21.1 Overview

Live Chat is AIUNIFY PROS SUITE’s RAG-powered support-agent workspace for creating an AI assistant that answers questions from a subscriber-controlled Knowledge Base.

The current interface identifies the workspace as:

Live Chat Support

and displays the badge:

RAG Powered

with the description:

“Train your AI assistant with your documents. Get accurate, grounded responses based only on your uploaded content.”

Live Chat currently provides subscriber-facing workflows for:

  1. Building a support Knowledge Base
  2. Uploading PDF, DOCX, and TXT documents
  3. Importing website content from a URL
  4. Monitoring document/indexing status
  5. Removing Knowledge Base documents
  6. Testing the trained assistant
  7. Sending text questions
  8. Sending reference images in Chat
  9. Receiving Markdown-formatted AI responses
  10. Copying an embed script
  11. Embedding the Chat experience on a website
  12. Using an account/support-context parameter in the standalone widget
  13. Reviewing Knowledge Base totals and indexing status

The operating concept is:

Add Business Knowledge → Index It → Test the AI → Embed the Support Widget

21.2 Where Live Chat Is Located

Navigate to:

Sidebar → Core Tools → Live Chat

The current route is:

/support-agent

and the Sidebar marks Live Chat as a New Core Tool.

21.3 Live Chat Is Different from AI Chat

PROS SUITE contains both:

Live Chat

/support-agent

Designed around:

  1. Your documents
  2. Imported website knowledge
  3. RAG-based support responses
  4. Website embedding
  5. Customer/support use

AI Chat

/chat

Designed as the general PROS SUITE conversational AI workspace.

The Sidebar presents them as separate Core Tools.

21.4 Live Chat Is Also Different from AI Voice Agent

AI Voice Agent is the dedicated voice interaction system.

Live Chat is currently a text/image-based RAG support interface.

Do not expect Live Chat to provide the microphone/voice-session workflow of AI Voice Agent.

21.5 Live Chat vs. the Separate AIUNIFY Chat System

Within this PROS SUITE manual, Live Chat means the RAG-powered support-agent builder at /support-agent.

It should not be confused with AIUNIFY’s separate Chat product/system. This chapter covers only the subscriber controls verified inside AIUNIFY PROS SUITE.

21.6 RAG Powered

The interface prominently labels Live Chat:

RAG Powered.

RAG means the assistant is designed to answer by retrieving relevant information from indexed Knowledge Base content and using that information when producing its response.

For the subscriber, the practical model is:

Your Content

Indexing

Relevant Knowledge Retrieved

AI Response

21.7 Knowledge Comes Before Chat

Unlike a general AI Chat tool, Live Chat is specifically designed around content you add.

The interface's own four-step explanation is:

  1. Add Content — Upload docs or provide website URLs
  2. Auto-Index — AI processes and indexes content
  3. Test Chat — Try queries in the preview
  4. Embed — Add widget to your website


21.8 Main Live Chat Workspace

The current Live Chat page contains several major areas:

Header

Live Chat Support / RAG Powered

Knowledge Status

  1. Documents
  2. Indexed
  3. Processing
  4. Errors

Knowledge Base

  1. File Upload
  2. URL Import
  3. Your Documents

Website Deployment

  1. Embed on Your Website

Testing

  1. Test Your Agent
  2. Launch Preview

Guidance

  1. How It Works


21.9 Knowledge Status Bar

At the top of the workspace are four status Cards:

  1. Documents
  2. Indexed
  3. Processing
  4. Errors


21.10 Documents

Documents displays the total number of currently loaded Knowledge Base document entries.

It is calculated from the current document list.

21.11 Indexed

Indexed counts documents whose current status is:

completed.

These are represented in the document list using the visible label:

Indexed.

21.12 Processing

Processing counts Knowledge Base entries that are still being processed/indexed.

21.13 Errors

Errors counts document entries whose current status is:

error.

Use this as a quick indicator that one or more Knowledge Base entries require attention.

21.14 Knowledge Base

The primary content-management Card is titled:

Knowledge Base

with:

“Upload documents to train your support agent”.

21.15 Two Knowledge-Input Methods

Knowledge Base currently provides two tabs:

File Upload

Upload a supported document.

URL Import

Provide a website URL for indexing.


21.16 File Upload

Select:

File Upload

to add a document from your device.

The upload area displays:

“Drop files here or click to upload”.

21.17 Supported File Types

The current file selector accepts:

  1. .pdf
  2. .docx
  3. .txt


The interface states:

“PDF, DOCX, or TXT • Max 10MB per file”.

21.18 File-Type Limitation

The current Knowledge Base upload control does not establish support for:

  1. XLSX
  2. CSV
  3. PPTX
  4. Images
  5. Audio
  6. Video
  7. ZIP files

as Knowledge Base document uploads.

Use PDF, DOCX, or TXT for the current verified workflow.

21.19 10 MB Upload Label

The visible interface states:

Max 10MB per file.

The backend upload handler is outside the sanitized source bundle, so this manual treats 10 MB as the current UI limit rather than independently auditing server enforcement.

21.20 One File per Selection

The current file input does not use a multiple-file selection attribute, and the upload handler retrieves the first selected file.

For predictable operation:

Upload documents one at a time.

