{"id":2619,"date":"2026-06-07T11:43:40","date_gmt":"2026-06-07T11:43:40","guid":{"rendered":"https:\/\/test.liviagents.ai\/?page_id=2619"},"modified":"2026-06-08T22:52:12","modified_gmt":"2026-06-08T22:52:12","slug":"faq","status":"publish","type":"page","link":"https:\/\/liviagents.ai\/index.php\/faq\/","title":{"rendered":"FAQ"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-page\" data-elementor-id=\"2619\" class=\"elementor elementor-2619\" data-elementor-post-type=\"page\">\n\t\t\t\t<div class=\"elementor-element elementor-element-eac8f57 e-con-full e-flex e-con e-parent\" data-id=\"eac8f57\" data-element_type=\"container\" data-e-type=\"container\" data-settings=\"{&quot;background_background&quot;:&quot;classic&quot;}\">\n\t\t<div class=\"elementor-element elementor-element-666f4cb e-con-full e-flex e-con e-child\" data-id=\"666f4cb\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t\t<h1 data-interaction-id=\"2478be1\" class=\"e-2478be1-42f051e e-heading-base\" data-e-type=\"widget\" data-id=\"2478be1\">Frequently Asked Questions\u200b<\/h1>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-ec21a15 e-flex e-con-boxed e-con e-child\" data-id=\"ec21a15\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-2603fab elementor-widget elementor-widget-text-editor\" data-id=\"2603fab\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p>Here, you&#8217;ll find answers to the most common questions about our AI platform tailored for clinical research. We aim to provide clarity on how our technology can help you innovate in your field. Your journey begins here\u2014let\u2019s explore how we can assist you.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-ee66636 e-flex e-con-boxed e-con e-parent\" data-id=\"ee66636\" data-element_type=\"container\" data-e-type=\"container\" data-settings=\"{&quot;background_background&quot;:&quot;classic&quot;}\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-9c49d83 elementor-widget elementor-widget-shortcode\" data-id=\"9c49d83\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"shortcode.default\">\n\t\t\t\t\t\t\t<div class=\"elementor-shortcode\"><div id='livi-faq'><div class='faq-wrap'><div class='faq-grid'><nav class='faq-rail' id='faqRail' aria-label='FAQ categories'><span class='faq-rail-title'>Categories<\/span><a class='rail-link' data-target='g-cost'><span class='ri'><svg viewBox='0 0 24 24' fill='none' stroke='currentColor' stroke-width='2'><rect x='3' y='11' width='18' height='11' rx='2'\/><path d='M7 11V7a5 5 0 0 1 10 0v4'\/><\/svg><\/span>Cost<span class='rc'>1<\/span><\/a><a class='rail-link' data-target='g-evaluation'><span class='ri'><svg viewBox='0 0 24 24' fill='none' stroke='currentColor' stroke-width='2'><rect x='3' y='11' width='18' height='11' rx='2'\/><path d='M7 11V7a5 5 0 0 1 10 0v4'\/><\/svg><\/span>Evaluation<span class='rc'>4<\/span><\/a><a class='rail-link' data-target='g-getting-started'><span class='ri'><svg viewBox='0 0 24 24' fill='none' stroke='currentColor' stroke-width='2'><rect x='3' y='11' width='18' height='11' rx='2'\/><path d='M7 11V7a5 5 0 0 1 10 0v4'\/><\/svg><\/span>Getting Started<span class='rc'>1<\/span><\/a><a class='rail-link' data-target='g-privacy'><span class='ri'><svg viewBox='0 0 24 24' fill='none' stroke='currentColor' stroke-width='2'><rect x='3' y='11' width='18' height='11' rx='2'\/><path d='M7 11V7a5 5 0 0 1 10 0v4'\/><\/svg><\/span>Privacy<span class='rc'>4<\/span><\/a><a class='rail-link' data-target='g-security'><span class='ri'><svg viewBox='0 0 24 24' fill='none' stroke='currentColor' stroke-width='2'><rect x='3' y='11' width='18' height='11' rx='2'\/><path d='M7 11V7a5 5 0 0 1 10 0v4'\/><\/svg><\/span>Security<span class='rc'>2<\/span><\/a><\/nav><div class='faq-content' id='faqContent'><section class=\"faq-group\" id=\"g-cost\"><div class=\"group-head\"><span class=\"gi\"><svg viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\"><rect x=\"3\" y=\"11\" width=\"18\" height=\"11\" rx=\"2\"\/><path d=\"M7 11V7a5 5 0 0 1 10 0v4\"\/><\/svg><\/span><h2>Cost<\/h2><\/div><div class=\"faq-item\"><button class=\"faq-q\" aria-expanded=\"true\">How much does Livi cost?