{"id":6831,"date":"2026-11-02T08:12:43","date_gmt":"2026-11-02T08:12:43","guid":{"rendered":"https:\/\/i10xnews.kinsta.cloud\/?p=6831"},"modified":"2026-11-02T08:12:43","modified_gmt":"2026-11-02T08:12:43","slug":"google-ai-visit-prep-agent-rct-study","status":"publish","type":"post","link":"https:\/\/i10x.ai\/news\/google-ai-visit-prep-agent-rct-study","title":{"rendered":"Google Study: Structured AI Agent Prepares Patients for Doctor Visits Better Than a Plain Chatbot"},"content":{"rendered":"\n<h2 class=\"wp-block-heading\">\u26a1 Quick Take<\/h2>\n\n\n<ul class=\"wp-block-list\"><li><strong>The finding:<\/strong> In a randomized study with 802 US adults in the Google Health app, a structured AI agent prepared patients for doctor visits better than a plain chatbot running on the same Gemini 2.5 Flash model.<\/li><li><strong>The numbers:<\/strong> 73.8% of agent users felt prepared for their visit vs. 57.0% with the control chatbot; blinded clinicians rated 67.2% of agent sessions fully comprehensive vs. 50.6%.<\/li><li><strong>The caveat:<\/strong> Safety stayed high in both arms, but patient satisfaction and clinician-rated quality did not correlate, and the study was run and funded by Google.<\/li><\/ul>\n\n\n<p class=\"wp-block-paragraph\">Many patients already ask chatbots what to expect before a doctor&#8217;s appointment. A new preprint from Google Research, &#8220;A prospective randomized study of patient-centered AI for clinical visit preparation&#8221; by Xincheng Tan, Mike Schaekermann, Quang Duong, Jackie M. Barr and 32 co-authors, tests whether a purpose-built AI visit preparation agent actually helps, compared with a minimally prompted chatbot. It is one of the first randomized tests of a patient-facing AI tool in a real consumer app rather than a benchmark or simulation.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\ud83d\udd2c What the study shows<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">All three study arms used the same model and interface and differed only in their system prompts. The visit preparation agent (in a standard and a concise variant, pooled in the main analysis) followed a fixed workflow: gather context, set expectations for the visit, give general health information, build a prioritized list of questions for the clinician and keep a running summary.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1344\" height=\"768\" src=\"https:\/\/i10xnews.kinsta.cloud\/wp-content\/uploads\/2026\/11\/chart-google-visit-prep-agent-rct-results.webp\" alt=\"Grouped bar chart comparing the visit preparation agent with a control chatbot. Clinician ratings: comprehensiveness 67.2% vs 50.6%, patient alignment 98.9% vs 90.4%, medical safety 93.7% vs 96.4%, appropriateness 93.7% vs 91.6%. Patient survey: felt prepared 73.8% vs 57%, knew what to ask 81.4% vs 67.1%, satisfied with tool 74% vs 62%.\" class=\"wp-image-6830\" srcset=\"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/11\/chart-google-visit-prep-agent-rct-results.webp 1344w, https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/11\/chart-google-visit-prep-agent-rct-results-300x171.webp 300w, https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/11\/chart-google-visit-prep-agent-rct-results-1024x585.webp 1024w, https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/11\/chart-google-visit-prep-agent-rct-results-768x439.webp 768w\" sizes=\"auto, (max-width: 1344px) 100vw, 1344px\" \/><figcaption class=\"wp-element-caption\">i10X chart based on data from Tan et al. (2026), arXiv:2610.41437, Section 3.<\/figcaption><\/figure>\n\n\n<ul class=\"wp-block-list\"><li><strong>More complete preparation:<\/strong> Three blinded primary care physicians reviewed 272 completed sessions. Agent sessions were fully comprehensive more often (67.2% vs. 50.6%; P &lt; 0.05) and better aligned with the patient&#8217;s health context (98.9% vs. 90.4%; P &lt; 0.01).<\/li><li><strong>No loss in safety:<\/strong> Medical safety (93.7% vs. 96.4% for control) and appropriateness (93.7% vs. 91.6%) did not differ significantly. &#8220;Unsafe helpfulness&#8221;, meaning high utility with lower reliability, occurred in 2.6% of agent sessions and none of the control sessions.<\/li><li><strong>More useful safe sessions:<\/strong> Sessions rated both highly reliable and highly useful rose from 50.6% to 64.6% (P &lt; 0.05).