21.21 Recommended Knowledge Base Documents

Useful support Knowledge Base content can include:

  1. Product manuals
  2. Service descriptions
  3. FAQs
  4. Pricing explanations
  5. Policy documents
  6. Customer onboarding guides
  7. Troubleshooting instructions
  8. Product specifications
  9. Internal approved support scripts
  10. User instructions
  11. Terms relevant to customer support

Only upload content that is appropriate for the assistant to use when answering users.

21.22 Uploading a Document

To add a document:

  1. Open Live Chat.
  2. Find Knowledge Base.
  3. Select File Upload.
  4. Click the Upload area.
  5. Select a PDF, DOCX, or TXT file.
  6. Wait for the upload/indexing process.
  7. Confirm the success message.
  8. Review Your Documents.

21.23 Uploading and Indexing

When an upload begins, Live Chat displays:

Uploading and indexing document...

The workflow therefore combines document submission with Knowledge Base indexing.

21.24 Successful Document Indexing

If the upload/index operation succeeds, Live Chat displays:

Document indexed successfully!

It then refreshes the document list.

21.25 Do Not Test Immediately Before Indexing Completes

If a document is still marked:

Processing

allow indexing to complete before relying on it for support answers.

For best results, test after the content is marked:

Indexed.

21.26 Upload Failed

When the upload process reports a problem, the Knowledge Base area can display:

Upload Failed

followed by the current error.

21.27 Upload Failure Toast

The current upload workflow can also display:

Upload failed

when the operation is rejected.

Review the displayed error before retrying.

21.28 Environment Setup Error

One source-defined error condition displays:

Database setup required.

The underlying UI may include technical setup wording, but ordinary subscribers should not attempt backend/database administration as part of this User Operations Manual.

If you encounter this error:

Contact the appropriate AIUNIFY support or system administrator.

21.29 URL Import

Knowledge Base also provides:

URL Import.

Use this when the information you want indexed is available on a website.

21.30 Train from URL

Inside URL Import, the interface displays:

Train from URL

and:

“Enter a website URL to crawl and index its content”.

21.31 URL Placeholder

The URL field displays:

https://example.com/docs.

21.32 URL Must Begin with HTTP or HTTPS

Before starting URL training, the current client checks that the value starts with:

  1. http://
  2. or https://

Otherwise it displays:

“Please enter a valid URL starting with http:// or https://”.

21.33 Starting URL Import

After entering the URL, select:

Train.

21.34 Scraping and Indexing

During URL Import, Live Chat displays:

Scraping and indexing website...

21.35 Successful Website Indexing

When URL Import succeeds, Live Chat displays:

Website indexed successfully!

The URL field is cleared and the document/knowledge list is refreshed.

21.36 Import Failed

If the URL operation fails, the interface can display:

Import failed

and the returned Error.

21.37 Crawl Depth Is Not Source-Verified

The interface describes URL Import as crawling and indexing website content.

However, the actual document/API crawler implementation was excluded from the sanitized User Operations bundle.

Therefore, this manual does not claim a specific:

  1. Number of pages
  2. Link depth
  3. Sitemap behavior
  4. JavaScript-rendering behavior
  5. Crawl limit

for URL Import.

Test the resulting Agent against the content you need.

21.38 Best Practice for URL Training

Start with the most authoritative URL possible.

For example:

https://yourcompany.com/help

may be more useful for support than a broad marketing homepage if your help center contains the answers customers actually need.

21.39 Use Approved Public Information

Before importing a URL, confirm that its content:

  1. Belongs in the support Knowledge Base
  2. Is current
  3. Is accurate
  4. Is appropriate for customer-facing answers

Outdated website information can produce outdated support answers.

21.40 Your Documents

Below the upload/import controls is:

Your Documents.

This is the current Knowledge Base content list.

21.41 Document Total

The heading displays:

[number] total.

21.42 No Documents Yet

If the Knowledge Base is empty, Live Chat displays:

No documents yet

and:

“Upload your first document to get started”.

21.43 Document Information

Each document entry displays:

  1. Document Name
  2. Created date
  3. Current indexing Status
  4. Delete control


21.44 Document Date

The current list formats creation dates in a form such as:

Aug 19, 2026.

21.45 Indexed Status

A completed document displays:

Indexed

with a Check indicator.

21.46 Processing Status

An in-progress document displays:

Processing.

21.47 Error Status

A failed document entry displays:

Error.

21.48 Refreshing the Knowledge Base List

The Knowledge Base header contains a Refresh control that reruns the document retrieval process.

Use it if a Processing status appears unchanged after sufficient time.

21.49 Removing a Knowledge Base Document

Each document entry contains a Trash/Delete button.

Selecting it opens a confirmation dialog.

21.50 Delete Confirmation

The dialog states:

Are you sure?

and:

“This action cannot be undone. This will permanently delete the document from your knowledge base.”

21.51 Cancel

Select:

Cancel

to leave the document in the Knowledge Base.

21.52 Delete

Select:

Delete

to proceed with permanent removal.

21.53 Successful Document Deletion

When deletion succeeds, Live Chat displays:

Document deleted.

The document is then removed from the displayed list.

21.54 Delete Failed

If deletion fails, the interface displays the returned Error or:

Delete failed.

21.55 Network Error

A failed document deletion request can also display:

Network error.

Do not assume the document was deleted if an error appears.

21.56 Deleting Knowledge Can Affect Future Answers

Removing a Knowledge Base document is not just file cleanup.