<span class=\"faq-chevron\"><svg viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2.5\"><polyline points=\"6 9 12 15 18 9\"\/><\/svg><\/span><\/button><div class=\"faq-a-wrap\"><div class=\"faq-a\"><div class=\"faq-a-inner\">\n<p class=\"wp-block-paragraph\">Pricing depends on how you deploy \u2014 the number of agents, patient or conversation volume, the integrations you need (EHR, wearables, Centralive), and your support and compliance requirements. Because clinical and research deployments vary widely, we scope pricing per request.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n<\/div><\/div><\/div><\/div><\/section><section class=\"faq-group\" id=\"g-evaluation\"><div class=\"group-head\"><span class=\"gi\"><svg viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\"><rect x=\"3\" y=\"11\" width=\"18\" height=\"11\" rx=\"2\"\/><path d=\"M7 11V7a5 5 0 0 1 10 0v4\"\/><\/svg><\/span><h2>Evaluation<\/h2><\/div><div class=\"faq-item\"><button class=\"faq-q\" aria-expanded=\"true\">Can we define our own evaluation criteria?<span class=\"faq-chevron\"><svg viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2.5\"><polyline points=\"6 9 12 15 18 9\"\/><\/svg><\/span><\/button><div class=\"faq-a-wrap\"><div class=\"faq-a\"><div class=\"faq-a-inner\">\n<p class=\"wp-block-paragraph\">Yes \u2014 evaluation in Livi is yours to design. You can define the metrics that matter for your use case, set how each is scored, and assign the pass\/fail thresholds an agent must meet before it's considered ready. Out of the box you get clinically relevant measures like Clinical Accuracy, Guardrail Compliance, Source Grounding, and Edge-Case Handling, but you're free to add, adjust, or weight criteria to fit your protocol or care standards. Evaluation is layered: Livi ships with built-in evaluation tools and standard metrics as a baseline, and your team adds its own domain-specific metrics, scores, and thresholds on top \u2014 so every agent is measured against both our standard and yours.<\/p>\n<\/div><\/div><\/div><\/div><div class=\"faq-item\"><button class=\"faq-q\" aria-expanded=\"true\">How do we actually test an agent?<span class=\"faq-chevron\"><svg viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2.5\"><polyline points=\"6 9 12 15 18 9\"\/><\/svg><\/span><\/button><div class=\"faq-a-wrap\"><div class=\"faq-a\"><div class=\"faq-a-inner\">\n<p class=\"wp-block-paragraph\">Two ways, and you can mix them. Run your agent against a benchmark of test scenarios for automated, repeatable scoring, or test it manually \u2014 chatting with the agent yourself, reviewing individual responses, and scoring them by hand. Both feed into the same evaluation view, so you get a complete picture of how the agent performs across automated and human judgment.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n<\/div><\/div><\/div><\/div><div class=\"faq-item\"><button class=\"faq-q\" aria-expanded=\"true\">How do we know an agent is accurate and safe before we deploy it?<span class=\"faq-chevron\"><svg viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2.5\"><polyline points=\"6 9 12 15 18 9\"\/><\/svg><\/span><\/button><div class=\"faq-a-wrap\"><div class=\"faq-a\"><div class=\"faq-a-inner\">\n<p class=\"wp-block-paragraph\">Because you deploy with evidence, not assumptions. By the time an agent goes live, it has been measured against the metrics and thresholds you defined and tested against your benchmark and\/or your own manual review \u2014 producing an overall agent score plus a breakdown of which checks passed and which need attention. Grounded in your uploaded content and governed by your guardrails (source citations, no self-diagnosis, auto-escalation), the agent ships validated to your standard. Our evaluation approach is grounded in peer-reviewed research on measuring the accuracy, safety, and trustworthiness of healthcare conversational AI \u2014 published in <a href=\"https:\/\/www.nature.com\/articles\/s41746-024-01074-z\">Nature Digital Medicine<\/a>, <a href=\"https:\/\/www.sciencedirect.com\/science\/article\/pii\/S2352648324000217\">Smart Health (ScienceDirect)<\/a>, <a href=\"https:\/\/ieeexplore.ieee.org\/abstract\/document\/10781547\/\">IEEE<\/a>, and <a href=\"https:\/\/arxiv.org\/abs\/2408.04650\">arXiv<\/a>.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n<\/div><\/div><\/div><\/div><div class=\"faq-item\"><button class=\"faq-q\" aria-expanded=\"true\">Is evaluation a one-time gate, or part of the design process?<span class=\"faq-chevron\"><svg viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2.5\"><polyline points=\"6 9 12 15 18 9\"\/><\/svg><\/span><\/button><div class=\"faq-a-wrap\"><div class=\"faq-a\"><div class=\"faq-a-inner\">\n<p class=\"wp-block-paragraph\">It's interactive and iterative. As you build and refine an agent, you can evaluate it, see where it falls short, update your metrics, thresholds, or guardrails, and re-test \u2014 all in the same loop. Evaluation isn't a checkpoint you pass once; it evolves alongside your agent so the rules keep pace with how you want it to behave.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n<\/div><\/div><\/div><\/div><\/section><section class=\"faq-group\" id=\"g-getting-started\"><div class=\"group-head\"><span class=\"gi\"><svg viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\"><rect x=\"3\" y=\"11\" width=\"18\" height=\"11\" rx=\"2\"\/><path d=\"M7 11V7a5 5 0 0 1 10 0v4\"\/><\/svg><\/span><h2>Getting Started<\/h2><\/div><div class=\"faq-item\"><button class=\"faq-q\" aria-expanded=\"true\">Who is Livi for?<span class=\"faq-chevron\"><svg viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2.5\"><polyline points=\"6 9 12 15 18 9\"\/><\/svg><\/span><\/button><div class=\"faq-a-wrap\"><div class=\"faq-a\"><div class=\"faq-a-inner\">\n<p class=\"wp-block-paragraph\">Livi is built for healthcare organizations and clinical and translational scientists \u2014 care teams, research groups, and digital health programs that want to turn their own approved content and real-world data into interactive agents. It's designed for teams that need engagement to reflect their clinical standards and stay under their control, whether they're running a study, supporting patients between visits, or scaling a care program.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n<\/div><\/div><\/div><\/div><\/section><section class=\"faq-group\" id=\"g-privacy\"><div class=\"group-head\"><span class=\"gi\"><svg viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\"><rect x=\"3\" y=\"11\" width=\"18\" height=\"11\" rx=\"2\"\/><path d=\"M7 11V7a5 5 0 0 1 10 0v4\"\/><\/svg><\/span><h2>Privacy<\/h2><\/div><div class=\"faq-item\"><button class=\"faq-q\" aria-expanded=\"true\">Do you use our clinical content or patient data to train AI models?<span class=\"faq-chevron\"><svg viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2.5\"><polyline points=\"6 9 12 15 18 9\"\/><\/svg><\/span><\/button><div class=\"faq-a-wrap\"><div class=\"faq-a\"><div class=\"faq-a-inner\">\n<p class=\"wp-block-paragraph\">No. Your uploaded guidelines, educational materials, and patient data are used to power and personalize <em>your<\/em> agent \u2014 not to train third-party foundation models or any model shared across customers. Your knowledge base stays yours.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n<\/div><\/div><\/div><\/div><div class=\"faq-item\"><button class=\"faq-q\" aria-expanded=\"true\">Is Livi HIPAA compliant, and how is patient data kept private?