<\/li><li><strong>Patients felt better prepared:<\/strong> In 460 post-surveys, agent users more often felt prepared (73.8% vs. 57.0%), knew what to ask (81.4% vs. 67.1%), felt able to make the most of the visit (81.4% vs. 69.6%), were satisfied (74.0% vs. 62.0%) and wanted to reuse the tool (76.6% vs. 65.8%).<\/li><li><strong>Two perspectives, no overlap:<\/strong> After correction for multiple comparisons, no patient survey item correlated significantly with any clinician rating.<\/li><\/ul>\n\n\n<figure class=\"wp-block-table\"><table><thead><tr><th>Outcome<\/th><th>Visit prep agent<\/th><th>Control<\/th><th>P<\/th><\/tr><\/thead><tbody><tr><td>Clinician: fully comprehensive<\/td><td>67.2%<\/td><td>50.6%<\/td><td>&lt; 0.05<\/td><\/tr><tr><td>Clinician: aligned with patient context<\/td><td>98.9%<\/td><td>90.4%<\/td><td>&lt; 0.01<\/td><\/tr><tr><td>Clinician: medically safe<\/td><td>93.7%<\/td><td>96.4%<\/td><td>n.s.<\/td><\/tr><tr><td>Patient: felt prepared<\/td><td>73.8%<\/td><td>57.0%<\/td><td>&lt; 0.01<\/td><\/tr><tr><td>Patient: confident what to ask<\/td><td>81.4%<\/td><td>67.1%<\/td><td>&lt; 0.01<\/td><\/tr><tr><td>Patient: satisfied with tool<\/td><td>74.0%<\/td><td>62.0%<\/td><td>&lt; 0.05<\/td><\/tr><\/tbody><\/table><figcaption class=\"wp-element-caption\">Share of sessions rated positively (4 or 5 on a 5-point scale). Source: Tan et al. (2026), arXiv:2610.41437, Sections 3.2 and 3.3.<\/figcaption><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\">\u2705 Why it matters: Structure beats raw model capability<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Because both arms ran on the same Gemini 2.5 Flash model, the gains come from how the conversation was designed, not from a stronger model. That is a useful result for anyone building health assistants: a guided workflow made patients feel more prepared without a measurable safety cost.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The design is stronger than most patient-facing AI studies. Participants were randomized, the trial was approved by the Advarra IRB and registered at ClinicalTrials.gov (NCT07552311), reporting followed CONSORT, clinicians were blinded to study arm and model, and P values were corrected for multiple testing with the Benjamini-Hochberg procedure. Completion rates were similar between arms (41.1% vs. 42.5% discontinued), which makes a biased comparison less likely.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\ud83e\uddea Method in brief<\/h2>\n\n\n<ul class=\"wp-block-list\"><li><strong>Setting:<\/strong> Decentralized study in the Google Health app on Android in the US, November 19, 2025 to May 15, 2026.<\/li><li><strong>Participants:<\/strong> 5,960 users consented and were randomized 1:2:2; 802 adults with 866 health-related conversations entered the analysis (control 141, agent 725). Mean age 50.5 years, 63.3% of conversations by women. People with known mental health conditions, STIs or pregnancy were excluded.<\/li><li><strong>Visits:<\/strong> Most common were specialist consultations (33.1%), annual wellness exams (21.8%) and chronic-condition primary care (17.0%).<\/li><li><strong>Evaluation:<\/strong> Primary outcome was the patient-reported preparation experience; secondary was blinded clinician review on medical safety, appropriateness, comprehensiveness and patient alignment; a 14-day follow-up was exploratory.<\/li><\/ul>\n\n\n<h2 class=\"wp-block-heading\">\u2753 What remains open<\/h2>\n\n\n<ul class=\"wp-block-list\"><li><strong>No clinical outcomes:<\/strong> The study measures how prepared patients felt and how clinicians rated the transcripts, not whether visits or health outcomes improved.<\/li><li><strong>Thin follow-up:<\/strong> Only 59 participants reported a doctor visit in the 14-day follow-up. 78.3% vs. 69.2% said the visit matched the expectations set by the agent, a difference that was not significant.<\/li><li><strong>Survivorship:<\/strong> 42.3% of included conversations ended early, and clinicians only rated completed sessions, so absolute quality ratings may be too high.<\/li><li><strong>Selective sample:<\/strong> Android users of the Google Health app who opted into research are likely more tech-savvy and health-literate than average patients, and education, income and ethnicity were not collected.<\/li><li><strong>Industry study:<\/strong> Google designed, ran and funded the trial. The system prompts are published in the appendix, but beyond example conversations the study data are not released.