Because Live Chat is designed to answer from indexed Knowledge, removing a source can affect what information remains available to future Chat responses.

Review dependencies before deleting important support content.

21.57 No Edit Document Function

The current document list does not establish an:

  1. Edit Document
  2. Replace Document
  3. Modify Indexed Text

control.

If source information changes, the safest current workflow is generally to remove outdated content and upload/import the updated source.

21.58 No Knowledge Base Folders

The current Live Chat source does not establish:

  1. Folders
  2. Categories
  3. Tags
  4. Collections

inside Your Documents.

21.59 No Knowledge Search Control

The current Knowledge Base list does not provide a subscriber-facing search box for finding a document by Name or content.

21.60 Test Your Agent

The right-side testing Card is titled:

Test Your Agent.

Its description states:

“Launch the preview to test how your AI responds to questions based on your uploaded documents.”

21.61 Launch Preview

Select:

Launch Preview.

This enables the floating Live Chat test widget.

21.62 Launch Preview Produces a Floating Chat Button

The Preview uses the same ChatWidget component as the embedded experience.

In non-embedded mode, the widget initially appears as a floating teal Message button near the bottom-right of the screen.

Select that button to open the Chat window.

21.63 Close Preview

Once Preview has been enabled, the Test Your Agent button changes to:

Close Preview.

Use this to remove the Preview component from the Live Chat page.

21.64 Widget X vs. Close Preview

These controls are slightly different.

X Inside the Chat Widget

Closes/minimizes the currently open non-embedded widget back to the floating Chat button.

Close Preview on the Live Chat Page

Removes the Preview widget from the page.


21.65 Preview Status Labels

The Test Your Agent Card displays:

  1. Instant
  2. Grounded


These are descriptive product-interface labels for the support experience.

21.66 Live Support Header

When opened, the widget displays:

Live Support.

21.67 Powered By

Under Live Support, the Chat header displays:

Powered by [site name]

and falls back to:

AI Suite

if another site Name is not configured.

21.68 Initial Greeting

A new ChatWidget session begins with:

“Hello! I'm your Live Support Assistant. How can I help you today based on our documents?”

An embedded support-context version can additionally identify a Support Mode.

21.69 Message Field

The Chat input displays:

Type your message...

21.70 Sending a Text Question

To test the assistant:

  1. Open Preview.
  2. Open the Live Support widget.
  3. Enter a question.
  4. Select Send or press Enter.
  5. Wait for the response.
  6. Review it against your Knowledge Base.

21.71 Enter Sends the Message

The Chat input is inside a standard form.

Pressing:

Enter

submits the current message.

The interface does not establish a multiline text-area workflow for this Chat input.

21.72 Send Button

The Send control uses a Send-arrow icon.

It is disabled when:

  1. A response is already loading
  2. There is no text and no attached image

21.73 Assistant Is Thinking...

While waiting for the support response, Live Chat displays:

Assistant is thinking...

21.74 Automatic Message Scrolling

As new messages are added, the current Chat widget automatically scrolls toward the latest content.

21.75 User Messages

User messages appear as teal message bubbles on the user side of the conversation.

21.76 Assistant Messages

Assistant replies appear using the AI-side message styling and are rendered through the PROS SUITE:

MarkdownRenderer.

This allows support answers to contain structured formatting where the response provides it.

21.77 Chat Supports Reference Images

The Live Support input also contains a Paperclip attachment control.

The current verified attachment type is:

image.

21.78 Image File Selector

The Chat attachment input accepts:

image/*.

It does not establish Chat attachments for PDF, DOCX, ZIP, or other documents.

Those belong in the Knowledge Base upload workflow.

21.79 Maximum Chat Image Size

The current ChatWidget rejects images larger than:

5 MB.

21.80 Image Too Large

If the image exceeds 5 MB, the exact current message is:

“Please upload an image smaller than 5MB.”

21.81 Image Preview

After selecting an image, a thumbnail Preview appears above the Chat input.

21.82 Removing a Pending Image

Select the small X on the image Preview to remove it before sending.

21.83 Image Can Be Sent with Text

You can enter a question and attach an image before sending.

The Chat request includes both:

  1. Prompt
  2. Image

when present.

21.84 Image-Only Requests Are Technically Allowed

The current Send logic permits submission when:

  1. Text is empty
  2. But an image is attached


However, adding a brief written question usually makes the intended support task clearer.

21.85 Example — Screenshot Support

A useful workflow is:

  1. Attach a screenshot of an issue.
  2. Ask:
  3. Based on our support documentation, what should the customer do next?
  4. Send.
  5. Review the response.

21.86 Sent Images Remain Visible in the Current Conversation

When an image is sent, the Chat bubble displays the shared image above the user's message.

21.87 Chat Request Content

For every submitted Chat message, the current widget sends:

  1. Current Prompt
  2. Optional support context
  3. Optional current image

to the RAG Chat service.

21.88 Important Multi-Turn Context Limitation

The current ChatWidget displays previous messages in the interface, but the request sent for each new answer contains only the current Prompt, optional support context, and optional image.

The current client request does not submit the visible previous message array with each new question.

Therefore:

Do not rely on source-verified conversational memory across previous Live Chat turns.

21.89 Repeat Important Context in Follow-Up Questions

Instead of:

What about the second option?

prefer:

Regarding the annual Enterprise plan described in our pricing document, what does the second support option include?

