AI-Powered Support
Meet Scout
Plansight's embedded AI support assistant — instant answers grounded in our full knowledge base, plus a curated onboarding walkthrough that consultants can tailor to each brokerage and user type.
Plansight's embedded AI support assistant — instant answers grounded in our full knowledge base, plus a curated onboarding walkthrough that consultants can tailor to each brokerage and user type.
Scout is Plansight's embedded AI support assistant — a single widget that gives every logged-in user instant access to help, training, and support without leaving the app.
Users ask questions in plain English. Scout searches the entire knowledge base, finds the most relevant articles (plus any video transcripts attached to them), and generates a clear, conversational answer — personalized with the user's first name and aware of which screen they're on.
A curated onboarding walkthrough — a sequence of articles your onboarding consultant assembles in the admin panel. Brokers click through, mark each lesson complete, and answer a quick "Got it / Still confused" prompt. Lessons can be targeted to specific user types (broker admin, manager, broker) or brokerage types (regular vs GA), so each new user only sees what's relevant to them.
Note on the knowledge base: The full UserGuiding KB is what Scout is trained on — every article is searchable in real time and used to ground every answer. There's no separate "browse the KB" tab in the widget; Scout pulls the right article when it's relevant and links to it. Brokers who want to read the full article still can, via the source links Scout cites in its answers and via the contextual article rail that appears when the chat opens.
When a user asks a question, here's what happens behind the scenes.
Via text input or voice (built-in microphone with speech-to-text).
Connects to UserGuiding via MCP protocol. Searches all articles, filters by relevance score (minimum threshold of 25).
Top articles + any embedded video transcripts + the user's question are sent to Claude Haiku 4.5. Scout responds in natural paragraphs, using the user's first name, and links back to the source articles so brokers can read the full content if they want.
Thumbs up/down feedback is captured on every answer. Related articles are shown as clickable links that open inline.
Who asked, what they asked, whether Scout could answer, the feedback, relevance scores — all logged for analytics. Conversations are saved per user, so they can pick up right where they left off next time.
When Scout can't answer, users see a simple "Get help" link — one click, not three. Two clear options:
A persistent "Need help? Contact our team" link is always visible below the input — users are never trapped.
Scout pulls from and pushes to the tools your team already uses.
Powers all AI responses. Grounded in the live UserGuiding knowledge base (plus video transcripts attached to articles) on every query. Responds as "Scout" with a warm, professional personality.
Direct connection to your knowledge base via MCP SSE. Searches all articles in real-time, fetches full content (including any video transcripts attached to articles) so Scout can ground answers in the latest source material. Onboarding lessons in the Get Started tab also reference UserGuiding article IDs — paste an ID into the admin and the lesson title auto-fetches from the live KB.
When a knowledge-base article has an embedded Wistia video, Scout pulls the captions transcript via the Wistia API and feeds it into the AI prompt alongside the article text. This makes Scout's answers grounded in the visual training content too — even though the widget itself no longer has a separate Video Library tab.
Support ticket creation with contact association, urgency levels, and auto-captured page URLs. Chat history logging on contact records.
Serverless PostgreSQL database for conversations, analytics, tenant config, and all persistent storage. Encrypted at rest (AES-256), SOC 2 Type II certified.
Real-time notifications across dedicated channels. Monitor all conversations, get alerted on negative feedback, track resource requests, and see support tickets — all in Slack.
Four dedicated Slack channels keep the right people informed at the right time.
General Monitoring
Every question and answer flows through here. See who's asking what, whether Scout could answer, and what articles were referenced. Your pulse on how users interact with support.
Thumbs Down Alerts
When a user gives a thumbs down, the team sees it immediately — the question, the answer that didn't work, and who was affected. Direct signal for content improvement.
Training Content Pipeline
When users request a new training resource, it shows up here with their description of what they need and what they were trying to accomplish. A direct content roadmap from your users — perfect input for the Get Started lessons your onboarding team curates.
