Agent experience from business sites beats talk for AI answers
AX is the New AEO
Artificial IntelligenceInformation Retrieval
Summary
Businesses have been told to spread information about themselves across the web to show up in AI-generated answers. The authors found that this isn’t enough anymore because AI agents now actually visit the business’s own website to get information. If the site is easy for the AI to read (agent experience), the AI gives better, more accurate answers. The authors tested thousands of questions about over a thousand businesses and showed that having a readable site leads to answers that use the business's own pages much more and are nearly twice as likely to be recommended.
What this means in practice
- •For digital marketing teams: Optimize business websites to improve AI agent readability for more accurate and recommended answers in AI-driven buyer questions.
- •For customer support teams: Improve website content structure to increase chances that AI answering agents fetch direct, accurate answers from official pages.
Authors
Ido Finder, Assaf Elovic, Gad Shalev
Abstract
In 2023, AI models answered from training data and hallucinated when it ran out, and businesses were told to seed that knowledge. Models' training knowledge has since given way to live web search, and the advice followed it there: answer-engine optimization, or AEO, now tells businesses to scatter breadcrumbs across forum threads, listicles, and off-site citations, so AI engines are likelier to surface and recommend them. But being surfaced is no longer enough: an agent opens the results and reads them before deciding, and one buyer question sends it through several rounds of search and fetch. What decides the outcome at this drill-down step is whether the agent can fetch and read the business's own site: agent experience (AX). We argue that AX is the new AEO. We run 37,927 agent journeys, each a buyer question about a business, across four independent harnesses over 1,056 real businesses, matched on fame, prior model knowledge, and two AEO proxies, then split based on their AX level. Only 7-10% of the finished answer comes from the model's training knowledge, whether or not the site is readable. Agent-ready businesses have answers built from their own pages 78% of the time against 56% and are clearly recommended 1.9x more often, while every grounded answer about a not-agent-ready business costs the agent 64% more. Holding business, harness, and question fixed, answers built from the site are 41% more accurate. The dominant failure is not fabrication but omission: web-built answers are 3.7x more likely to contain none of the facts the buyer asked for. Baselines differ sharply across the four harnesses, with clear-recommendation rates varying sevenfold from stack to stack, yet the effect holds in every one. In the agentic web era, being readable beats being talked about, and improving a site's AX is the strongest lever a business has.