This makes the question more self-contained.

21.90 Visible Conversation History Is Still Useful

Although prior messages are not source-verified as being sent back on every request, they remain visible to the user while the ChatWidget stays mounted.

This helps you visually compare questions and answers during testing.

21.91 No Persistent Chat History Is Established

The message list exists in the ChatWidget's current component state.

The source does not establish:

  1. Saved Chat sessions
  2. Conversation IDs
  3. Chat-history database
  4. Reopen Previous Conversation

for Live Chat.

21.92 Closing and Reopening the Floating Widget

When the non-embedded Preview widget is merely minimized with its X, the component remains mounted.

Its current message state can therefore remain visible when reopened during that same mounted page session.

21.93 Closing Preview Can Reset the Test Conversation

Selecting:

Close Preview

removes the ChatWidget component from the Live Chat page.

Launching a newly mounted Preview creates a new widget state beginning with its initial greeting.

21.94 Refreshing the Page Can Reset the Chat

Because no persistent Live Chat conversation-storage source is established, do not rely on the current visible test conversation surviving a page refresh.

21.95 No New Chat Button

The current widget does not contain a dedicated:

New Chat

control.

For testing a fresh session, Close Preview and relaunch it or reload as appropriate.

21.96 No Clear Conversation Button

There is no source-verified:

  1. Clear Chat
  2. Delete Conversation
  3. Clear History

control inside the current Live Support widget.

21.97 No Copy Answer Button

The Live Support widget does not currently establish a dedicated:

Copy Answer

control.

This differs from Browser Control and some other PROS SUITE workspaces.

21.98 No Download Conversation

The current Live Chat source does not provide:

  1. Download Transcript
  2. Export Chat
  3. Save as PDF
  4. Save as TXT

for a Chat session.

21.99 No Thumbs Up/Down Feedback

The current ChatWidget does not establish:

  1. Like
  2. Dislike
  3. Rate Answer
  4. Helpful/Not Helpful

controls.

21.100 Error Returned by RAG Service

If the Chat service returns an Error, the assistant places a message into the conversation formatted as:

Error: [error].

21.101 Connection Error

If the Chat request itself fails, the assistant displays:

“Sorry, I had trouble connecting to the support server.”

21.102 Test Answers Against the Source

A successful technical response does not automatically mean the answer is correct.

For each important support category, test:

  1. Exact product Name
  2. Policy details
  3. Pricing
  4. Troubleshooting
  5. Onboarding steps
  6. Restrictions
  7. Common customer questions

and compare the answer with the original indexed source.

21.103 Grounded Does Not Mean Infallible

The interface describes the support agent as:

Grounded

and says responses are based on indexed content.

However, the final wording is still AI-generated.

Verify high-impact answers before deploying them broadly to customers.

21.104 Build a Clean Knowledge Base

RAG quality depends heavily on source quality.

Avoid mixing:

  1. Old policies
  2. New policies
  3. Duplicate documents with conflicting wording
  4. Draft pricing
  5. Final pricing
  6. Obsolete instructions

unless you intentionally want all of them available.

21.105 Remove Outdated Documents

If a product manual is replaced:

  1. Upload the updated version.
  2. Confirm it becomes Indexed.
  3. Test the new information.
  4. Remove the obsolete document if it could create conflicting answers.

21.106 Test Before Embedding

Do not move directly from upload to public deployment.

Use:

Test Your Agent → Launch Preview

first.

21.107 Recommended Testing Categories

Test at least:

  1. Basic product question
  2. Pricing question
  3. Setup question
  4. Troubleshooting question
  5. Policy question
  6. Question that requires two related facts
  7. Question whose answer is not in the Knowledge Base

This helps reveal gaps.

21.108 Test Missing Knowledge

Ask the Agent something that is deliberately not contained in your Knowledge Base.

This helps you understand how the deployed assistant behaves when it lacks supporting information.

21.109 Embed on Your Website

Below Knowledge Base is:

Embed on Your Website

with:

“Add this script before </body>.

21.110 Generated Embed Script

Live Chat automatically builds an embed snippet using the current PROS SUITE origin.

Its structure is:

<script src="[PROS SUITE origin]/chat-widget-embed.js" data-site-url="[PROS SUITE origin]"></script>


The live page fills the actual origin automatically.

21.111 You Do Not Manually Construct the Script

Use the code shown in your own Live Chat workspace.

Do not manually substitute domains unless your implementation specifically requires it.

21.112 Copy

Hover over the code block and select:

Copy.

21.113 Embed Code Copied

After copying, Live Chat displays:

Embed code copied!

21.114 Where the Script Goes

The interface instructs:

“Add this script before </body>.

Conceptually:


...
<script ...></script>
</body>

Use your website's normal safe method for adding a script before its closing body tag.

21.115 Do Not Modify Production Code Without a Backup

If adding the widget manually to a production website:

  1. Back up the page/template.
  2. Use a staging environment where available.
  3. Add only the copied script.
  4. Test desktop and mobile.
  5. Confirm the rest of the website continues to operate correctly.

21.116 Standalone ChatWidget Route

The source contains a dedicated standalone ChatWidget page that renders the widget in:

embedded mode.

This is the browser-side presentation intended to support embedded Chat operation.

21.117 Embedded Mode Opens the Full Chat Interface

Unlike the floating internal Preview—which initially renders a button—the embedded=true version renders the full Chat panel directly.

