AI Training — How Your AI Learns Everything

Train your Vanio AI through 4 manual methods (conversations, videos, questionnaire, documents/paste) and 11 automated systems that learn from your daily operations

How AI Training Works

Vanio AI learns about your properties through 4 manual training methods and 11+ automated learning systems that run in the background. The more the AI knows, the more guest questions it handles autonomously.

Open the training modal from any listing page by clicking Train AI, or go to Settings > AI to see training scores across all listings.

Every listing has a training modal (?train=<listingId>) with three sections:

Left sidebar — Training progress by category, article counts, and an overall training score
Center — Smart guidance banner + 4 training method cards + all KB articles organized by category
Right sidebar — VanioChat with two modes: "Training Assistant" (helps draft articles) and "Guest Demo" (simulates guest conversations to test your AI)

The system recommends what to do next based on what you have already completed.

4 Manual Training Methods

Step 1: Mine from Conversations

If you have existing guest conversations (5+), this is the fastest way to train. The AI reads your message history, extracts reusable factual information, and generates knowledge base articles.

Click Mine from Conversations in the training modal
The system analyzes all conversations for this listing
Review the draft articles — each shows the extracted knowledge
Select the ones you want to keep and save

What you'll see: The tool now provides accurate feedback about mining results. Instead of generic messages, you'll get clear information about exactly how many articles were saved to your knowledge base. If the system doesn't find enough conversations to process or no new articles are generated, you'll see an appropriate message explaining what happened.

The system automatically deduplicates against existing articles (using embedding similarity) and consolidates group-level knowledge if you have multiple units in the same building.

Important: During training conversations with the Training Assistant, the AI now properly creates knowledge base entries to help improve your AI's responses to future guest questions.

Step 2: Videos & Photos

Upload a walkthrough video of your property or select from existing photos. The AI transcribes the video, identifies knowledge topics, and generates articles.

Video upload:

Click Videos & Photos in the training modal
Upload an MP4, MOV, or WebM file (up to 500MB)
The AI transcribes the video and extracts topics
Review the generated articles — toggle "embed video in article" if you want guests to see the video
Save

Photo analysis:

Switch to the Photos tab
Select property photos
The AI analyzes what it sees and generates relevant articles (room descriptions, amenities, layout)
Review and save

Step 3: Quick Questionnaire

A guided form with ~60 property-specific questions across 10 categories. Answer the questions; the AI generates KB articles from your answers.

Categories:

Check-in/Check-out (access method, lockbox, directions, checkout instructions)
Amenities (WiFi, kitchen, laundry, climate, entertainment, pool, gym, EV charging, workspace, and more)
House Rules (garbage, visitors, other rules)
Property Information (floor, bedrooms, bathrooms, parking, special features)
Travel Planning (transport, grocery, restaurants, attractions, airport, medical)
Technical Issues (WiFi troubleshooting, heating, hot water, appliance quirks, lockout, emergency)
Customer Service (host contact, building manager, maintenance, local services)
Maintenance/Housekeeping (cleaning schedule, mid-stay clean, linen, supplies)
Booking/Reservation (cancellation, minimum stay, payment, modification, deposit, extra guest fees)
Procedures (early check-in, late checkout, refunds, complaints, escalation, upsells, maintenance)
Guest Portal (portal link, early/late checkout limits, mid-stay cleaning, invoices) — only shown when the listing has an active portal

Questions are filtered by your listing's amenities — if you don't have a pool, pool questions don't appear. Some questions are pre-filled from structured data (Airbnb WiFi, directions, etc.).

Step 4: Upload Documents

Upload existing house guides, SOPs, or rules documents, or paste content directly into the platform. Supported formats: PDF, TXT, DOCX, Markdown.

Upload files:

Click Upload Documents
Drag and drop or browse for files
The AI extracts text, splits it into discrete topics, and creates KB articles
Review and save

Paste content directly:

Click Upload Documents in the training modal
Switch to the Paste content tab
Paste up to 30,000 characters of text (markdown formatting supported)
Add an optional source label (like "House Rules" or "Guest Guide")
The AI automatically organizes your pasted content into knowledge base articles
Review and save

This is perfect for quickly adding notes, policies, or instructions without creating files first.

11 Automated Learning Systems

These run in the background without any action from you. The AI gets smarter passively as you operate.

Shadow Learning

When the AI escalates a message to you (or answers with low confidence) and you reply to the guest, the system captures your response, pairs it with the guest's question, and creates a KB article. Your real answers become the AI's future responses.

Ratings Feedback (Thumbs Up / Thumbs Down)

Every AI response has a thumbs-up/thumbs-down button in the timeline. Thumbs-up validates the response and reinforces confidence. Thumbs-down flags it for correction and feeds the learning loop.

Supervisor Learning

The AI has a quality supervisor that reviews every response. When the supervisor repeatedly modifies or retries responses for the same reason, the system detects the pattern and auto-creates a KB article to prevent the mistake. Runs nightly.

Rephrase Detection

When a guest rephrases the same question within 30 minutes, the system marks the first AI response as "potentially incomplete." This feeds shadow learning — even if you don't manually flag it, the system knows the AI's answer wasn't good enough.