Urgent Issues
Support tickets with urgency level, description, the user's current page URL, and contact info. The support team sees it the moment it's submitted — no delay.
Scout serves multiple roles across the organization.
Deflect routine questions with AI answers. Track what users are asking to identify knowledge gaps. Use resource requests to prioritize new content. Reduce ticket volume while maintaining quality support.
New users get a Get Started walkthrough — a curated sequence of articles tailored to their user type and brokerage type. Onboarding consultants set the order, brokers mark each lesson complete, and the admin sees who's done what. Scout's chat is always there for everything else.
Analytics show exactly what features users struggle with. Unanswered questions reveal documentation gaps. Feedback data (thumbs up/down) identifies where help content needs improvement.
Tickets arrive with full context — what the user asked Scout, what page they were on, urgency level. Fewer tickets overall, and the ones that come through are higher quality.
Every interaction is tracked and queryable. Built-in endpoints provide:
Simple, maintainable, and ready for enterprise deployment.
Backend: Node.js / Express
AI: Anthropic Claude Haiku 4.5 via API
Knowledge Base: UserGuiding MCP (SSE)
Widget: Vanilla JavaScript — no frameworks, no build step
Database: Neon PostgreSQL (serverless)
Deployment: Vercel (serverless edge)
What your developer adds to the Laravel Blade layout:
<script>
window.PlansightChatConfig = {
apiUrl: 'https://scout.plansight.com',
tenantId: 'plansight',
user: {
// Identity
userId: '{{ auth()->user()->id }}',
name: '{{ auth()->user()->name }}',
email: '{{ auth()->user()->email }}',
// Brokerage — used for analytics + lesson targeting
brokerageId: '{{ auth()->user()->brokerage_id }}',
brokerageName: '{{ auth()->user()->brokerage->name }}',
brokerageType: '{{ auth()->user()->brokerage->type }}', // 'regular' | 'ga'
// Role within the brokerage — used for lesson targeting
userType: '{{ auth()->user()->role }}' // 'broker_admin' | 'broker_manager' | 'broker'
}
};
</script>
<script src="https://scout.plansight.com/chatbot.js"></script>
Two script tags. The four new fields (brokerageId, brokerageName, brokerageType, userType) let Scout's admin tools track who took which lesson and let onboarding consultants target lessons at specific user types or brokerage types. Anything missing is treated as "no targeting" so the snippet is forward-compatible — old code that doesn't pass these fields keeps working.
Every detail is designed to feel native to Plansight.
Implies wisdom and guidance. Ties into the green brand palette. Warm and approachable.
#1D3A44 Dark Green · #B4E0D8 Light Green · #FB513B Accent Orange
Barlow for headings and buttons. Inter for body text. Clean, professional, readable.
Scout speaks like a knowledgeable coworker — warm, professional, and genuinely helpful. Uses the user's first name naturally. Writes in flowing paragraphs, not robotic bullet points. Acknowledges when something is complex and walks users through it.
While processing, Scout cycles through playful status messages: "Digging through the docs...", "Connecting the dots...", "Rummaging through articles..." — with an animated spinning logo. It makes the wait feel alive and intentional.
Built with insurance industry compliance in mind.
A dismissible banner at the top of every chat session warns users: "Please don't share personal health information (PHI), Social Security numbers, or other sensitive data in this chat."
Anthropic's API does not train on customer data. All conversations are logged locally (moving to encrypted Supabase). HTTPS everywhere via Vercel. Plan for BAA with Anthropic for production.
User info comes from Laravel's authenticated session — not stored in the widget. Only logged-in Plansight users can access Scout. Auth0 handles authentication.
Deployed on Vercel (serverless) with Neon PostgreSQL. SOC 2 certified stack. Auto-deploys from GitHub. All conversations, tokens, and costs tracked in real time.
Scout isn't just trained on Plansight documentation — it understands the employee benefits industry.