21.118 Closing an Embedded Widget

When the embedded Chat's X is selected, it sends a browser message to its parent page requesting:

close-chat-widget.

The surrounding embed script is expected to determine how that parent interaction is handled.

21.119 Embed Script Implementation Was Not Included in the Bundle

The user-facing page references:

chat-widget-embed.js

but the sanitized manual source bundle does not contain that script's implementation.

Therefore, this manual can verify:

  1. The generated embed code
  2. The standalone ChatWidget
  3. The ChatWidget's embedded mode

but not every implementation detail of the external loader script.

21.120 Verify the Embedded Widget on the Actual Website

After deployment, test:

  1. Widget appears.
  2. Widget opens.
  3. Widget closes.
  4. User can enter a message.
  5. Responses are returned.
  6. Knowledge is correct.
  7. Images can be attached if appropriate.
  8. Mobile positioning works.
  9. The widget does not interfere with your site navigation.

21.121 Important Public-Access Source Check

The middleware source explicitly treats:

/api/chat/rag

as an API path that does not require the normal authenticated session.

That is consistent with an externally used support Chat service.

21.122 Standalone Widget Route Access Needs Live Verification

However, the same middleware's current public page list does not explicitly include:

/chat-widget.

Because the external embed-loader implementation is also absent from the sanitized bundle, this manual cannot source-verify that an unauthenticated website visitor can always reach the standalone widget in the current deployment.

Therefore:

Test the embedded widget in a logged-out/private browser before considering deployment complete.

21.123 Why Logged-Out Testing Matters

An owner can see a working widget while signed into PROS SUITE, yet a customer may visit the website without any PROS SUITE session.

Public deployment should therefore be verified using:

  1. Incognito/private browser
  2. Logged-out browser
  3. Another device

21.124 If Visitors Are Redirected to Login

If the embedded widget unexpectedly redirects an external visitor to the AIUNIFY Login page, this is not a Knowledge Base problem.

It indicates a deployment/access-routing issue that should be corrected by the appropriate AIUNIFY technical administrator.

Subscribers should not attempt middleware/server changes through this User Operations workflow.

21.125 Support Context

The standalone ChatWidget route can read an optional parameter named:

supportEmail.

That value is passed into the embedded ChatWidget.

21.126 Support Mode Greeting

If a supportEmail value exists, the initial greeting includes:

“(Support Mode: [supportEmail])”.

21.127 Support Context Is Sent with Chat Requests

The current Chat request sends the optional supportEmail along with:

  1. Current Prompt
  2. Optional Image


21.128 The Live Preview Does Not Supply supportEmail

The in-dashboard Test Your Agent Preview renders:

<ChatWidget />

without a supportEmail value.

Therefore its greeting does not display Support Mode.

21.129 Embed Code Does Not Visibly Contain supportEmail

The current subscriber-visible embed code contains:

  1. Script source
  2. data-site-url

but no visible supportEmail attribute.

Because the embed-loader script is outside the bundle, this manual does not invent how account-specific Knowledge Base routing is derived in the final external widget.

21.130 Verify Knowledge Isolation Before Customer Deployment

If multiple companies/users have separate Knowledge Bases, test that an external widget returns the correct organization's information.

This is especially important because the account-routing behavior of the omitted embed loader/RAG backend cannot be fully verified from this user-only bundle.

21.131 Live Chat Token Catalogue Entry

The generic PROS SUITE feature catalogue currently lists:

Live Chat — 10 Tokens.

21.132 Important Token Qualification

The Live Chat client does not:

  1. Display 10 tokens per use
  2. Explicitly deduct Tokens
  3. Send a Tool cost with the Chat request

The actual /api/chat/rag implementation is outside the sanitized source bundle.

Therefore:

The generic 10-Token catalogue entry is not sufficient to prove the exact live per-message charge.

21.133 Shared Access Logic Treats support-agent as Basic

The shared PROS SUITE FeatureGuard source specifically classifies:

support-agent

as a:

basic tool

alongside Dashboard when evaluating Plan scope.

This creates an additional reason not to infer a simple 10-Tokens-per-message billing rule from the generic feature catalogue alone.

21.134 No Token Balance Is Displayed Inside Live Chat

The current Live Chat page does not show:

  1. Message cost
  2. Current Token balance
  3. Token consumption meter

inside the ChatWidget.

Use the normal PROS SUITE Monthly Tokens display for general account monitoring.

21.135 Exact RAG Message Billing Is Not Source-Verified

Because the server-side /api/chat/rag implementation was intentionally excluded from the User Operations bundle, this manual does not claim:

  1. Each Chat answer costs 10 Tokens.
  2. Chat is universally free.
  3. Image questions cost more.
  4. Knowledge indexing costs Tokens.
  5. URL Import costs Tokens.
  6. Embed visitor messages have a particular Token rate.

Those rules require server-side/current-account verification.

21.136 Header AI Model Does Not Appear in ChatWidget Requests

The Live Chat client sends:

  1. Prompt
  2. supportEmail
  3. Image

but does not send the shared PROS SUITE selectedModel.

Therefore:

The source does not verify that changing the Header AI Model changes the RAG Live Chat Model.

21.137 No Live Chat Model Selector

The Live Chat page itself does not expose an:

AI Model

selector.