Repeated Questions Detection

Weekly scan that clusters recent guest questions by topic. If 3+ guests ask the same unanswered question, the system creates a training suggestion: "Multiple guests are asking about X — please provide an answer."

Gap Filler

When the accuracy evaluation finds categories where the AI scores poorly, Gap Filler searches your conversation history for host answers to those topics. If found, it auto-creates articles. If not found, it creates training suggestions asking you to fill the gap.

Implicit Validation

When an AI response gets no negative signal within 24 hours (no thumbs-down, no guest rephrase, and the conversation continued), the system marks it as implicitly validated. This feeds confidence calibration at scale.

Confidence Calibration

Tracks AI stated confidence vs actual outcomes. After enough data points per listing, the system computes calibration curves and recommends dynamic escalation thresholds — so the AI knows more precisely when to handle a question itself vs. when to escalate to you.

Cross-Customer Intelligence

Same building: When a new customer onboards units at an address where another customer already has trained units, the system auto-copies relevant KB articles (shared building info: gym, parking, trash, etc.).

Same region: For new listings in a city with existing customers, the system creates training suggestions based on common regional question patterns (local transport, popular restaurants, etc.).

Procedure Pattern Detection

When the AI handles a situation the same way 5+ times in 30 days (same sequence of tool calls), it detects the pattern and suggests saving it as an AI Skill: "I notice I handle early check-in requests the same way every time — want to save this as a procedure?"

Memory Service (Host Brain)

Three-layer memory that learns how you work:

Host preferences — stable facts about your style and decisions
Conversation summaries — compressed digests of each dashboard conversation
Behavioral patterns — aggregated patterns from your actions (updated nightly)

The AI uses this to adapt its tone, decision-making, and recommendations to match how you operate.

Training Dashboard

Go to Settings > AI > Training for the global view:

Stats — Total learning events, KB articles learned, validated responses, supervisor corrections (7d / 30d / 90d)
Training Suggestions — Questions the AI needs help with. Type an answer and click "Teach" to create a KB article instantly.
Learning Events Timeline — Chronological feed of everything the AI learned: shadow learning, ratings, supervisor corrections, auto-created articles, accuracy changes
Knowledge Base Growth — Visual breakdown of article sources: manually created, AI-generated, from chat history, imported
Accuracy Trend Chart — Line chart showing accuracy score (0-3) over time per listing
Per-Listing Scorecards — Accuracy and coverage scores per listing, with question counts

Training Score

Every listing has a training score based on questionnaire coverage: (covered applicable questions / total applicable questions) × 100. View scores on the Settings > AI page to see which listings need more training.

How the AI Finds Information

When guests ask questions, the AI searches through the right knowledge sources to give accurate answers:

Platform capabilities ("Can Vanio automate guest communications?", "What can your system do?") → Searches general platform documentation
Property-specific questions ("What's the WiFi password?", "How do I check in?") → Searches your property's knowledge base

This improved routing ensures the AI gives you accurate guidance about Vanio's features without mixing up your property information with platform capabilities.

Testing Your AI

Two ways to test:

Guest Demo (training modal right sidebar) — Chat with the AI as a guest would, for the specific listing you're training
Test AI Lab (/test-ai) — Select any listing + reservation, then chat with the AI to test responses against your KB

Improved Listing Recognition

When searching for your listings, the AI can now see both your internal listing names and the guest-facing names you've set for each property. This means the AI won't confuse which name to show to potential guests and will provide more accurate responses when discussing specific properties.

Tips

Start with Mine from Conversations if you have history — it's the fastest path to a well-trained AI
Upload a walkthrough video — 5 minutes of narration generates dozens of articles
Use the questionnaire to fill remaining gaps — the coverage score tells you what's missing
Paste content directly for quick training — no need to create files for notes, policies, or instructions you already have written
Check Training Suggestions weekly — answering 5 questions takes 2 minutes and significantly improves accuracy
Watch the accuracy trend — a rising line means your training is working
The AI learns passively from your normal operations — shadow learning, implicit validation, and supervisor learning all happen without any effort from you
During training conversations, the AI will now properly create knowledge base entries instead of tasks, making the training process more effective
Ask about Vanio's capabilities directly — the AI now correctly searches platform documentation for questions about what Vanio can do for your rental business
Pay attention to mining feedback — the tool tells you exactly what happened so you know whether to try again or move to other training methods

STRICTLY FORBIDDEN — never mention:

LLM/AI model names (Claude, GPT, OpenAI, Anthropic, Sonnet, etc.)
API endpoints, webhooks, database tables, schemas, migrations
Internal service/handler/worker/queue names
Code architecture, file paths, environment variables
Stripe Connect internals (say "payment processing")
Any implementation detail a user would never see in the UI

REQUIRED:

Write for property managers, not developers
Step-by-step instructions with UI references ("Go to Settings → ...", "Click ...")
What happens automatically (explain WHAT, never HOW technically)
[Screenshot: description] placeholders where visuals would help
Voice: "you" addressing the user. Warm, clear, confident.

Structure

What it does — 2-3 sentence overview
Getting started — step-by-step with UI references
How it works — what happens automatically, what the user sees
Key features — bullet list with brief explanations
Tips & best practices
Common questions — 2-3 FAQs