<\/li><\/ul>\n\n\n<h2 class=\"wp-block-heading\">\ud83e\udded Context: From diagnosis benchmarks to patient support<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Most medical AI research tests models on exam questions or simulated diagnoses. This study puts a <a href=\"\/news\/product\/gemini\">Gemini<\/a>-based agent in a narrower, non-diagnostic role and measures real users. That matters because other recent studies have shown the risks of chatbots in health, from <a href=\"\/news\/medical-sycophancy-ai-diagnosis-patient-beliefs\">models bending diagnoses to patient beliefs<\/a> to <a href=\"\/news\/reasoning-models-clinical-diagnosis-false-positives-study\">reasoning models producing false positives<\/a>. <a href=\"\/news\/company\/google\">Google<\/a>&#8216;s result suggests that scoping the task tightly is one way to keep that risk low. More research is collected in <a href=\"\/news\/category\/society-economy\">Society &amp; Economy<\/a>.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\ud83d\udee0\ufe0f What it means for health apps and patients<\/h2>\n\n\n<ul class=\"wp-block-list\"><li><strong>Builders:<\/strong> Prompt and workflow design can move outcomes as much as model choice. Structured steps and a running summary are cheap to add.<\/li><li><strong>Evaluators:<\/strong> Patient satisfaction is not a proxy for clinical quality. Health AI should be judged by both clinicians and users.<\/li><li><strong>Patients:<\/strong> Asking a chatbot to help you list and prioritize questions before a visit is a low-risk use, as long as it does not replace the clinician&#8217;s judgment.<\/li><\/ul>\n\n\n<h2 class=\"wp-block-heading\">\u270d\ufe0f About the analysis<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">This article is based on the full text of the preprint (arXiv:2610.41437v1, submitted October 30, 2026), including the appendix. All numbers come from the paper; i10X did not rerun the analysis. The chart was drawn by i10X from numbers stated in Section 3; arXiv lists the paper under CC BY 4.0, while the PDF carries a Google copyright notice, so no original figures were reused. The study was funded by Alphabet, and authors who are Alphabet employees may own stock. AI tools assisted with research and drafting; the selection, fact-checking and final editing were done by the i10X editorial team.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\ud83d\udd2d i10x Perspective<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">The interesting part is not that Google&#8217;s agent won, but why: the same model, given a better script, did measurably more for patients. As chatbots become the first stop before a doctor&#8217;s visit, how they are structured will matter as much as which model sits underneath.<\/p>\n\n","protected":false},"excerpt":{"rendered":"<p>In a randomized Google Health app study, a structured AI visit prep agent beat a plain chatbot on the same Gemini model: 73.8% of users felt prepared vs. 57.0%.<\/p>\n","protected":false},"author":2,"featured_media":6829,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"paper_title":"A prospective randomized study of patient-centered AI for clinical visit preparation","paper_url":"https:\/\/arxiv.org\/abs\/2610.41437","pdf_url":"https:\/\/arxiv.org\/pdf\/2610.41437v1","doi":"","arxiv_id":"2610.41437","authors":"Xincheng Tan, Matthew Thompson, Xiang Ji, Angelica Willis, Will Vaughan, Roma Ruparel, et al. (36 authors; equal leadership: Mike Schaekermann, Quang Duong, Jackie M. Barr)","institutions":"Google Research","paper_date":"2026-10-30","venue":"Preprint (arXiv cs.HC, version 1); registered trial NCT07552311","peer_reviewed":false,"code_url":"","data_url":"","funding_coi":"Funded by Alphabet Inc.; authors are Alphabet employees and may own stock. IRB: Advarra Pro00089880.","figure_license":"Own chart redrawn from numbers in Section 3","paper_license":"CC BY 4.0 (arXiv listing; PDF carries a Google copyright notice)","replication":"partial","study_models":"Gemini 2.5 Flash (control chatbot and two structured visit preparation agents, differing only in system prompts)","study_sample":"5,960 randomized users (1:2:2); 802 US adults with 866 health-related conversations analysed; 272 sessions clinician-rated; 460 post-surveys; 95 follow-ups","footnotes":"","_yoast_wpseo_primary_category":""},"categories":[13,59,52],"tags":[],"companies":[37],"products":[49],"class_list":["post-6831","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-safety-ethics-society","category-society-economy","category-studies","company-google","product-gemini"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.7 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Google Study: AI Agent Preps Patients for Doctor Visits - i10X News<\/title>\n<meta name=\"description\" content=\"Google&#039;s randomized study of 802 US adults finds a structured Gemini agent prepares patients for doctor visits better than a plain chatbot, safety intact.