Model behavior appears to be handled by the RAG service rather than selected inside this subscriber workspace.

21.138 No Provider API-Key Controls in Live Chat

There is no Gemini/OpenAI/Anthropic/etc. provider-key field inside Live Chat.

Those general AI settings should not be confused with this support-agent Knowledge Base interface.

21.139 Live Chat Is More Than a Chat Window

For subscriber operations, the Live Chat feature should be understood as:

RAG SUPPORT AGENT BUILDER

rather than merely:

a Chat box.

Its main value comes from controlling the Knowledge Base and deploying the trained support experience.

21.140 Recommended Knowledge Base Workflow

LIVE CHAT

KNOWLEDGE BASE

Choose:

FILE UPLOAD

or:

URL IMPORT

Wait for:

INDEXED

Review:

DOCUMENTS / INDEXED / PROCESSING / ERRORS

TEST YOUR AGENT

LAUNCH PREVIEW

Ask representative customer questions

Correct Knowledge Base gaps

Retest

EMBED ON YOUR WEBSITE

21.141 Recommended Document-Update Workflow

When support information changes:

ADD UPDATED SOURCE

Wait for:

INDEXED

Test updated question

Verify correct answer

Remove outdated conflicting source

Retest

This reduces the risk of Knowledge Base contradictions.

21.142 Recommended Chat Testing Workflow

Test:

  1. Product Overview
  2. Setup question
  3. Pricing question
  4. Policy question
  5. Troubleshooting question
  6. Edge case
  7. Missing-information question
  8. Screenshot/image question
  9. Follow-up written as a self-contained question

21.143 Example — Product Question

What does the Professional Plan include?

Then compare the answer with the indexed pricing documentation.

21.144 Example — Troubleshooting Question

A customer cannot complete Step 3 of the onboarding process. Based on our support manual, what should they check first?

21.145 Example — Policy Question

What does our refund policy say about cancellations after 30 days?

Only deploy the answer if the correct policy source has been indexed.

21.146 Example — Missing Information

Ask:

What is our office location in Tokyo?

when no such information exists in the Knowledge Base.

Observe how the assistant handles an unsupported question.

21.147 Best Practice — Make Documents Customer-Readable

A support Agent performs better when its source content is:

  1. Clear
  2. Structured
  3. Current
  4. Specific
  5. Consistent

A vague internal draft can produce vague support responses.

21.148 Best Practice — Use Descriptive Document Names

Names such as:

Enterprise_Onboarding_Guide_2026.pdf

are easier to manage than:

document-final-3.pdf.

The current interface displays the file Name directly in Your Documents.

21.149 Best Practice — Avoid Conflicting Versions

Do not leave:

  1. Pricing 2025
  2. Pricing Draft
  3. Pricing Final
  4. Pricing Revised

all active if they contain contradictory information.

Maintain one authoritative current version where practical.

21.150 Best Practice — Separate Internal Secrets from Customer Knowledge

Only add content appropriate for the support use case.

Do not casually upload:

  1. Passwords
  2. Private API Keys
  3. Internal credentials
  4. Sensitive customer data
  5. Confidential financial information

to a Knowledge Base intended to support external users.

21.151 Best Practice — Test Every Important Policy

Before embedding publicly, test:

  1. Refunds
  2. Cancellation
  3. Billing
  4. Service limitations
  5. Privacy
  6. Access rules

If customers may make decisions based on the answer, accuracy matters.

21.152 Best Practice — Keep Questions Self-Contained

Because visible previous messages are not submitted as Chat history by the current client, phrase each important question so it can stand on its own.

21.153 Best Practice — Do Not Use Preview as Proof of Public Deployment

Internal Preview proves the ChatWidget works while you are inside PROS SUITE.

It does not prove that an unauthenticated visitor can use the external widget.

Always test the actual website separately.

21.154 Best Practice — Test Desktop and Mobile

The non-embedded widget uses responsive sizing for smaller screens.

After embedding, test:

  1. Desktop
  2. Tablet
  3. Mobile

and verify that the widget does not cover important website controls.

21.155 Best Practice — Test the Embedded Close Button

Because the embedded widget communicates its Close request to the parent page, verify the final embed-loader behavior after deployment.

21.156 Best Practice — Repeat Testing After Knowledge Changes

Knowledge Base modifications can change support behavior.

After:

  1. Uploading
  2. Importing
  3. Removing
  4. Replacing

important content, rerun representative questions.

21.157 Troubleshooting — File Will Not Upload

Check:

  1. File is PDF, DOCX, or TXT.
  2. File is within the displayed 10 MB limit.
  3. Another upload/import is not still running.
  4. Your session is active.

21.158 Troubleshooting — Wrong File Type

The current file picker accepts only:

.pdf,.docx,.txt.

Convert unsupported content to an accepted format if appropriate.

21.159 Troubleshooting — Upload Shows Processing

Processing means the content is not yet in the completed Indexed state.

Use the Refresh control and wait for:

Indexed

before relying on it.

21.160 Troubleshooting — Upload Shows Error

Review the displayed upload Error.

If it references system/database setup rather than your file, contact AIUNIFY support instead of attempting backend changes.

21.161 Troubleshooting — URL Is Rejected

The URL must begin with:

http://

or:

https://.