A custom knowledge base of industry content gives Scout deep understanding of benefits concepts, funding models, compliance requirements, and contribution strategies. When a broker asks a question, Scout can explain both the industry concept and how to handle it in Plansight.
HMO, PPO, EPO, HDHP — plan types, design elements, deductible structures, Rx tiers, network considerations, and rating factors.
DPPO vs. DHMO, annual maximums, frequency limitations, vision allowances, and carrier landscape.
Basic vs. voluntary life, AD&D, STD/LTD, elimination periods, own-occ vs. any-occ, imputed income, and EOI requirements.
Fully insured, community-rated, level-funded, self-funded, experience-rated — when to use each and the tradeoffs.
Percentage-based, defined dollar, buy-up, salary-based, spousal surcharges, opt-out credits, and tier structures.
Tax-advantaged accounts — eligibility, contribution limits, rollover rules, ICHRA, QSEHRA, and strategic pairing with HDHPs.
Accident, critical illness, hospital indemnity, pet insurance — supplemental benefits that fill gaps in major medical coverage.
Employer mandate, affordability thresholds, essential health benefits, metal tiers, reporting requirements, and compensation disclosure.
100+ terms every broker should know — from deductibles and coinsurance to stop-loss, HIOS IDs, and situs state.
The industry knowledge base is maintained as markdown files that can be updated anytime. As Plansight adds features or the regulatory landscape changes, Scout's understanding grows with it. Your team can add new topics, update compliance information, and refine industry content without touching any code.
Scout uses Claude Haiku 4.5 via the Anthropic API — fast, accurate, and extremely affordable.
Claude Haiku 4.5 Pricing
per million tokens (input / output)
Estimated Cost Per Question
half a cent per question
Each time a user asks a question, one API call is made. This sends a system prompt (~500 tokens), the user's question (~50 tokens), and 3–5 relevant articles plus their video transcripts (~2,000–4,000 tokens) as input. Claude responds with ~300–500 tokens. At Haiku 4.5 rates, a typical question costs about half a cent. Token usage and costs are tracked in real time in the Admin dashboard.
| Monthly Volume | Input Tokens | Output Tokens | Estimated Cost |
|---|---|---|---|
| 500 questions/mo Small team, early adoption |
~2.5M tokens | ~250K tokens | ~$3/mo |
| 2,000 questions/mo Growing user base |
~10M tokens | ~1M tokens | ~$12/mo |
| 5,000 questions/mo Full rollout |
~25M tokens | ~2.5M tokens | ~$30/mo |
| 10,000 questions/mo High-volume enterprise |
~50M tokens | ~5M tokens | ~$60/mo |
With prompt caching enabled, real-world costs could be 50–70% lower than the estimates above.
Only the Ask Scout AI chat incurs Claude API costs. The Get Started tab pulls articles directly from UserGuiding — no AI tokens consumed.
Current status and planned enhancements.
Plansight's support experience has two complementary layers. They work together — not as replacements for each other.
Contextual help that follows you
Hubs are UserGuiding's native sliding panel — they automatically update content based on which page you're on. On the Dashboard, you see Dashboard help. On an RFP, you see RFP resources.
AI-powered help + targeted onboarding
Scout is a custom-built AI assistant that lives on every page, all the time. Users ask questions in plain English and get instant answers drawn from the entire knowledge base — not just the current page. Onboarding consultants curate a Get Started sequence, and lessons can be targeted to specific user types or brokerage types.
A user working on an RFP might open the Hub to follow the step-by-step RFP checklist. But when they hit an unexpected question — "Can I change the situs state after sending?" — they ask Scout, who searches the entire knowledge base and gives an instant answer.
Hubs handle the structured, contextual learning path. Scout handles the unstructured, on-demand questions. Together, users never get stuck.
Scout gives your brokers the support they need, the moment they need it — so they can focus on relationships, not searching for answers.