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/i10xnews.kinsta.cloud\/google-ai-visit-prep-agent-rct-study\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Google Study: AI Agent Preps Patients for Doctor Visits - i10X News\" \/>\n<meta property=\"og:description\" content=\"Google&#039;s randomized study of 802 US adults finds a structured Gemini agent prepares patients for doctor visits better than a plain chatbot, safety intact.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/i10xnews.kinsta.cloud\/google-ai-visit-prep-agent-rct-study\" \/>\n<meta property=\"og:site_name\" content=\"i10X News\" \/>\n<meta property=\"article:published_time\" content=\"2026-11-02T08:12:43+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/i10xnews.kinsta.cloud\/wp-content\/uploads\/2026\/11\/google-ai-visit-prep-agent-rct-study-title.webp\" \/>\n\t<meta property=\"og:image:width\" content=\"1344\" \/>\n\t<meta property=\"og:image:height\" content=\"768\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/webp\" \/>\n<meta name=\"author\" content=\"Christopher Ort\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@i10x_ai\" \/>\n<meta name=\"twitter:site\" content=\"@i10x_ai\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Christopher Ort\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/google-ai-visit-prep-agent-rct-study#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/google-ai-visit-prep-agent-rct-study\"},\"author\":{\"name\":\"Christopher Ort\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#\\\/schema\\\/person\\\/d410bb7ee72febefca2c9c369939219a\"},\"headline\":\"Google Study: Structured AI Agent Prepares Patients for Doctor Visits Better Than a Plain Chatbot\",\"datePublished\":\"2026-11-02T08:12:43+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/google-ai-visit-prep-agent-rct-study\"},\"wordCount\":1119,\"publisher\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/google-ai-visit-prep-agent-rct-study#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/11\\\/google-ai-visit-prep-agent-rct-study-title.webp\",\"articleSection\":[\"Safety, Ethics &amp; Society\",\"Society &amp; Economy\",\"Studies\"],\"inLanguage\":\"en-US\",\"dateModified\":\"2026-11-02T08:12:43+00:00\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/google-ai-visit-prep-agent-rct-study\",\"url\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/google-ai-visit-prep-agent-rct-study\",\"name\":\"Google Study: AI Agent Preps Patients for Doctor Visits - i10X News\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/google-ai-visit-prep-agent-rct-study#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/google-ai-visit-prep-agent-rct-study#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/11\\\/google-ai-visit-prep-agent-rct-study-title.webp\",\"datePublished\":\"2026-11-02T08:12:43+00:00\",\"description\":\"Google's randomized study of 802 US adults finds a structured Gemini agent prepares patients for doctor visits better than a plain chatbot, safety intact.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/google-ai-visit-prep-agent-rct-study#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/google-ai-visit-prep-agent-rct-study\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/google-ai-visit-prep-agent-rct-study#primaryimage\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/11\\\/google-ai-visit-prep-agent-rct-study-title.webp\",\"contentUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/11\\\/google-ai-visit-prep-agent-rct-study-title.webp\",\"width\":1344,\"height\":768,\"caption\":\"Illustration: i10X\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/google-ai-visit-prep-agent-rct-study#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/i10x.ai\\\/news\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Google Study: Structured AI Agent Prepares Patients for Doctor Visits Better Than a Plain Chatbot\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#website\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\",\"name\":\"i10X News\",\"description\":\"Stay updated with the latest news and announcements from i10X.\",\"publisher\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/i10x.ai\\\/news?