21.162 Troubleshooting — Train Button Is Disabled

The URL Import Train button is disabled while:

  1. Upload/index work is active
  2. The URL field is empty


21.163 Troubleshooting — Website Indexed but Agent Misses Information

Possible user-level checks include:

  1. Confirm the desired information is really on the imported source.
  2. Refresh the Knowledge Base list.
  3. Test with more specific wording.
  4. Upload a dedicated document containing the relevant information.
  5. Remove contradictory/outdated sources.

Because crawl depth is not source-verified, do not assume every linked page was automatically indexed.

21.164 Troubleshooting — Agent Gives an Old Answer

Check whether an outdated document or URL content remains in the Knowledge Base.

Remove obsolete sources after the replacement content is Indexed.

21.165 Troubleshooting — Agent Gives Conflicting Answers

Look for:

  1. Duplicate policies
  2. Old pricing
  3. Multiple product versions
  4. Draft/final documents

Simplify the Knowledge Base so the authoritative information is clear.

21.166 Troubleshooting — Launch Preview Does Not Open a Large Chat Window

Launch Preview first mounts the floating ChatWidget.

You may then need to select the floating teal Chat button in the lower-right corner to open it.

21.167 Troubleshooting — X Only Minimized the Chat

That is expected in the non-embedded Preview.

Use the page-level:

Close Preview

to fully remove the Preview.

21.168 Troubleshooting — Assistant Is Thinking...

Wait for the current request to complete.

The Send and Paperclip controls are disabled from starting another request while the current answer is loading.

21.169 Troubleshooting — Follow-Up Question Lost Context

The current request does not include the preceding messages.

Rewrite the follow-up as a complete question containing the necessary context.

21.170 Troubleshooting — Image Is Rejected

The current Chat attachment limit is:

5 MB.

Use a smaller image.

21.171 Troubleshooting — Cannot Attach PDF Inside Chat

PDF files belong in:

Knowledge Base → File Upload

The current Chat Paperclip accepts images, not PDFs.

21.172 Troubleshooting — Connection to Support Server Failed

If the widget displays:

“Sorry, I had trouble connecting to the support server.”

the Chat request itself could not complete.

Retry after confirming your connection and service availability.

21.173 Troubleshooting — Assistant Displays “Error: ...”

This means the RAG service returned an Error payload.

Review the actual Error text before changing your Knowledge Base.

21.174 Troubleshooting — Embed Script Cannot Be Found

Use the exact code displayed under:

Embed on Your Website.

If the referenced script cannot load from the live PROS SUITE domain, the issue requires technical/deployment review rather than changing Knowledge Base content.

21.175 Troubleshooting — Embedded Widget Redirects to Login

Test while logged out.

The source's current public-path configuration does not explicitly list /chat-widget, so a login redirect would be consistent with an access-routing problem that needs technical correction.

21.176 Troubleshooting — Embed Works for You but Not Customers

Test using:

  1. Private/incognito browser
  2. Another device
  3. Another network

This helps separate your authenticated PROS SUITE session from actual public visitor behavior.

21.177 Troubleshooting — Wrong Knowledge Appears on Embedded Widget

If multiple support Knowledge Bases exist, verify the deployed widget is being routed to the correct account/support context.

The omitted embed-loader/backend source prevents this manual from guaranteeing the exact mapping mechanism.

21.178 Troubleshooting — Cannot Change AI Model

Live Chat currently has no subscriber-facing Model selector.

Changing the general Header Model is not source-verified to affect Live Chat because its requests do not submit selectedModel.

21.179 Troubleshooting — Cannot Find Token Cost

Live Chat does not display a current per-message Token cost.

The generic catalogue contains 10 Tokens, but exact RAG-service billing is not established in this sanitized source.

21.180 Live Chat Deployment Checklist

Before embedding:

  1. My important support documents are uploaded.
  2. Relevant URLs are imported.
  3. Important sources show Indexed.
  4. Errors have been resolved.
  5. Obsolete documents have been removed.
  6. I tested common product questions.
  7. I tested pricing questions.
  8. I tested troubleshooting.
  9. I tested policy questions.
  10. I tested missing information.
  11. I tested an image/screenshot question where relevant.
  12. I understand follow-up memory is not source-verified.
  13. I copied the current embed code.
  14. I backed up the website/template before modification.

21.181 External Widget Checklist

After embedding:

  1. The Chat control appears.
  2. It opens correctly.
  3. It closes correctly.
  4. Text questions submit.
  5. AI answers appear.
  6. Answers use the correct Knowledge Base.
  7. Images can be attached where appropriate.
  8. Desktop layout works.
  9. Mobile layout works.
  10. The widget does not cover critical website controls.
  11. I tested while logged out of PROS SUITE.
  12. I tested in private/incognito mode.
  13. Visitors are not redirected to Login.
  14. The correct organization's Knowledge is returned.

21.182 Knowledge Base Maintenance Checklist

Periodically review:

  1. Document count.
  2. Indexed count.
  3. Processing count.
  4. Error count.
  5. Outdated files.
  6. Old pricing.
  7. Old policies.
  8. Duplicate documents.
  9. Broken/outdated URL content.
  10. Common unanswered customer questions.
  11. New products/services requiring documentation.