<span class=\"faq-chevron\"><svg viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2.5\"><polyline points=\"6 9 12 15 18 9\"\/><\/svg><\/span><\/button><div class=\"faq-a-wrap\"><div class=\"faq-a\"><div class=\"faq-a-inner\">\n<p class=\"wp-block-paragraph\">Yes \u2014 Livi is built to be HIPAA-compliant from the ground up. Protected health information (PHI) is safeguarded throughout the platform, and PHI redaction is one of the default guardrails you can enforce on every agent. Patient data drawn from EHRs, wearables, and EMAs is used only to ground and personalize the agent's responses for that patient \u2014 never exposed beyond the controls you configure.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n<\/div><\/div><\/div><\/div><div class=\"faq-item\"><button class=\"faq-q\" aria-expanded=\"true\">What patient data does Livi access, and who can see it?<span class=\"faq-chevron\"><svg viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2.5\"><polyline points=\"6 9 12 15 18 9\"\/><\/svg><\/span><\/button><div class=\"faq-a-wrap\"><div class=\"faq-a\"><div class=\"faq-a-inner\">\n<p class=\"wp-block-paragraph\">Livi connects to the sources you authorize: EHR records, wearable and biosignal data, and EMAs (delivered through our Centralive integration). Access is governed by your role-based permissions, so clinicians, researchers, and patients each see only what they should.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n<\/div><\/div><\/div><\/div><div class=\"faq-item\"><button class=\"faq-q\" aria-expanded=\"true\">Who owns the agents, content, and IP created on Livi?<span class=\"faq-chevron\"><svg viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2.5\"><polyline points=\"6 9 12 15 18 9\"\/><\/svg><\/span><\/button><div class=\"faq-a-wrap\"><div class=\"faq-a\"><div class=\"faq-a-inner\">\n<p class=\"wp-block-paragraph\">You do. Your approved clinical content, your real-world data, the agents you build, and the conversations they produce remain your intellectual property \u2014 Livi does not claim ownership of them and never reuses them for another customer. Livi retains the IP for the underlying platform and tooling (built on the open-source, peer-reviewed openCHA framework), but everything you create on top of it is yours to keep, export, and control.<\/p>\n<\/div><\/div><\/div><\/div><\/section><section class=\"faq-group\" id=\"g-security\"><div class=\"group-head\"><span class=\"gi\"><svg viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\"><rect x=\"3\" y=\"11\" width=\"18\" height=\"11\" rx=\"2\"\/><path d=\"M7 11V7a5 5 0 0 1 10 0v4\"\/><\/svg><\/span><h2>Security<\/h2><\/div><div class=\"faq-item\"><button class=\"faq-q\" aria-expanded=\"true\">How do you stop an agent from giving unsafe or out-of-scope medical advice?<span class=\"faq-chevron\"><svg viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2.5\"><polyline points=\"6 9 12 15 18 9\"\/><\/svg><\/span><\/button><div class=\"faq-a-wrap\"><div class=\"faq-a\"><div class=\"faq-a-inner\">\n<p class=\"wp-block-paragraph\">Safety is enforced by configurable guardrails rather than left to chance. You can block diagnosis claims, prevent self-diagnosis, require every answer to cite its source, and set automatic escalation to a human provider when a conversation crosses a clinical threshold (for example, a patient reporting severe symptoms). These rules are encoded once and applied to every interaction.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n<\/div><\/div><\/div><\/div><div class=\"faq-item\"><button class=\"faq-q\" aria-expanded=\"true\">How is our data protected?