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#organization\",\"name\":\"i10X\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/i10x-logo-180.png\",\"contentUrl\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/i10x-logo-180.png\",\"width\":180,\"height\":180,\"caption\":\"i10X\"},\"image\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/i10x_ai\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/i10x-ai\",\"https:\\\/\\\/instagram.com\\\/i10x.ai\",\"https:\\\/\\\/www.youtube.com\\\/@i10X_ai_official\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#\\\/schema\\\/person\\\/d410bb7ee72febefca2c9c369939219a\",\"name\":\"Christopher Ort\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/christopher-ort-192.webp\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/christopher-ort-192.webp\",\"contentUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/christopher-ort-192.webp\",\"caption\":\"Christopher Ort\"},\"description\":\"Christopher Ort handles SEO, AI agent workflows and PR & partnerships at i10x.ai, the all-in-one AI workspace built by i10X Global Pte. Ltd. in Singapore. He is a graduate of Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU). He is the author of \u201cThe Style Penalty\u201d, a study published on SSRN that analyses 1,576 evaluation decisions by four frontier AI models to show how AI-written CVs fare in automated hiring screens; the research has been covered by heise online and t3n.\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/author\\\/christopher-ort\",\"sameAs\":[\"https:\\\/\\\/i10x.ai\\\/blog\\\/author\\\/christopher-ort\"],\"worksFor\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#organization\"},\"alumniOf\":{\"@type\":\"EducationalOrganization\",\"name\":\"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU)\",\"url\":\"https:\\\/\\\/www.fau.eu\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Google Study: AI Agent Preps Patients for Doctor Visits - i10X News","description":"Google's randomized study of 802 US adults finds a structured Gemini agent prepares patients for doctor visits better than a plain chatbot, safety intact.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/i10xnews.kinsta.cloud\/google-ai-visit-prep-agent-rct-study","og_locale":"en_US","og_type":"article","og_title":"Google Study: AI Agent Preps Patients for Doctor Visits - i10X News","og_description":"Google's randomized study of 802 US adults finds a structured Gemini agent prepares patients for doctor visits better than a plain chatbot, safety intact.","og_url":"https:\/\/i10xnews.kinsta.cloud\/google-ai-visit-prep-agent-rct-study","og_site_name":"i10X News","article_published_time":"2026-11-02T08:12:43+00:00","og_image":[{"width":1344,"height":768,"url":"https:\/\/i10xnews.kinsta.cloud\/wp-content\/uploads\/2026\/11\/google-ai-visit-prep-agent-rct-study-title.webp","type":"image\/webp"}],"author":"Christopher Ort","twitter_card":"summary_large_image","twitter_creator":"@i10x_ai","twitter_site":"@i10x_ai","twitter_misc":{"Written by":"Christopher Ort","Est. reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/i10xnews.kinsta.cloud\/google-ai-visit-prep-agent-rct-study#article","isPartOf":{"@id":"https:\/\/i10xnews.kinsta.cloud\/google-ai-visit-prep-agent-rct-study"},"author":{"name":"Christopher Ort","@id":"https:\/\/i10x.ai\/news\/#\/schema\/person\/d410bb7ee72febefca2c9c369939219a"},"headline":"Google Study: Structured AI Agent Prepares Patients for Doctor Visits Better Than a Plain Chatbot","datePublished":"2026-11-02T08:12:43+00:00","mainEntityOfPage":{"@id":"https:\/\/i10xnews.kinsta.cloud\/google-ai-visit-prep-agent-rct-study"},"wordCount":1119,"publisher":{"@id":"https:\/\/i10x.ai\/news\/#organization"},"image":{"@id":"https:\/\/i10xnews.kinsta.cloud\/google-ai-visit-prep-agent-rct-study#primaryimage"},"thumbnailUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/11\/google-ai-visit-prep-agent-rct-study-title.webp","articleSection":["Safety, Ethics &amp; Society","Society &amp; Economy","Studies"],"inLanguage":"en-US","dateModified":"2026-11-02T08:12:43+00:00"},{"@type":"WebPage","@id":"https:\/\/i10xnews.kinsta.cloud\/google-ai-visit-prep-agent-rct-study","url":"https:\/\/i10xnews.kinsta.cloud\/google-ai-visit-prep-agent-rct-study","name":"Google Study: AI Agent Preps Patients for Doctor Visits - i10X