21.183 What Live Chat Currently Supports

The source verifies subscriber-facing capabilities for:

Knowledge Base

  1. File Upload
  2. PDF
  3. DOCX
  4. TXT
  5. UI-stated 10 MB maximum
  6. URL Import
  7. Document status
  8. Indexed
  9. Processing
  10. Error
  11. Delete Document
  12. Refresh document list

Chat Testing

  1. Launch Preview
  2. Floating widget
  3. Live Support
  4. Text questions
  5. Enter-to-send
  6. Image attachment
  7. 5 MB Chat image limit
  8. Markdown assistant responses
  9. Loading state
  10. Error responses

Deployment

  1. Embed script
  2. Copy embed code
  3. Standalone embedded ChatWidget
  4. Optional supportEmail context
  5. Public RAG API exception in middleware

21.184 What Live Chat Does Not Currently Establish

The supplied subscriber-facing source does not establish:

  1. Persistent Chat session history
  2. Conversation IDs
  3. Reopen Previous Chat
  4. New Chat button
  5. Clear Chat button
  6. Copy Answer
  7. Download Chat Transcript
  8. Thumbs Up/Down feedback
  9. Human-agent handoff UI
  10. Support ticket creation
  11. Live human operator inbox
  12. Visitor identity/profile management
  13. Conversation analytics
  14. Direct Model selector
  15. Header Model control over RAG
  16. Exact per-message Token charge
  17. Knowledge Base folders
  18. Knowledge Base tags
  19. Knowledge Base search
  20. Edit document
  21. Replace document button
  22. Bulk document upload
  23. Confirmed arbitrary URL crawl depth
  24. Confirmed public /chat-widget access in the current middleware
  25. Fully verifiable external embed-loader behavior

These should not be described as active subscriber features unless a future release/source establishes them.

21.185 Important Current-Version Source Findings

Several details deserve particular attention.

RAG-Centered

The product is explicitly designed around indexed subscriber Knowledge.

Two Knowledge Sources

Subscribers can use:

  1. Documents
  2. Website URLs


Chat Images

The Chat itself accepts images up to 5 MB.

No Verified Multi-Turn Memory

Each Chat request sends the current Prompt/image/support context but not the visible prior-message array.

Persistent Knowledge, Not Persistent Conversations

Documents are loaded from the Knowledge Base service, while Chat messages exist only in the current widget state.

External Embed Needs Live Verification

The embed feature is visible and the standalone widget exists, but /chat-widget is not explicitly listed as a public page in the current middleware source.

21.186 Live Chat at a Glance

The current user workflow is:

LIVE CHAT SUPPORT

KNOWLEDGE BASE

Choose:

FILE UPLOAD

or:

URL IMPORT

Content moves through:

PROCESSING

INDEXED

Review:

DOCUMENTS

INDEXED

PROCESSING

ERRORS

TEST YOUR AGENT

LAUNCH PREVIEW

Click floating Chat button

LIVE SUPPORT

Ask:

TYPE YOUR MESSAGE...

or attach:

IMAGE

ASSISTANT IS THINKING...

Review grounded response

Repeat testing

EMBED ON YOUR WEBSITE

COPY

Add script before:

</body>

Test website as a logged-out visitor

Maintain Knowledge Base over time

21.187 Chapter Summary

AIUNIFY PROS SUITE Live Chat is a RAG-powered support-agent builder rather than simply another general-purpose Chat interface.

The workspace identifies itself as:

Live Chat Support

and tells subscribers:

“Train your AI assistant with your documents. Get accurate, grounded responses based only on your uploaded content.”

The Knowledge Base supports:

  1. File Upload
  2. URL Import

with the current file interface accepting:

  1. PDF
  2. DOCX
  3. TXT

and displaying:

“Max 10MB per file.”

Subscribers can monitor:

  1. Documents
  2. Indexed
  3. Processing
  4. Errors

and manage individual Knowledge Base entries through the Your Documents list.

A completed document displays:

Indexed

while a failed entry displays:

Error. Documents can be permanently removed after the confirmation:

“This action cannot be undone. This will permanently delete the document from your knowledge base.”

To test the RAG assistant, use:

Test Your Agent → Launch Preview

and then open the floating Chat button. The widget identifies itself as:

Live Support

and begins with:

“Hello! I'm your Live Support Assistant. How can I help you today based on our documents?”

Users can submit:

  1. Text
  2. Optional images up to 5 MB

and the assistant renders its response using Markdown.

An important current limitation is that each request sends the current Prompt, optional support context, and optional image—but not the visible previous Chat-message array. Accordingly, multi-turn contextual memory should not be assumed.

Live Chat also provides:

Embed on Your Website

and tells subscribers to add the generated script before:

</body>.

The source contains a standalone embedded ChatWidget and a public exception for the RAG API. However, the middleware's current public-page list does not explicitly include /chat-widget, and the external chat-widget-embed.js implementation was not part of the sanitized bundle. Therefore, the correct deployment practice is to test the widget while logged out before declaring it customer-ready.

Finally, although the generic feature catalogue lists Live Chat at 10 Tokens, the actual RAG endpoint's billing logic is outside the user-operations source, the Chat interface shows no per-message cost, and shared access logic treats support-agent as a basic Tool. The manual therefore does not claim a fixed 10-Token charge for every Live Chat message.

The recommended operating principle is:

Build a Clean Knowledge Base → Wait for Indexing → Test the Agent Thoroughly → Correct Knowledge Gaps → Embed the Widget → Test as an External Visitor → Maintain the Knowledge Base as Your Business Changes.

Write Your Comment