<span class=\"faq-chevron\"><svg viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2.5\"><polyline points=\"6 9 12 15 18 9\"\/><\/svg><\/span><\/button><div class=\"faq-a-wrap\"><div class=\"faq-a\"><div class=\"faq-a-inner\">\n<p class=\"wp-block-paragraph\">Data is encrypted in transit and at rest, access is restricted through role-based permissions, and activity is logged for auditability. Security is layered: Livi maintains its own internal security standards, metrics, and technical safeguards as a baseline \u2014 and your team adds its domain-specific security and compliance requirements on top, so every agent meets both our standard and yours. Because guardrails like PHI protection and required source citations run at the response level, safety isn't only a network concern.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n<\/div><\/div><\/div><\/div><\/section><\/div><\/div><\/div><\/div><\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-3ed96e3 elementor-widget elementor-widget-html\" data-id=\"3ed96e3\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"html.default\">\n\t\t\t\t\t<script>\n(function(){\n  var root = document.getElementById('livi-faq');\n  if(!root) return;\n\n  \/* ---- accordion ---- *\/\n  root.querySelectorAll('.faq-q').forEach(function(btn){\n    btn.addEventListener('click', function(){\n      var item = btn.closest('.faq-item');\n      var open = item.classList.toggle('open');\n      btn.setAttribute('aria-expanded', open ? 'true' : 'false');\n    });\n  });\n\n  \/* ---- reveal on scroll ---- *\/\n  var io = new IntersectionObserver(function(es){\n    es.forEach(function(e){ if(e.isIntersecting){ e.target.classList.add('in'); io.unobserve(e.target); } });\n  }, {threshold:.12});\n  root.querySelectorAll('.faq-item').forEach(function(el,i){\n    el.style.transitionDelay = (Math.min(i,6)*40)+'ms';\n    io.observe(el);\n  });\n\n  \/* ---- sidebar: smooth scroll ---- *\/\n  var offset = parseInt(getComputedStyle(root).getPropertyValue('--nav-offset')) || 96;\n  var links = Array.prototype.slice.call(root.querySelectorAll('.rail-link'));\n  links.forEach(function(link){\n    link.addEventListener('click', function(e){\n      e.preventDefault();\n      var t = document.getElementById(link.dataset.target);\n      if(!t) return;\n      var y = t.getBoundingClientRect().top + window.pageYOffset - offset - 8;\n      window.scrollTo({top:y, behavior:'smooth'});\n    });\n  });\n\n  \/* ---- scrollspy ---- *\/\n  var groups = Array.prototype.slice.call(root.querySelectorAll('.faq-group'));\n  var spy = new IntersectionObserver(function(es){\n    es.forEach(function(e){\n      if(e.isIntersecting){\n        links.forEach(function(l){ l.classList.toggle('active', l.dataset.target === e.target.id); });\n      }\n    });\n  }, {rootMargin:'-'+(offset+20)+'px 0px -65% 0px', threshold:0});\n  groups.forEach(function(g){ spy.observe(g); });\n})();\n<\/script>\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>Frequently Asked Questions\u200b Here, you&#8217;ll find answers to the most common questions about our AI platform tailored for clinical research. We aim to provide clarity on how our technology can help you innovate in your field. Your journey begins here\u2014let\u2019s explore how we can assist you.<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-2619","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/liviagents.ai\/index.php\/wp-json\/wp\/v2\/pages\/2619","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/liviagents.ai\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/liviagents.ai\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/liviagents.ai\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/liviagents.ai\/index.php\/wp-json\/wp\/v2\/comments?post=2619"}],"version-history":[{"count":57,"href":"https:\/\/liviagents.ai\/index.php\/wp-json\/wp\/v2\/pages\/2619\/revisions"}],"predecessor-version":[{"id":2947,"href":"https:\/\/liviagents.ai\/index.php\/wp-json\/wp\/v2\/pages\/2619\/revisions\/2947"}],"wp:attachment":[{"href":"https:\/\/liviagents.ai\/index.php\/wp-json\/wp\/v2\/media?parent=2619"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}