News","isPartOf":{"@id":"https:\/\/i10x.ai\/news\/#website"},"primaryImageOfPage":{"@id":"https:\/\/i10xnews.kinsta.cloud\/google-ai-visit-prep-agent-rct-study#primaryimage"},"image":{"@id":"https:\/\/i10xnews.kinsta.cloud\/google-ai-visit-prep-agent-rct-study#primaryimage"},"thumbnailUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/11\/google-ai-visit-prep-agent-rct-study-title.webp","datePublished":"2026-11-02T08:12:43+00:00","description":"Google's randomized study of 802 US adults finds a structured Gemini agent prepares patients for doctor visits better than a plain chatbot, safety intact.","breadcrumb":{"@id":"https:\/\/i10xnews.kinsta.cloud\/google-ai-visit-prep-agent-rct-study#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/i10xnews.kinsta.cloud\/google-ai-visit-prep-agent-rct-study"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/i10xnews.kinsta.cloud\/google-ai-visit-prep-agent-rct-study#primaryimage","url":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/11\/google-ai-visit-prep-agent-rct-study-title.webp","contentUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/11\/google-ai-visit-prep-agent-rct-study-title.webp","width":1344,"height":768,"caption":"Illustration: i10X"},{"@type":"BreadcrumbList","@id":"https:\/\/i10xnews.kinsta.cloud\/google-ai-visit-prep-agent-rct-study#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/i10x.ai\/news"},{"@type":"ListItem","position":2,"name":"Google Study: Structured AI Agent Prepares Patients for Doctor Visits Better Than a Plain Chatbot"}]},{"@type":"WebSite","@id":"https:\/\/i10x.ai\/news\/#website","url":"https:\/\/i10x.ai\/news","name":"i10X News","description":"Stay updated with the latest news and announcements from i10X.","publisher":{"@id":"https:\/\/i10x.ai\/news\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/i10x.ai\/news?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/i10x.ai\/news\/#organization","name":"i10X","url":"https:\/\/i10x.ai\/news\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/i10x.ai\/news\/#\/schema\/logo\/image\/","url":"https:\/\/i10xnews.kinsta.cloud\/wp-content\/uploads\/2026\/10\/i10x-logo-180.png","contentUrl":"https:\/\/i10xnews.kinsta.cloud\/wp-content\/uploads\/2026\/10\/i10x-logo-180.png","width":180,"height":180,"caption":"i10X"},"image":{"@id":"https:\/\/i10x.ai\/news\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/i10x_ai","https:\/\/www.linkedin.com\/company\/i10x-ai","https:\/\/instagram.com\/i10x.ai","https:\/\/www.youtube.com\/@i10X_ai_official"]},{"@type":"Person","@id":"https:\/\/i10x.ai\/news\/#\/schema\/person\/d410bb7ee72febefca2c9c369939219a","name":"Christopher Ort","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/christopher-ort-192.webp","url":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/christopher-ort-192.webp","contentUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/christopher-ort-192.webp","caption":"Christopher Ort"},"description":"Christopher Ort handles SEO, AI agent workflows and PR & partnerships at i10x.ai, the all-in-one AI workspace built by i10X Global Pte. Ltd. in Singapore. He is a graduate of Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU). He is the author of \u201cThe Style Penalty\u201d, a study published on SSRN that analyses 1,576 evaluation decisions by four frontier AI models to show how AI-written CVs fare in automated hiring screens; the research has been covered by heise online and t3n.","url":"https:\/\/i10x.ai\/news\/author\/christopher-ort","sameAs":["https:\/\/i10x.ai\/blog\/author\/christopher-ort"],"worksFor":{"@id":"https:\/\/i10x.ai\/news\/#organization"},"alumniOf":{"@type":"EducationalOrganization","name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU)","url":"https:\/\/www.fau.eu"}}]}},"_links":{"self":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/posts\/6831","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/comments?post=6831"}],"version-history":[{"count":1,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/posts\/6831\/revisions"}],"predecessor-version":[{"id":6833,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/posts\/6831\/revisions\/6833"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/media\/6829"}],"wp:attachment":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/media?parent=6831"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/categories?post=6831"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/tags?post=6831"},{"taxonomy":"company","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/companies?post=6831"},{"taxonomy":"product","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/products?post=6831"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}