Webflow is mentioned across different prompts and engines. Our visibility score for the last 30 days is 47%, indicating that Webflow is mentioned in a significant portion of the responses. We also review each response to assess the accuracy and relevance of the information provided, including whether Webflow is named, its tier (official, community, or not listed), the accuracy of the description, and the type of source used.

Written by urgent.news from The New Stack's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at thenewstack.io →

More in AI

Understanding hybrid inference: the role of Firebase AI Logic: Web Architecture & Implementation Guide

Original: https://codingcat.dev/post/firebase-2025-10-understand-ai-logic-hybrid-inference Calling frontier multimodal models directly from a web or mobile client is a security minefield if you expose…

  • Hybrid inference combines on-device and cloud-hosted AI models in web apps.
  • Firebase AI Logic enables Gemini and Imagen model invocation via Firebase Web SDK.
  • Hybrid inference supports text summarization, image captioning, and real-time translation.

Extracting structured data from PDFs using Gemini 2.0 and Genkit in Firebase: Web Architecture & Implementation Guide

Original: https://codingcat.dev/post/firebase-2025-02-gemini-genkit-pdf-structured-data Building AI features in TypeScript or Go quickly turns into spaghetti when you try to bolt structured output…

  • Google released Gemini 2.0 for structured data extraction from PDFs
  • Author rebuilds sample using Genkit, an AI integration framework
  • TypeScript utility extracts invoice details like number, date, line items

More from Saturday 31 October →