yourang.ai Logo
Back to the platform
Documentation
Get started
  • What the platform is
  • First access
  • Platform overview
  • Quick glossary
Dashboard Assistant
  • What the dashboard assistant is
  • How to use it
  • What it can do
  • Safety and privacy
  • Plans and usage limits
Voice agent
  • Basic configuration
  • Voices and language
  • Instructions
  • Prompt tokens
  • Advanced settings
  • Evaluation criteria
  • Testing and playground
  • Updating instructions
  • External Tools
  • Built-in tools
  • MCP servers
Models offered
  • What models are and why they matter
  • Voice models
  • AI models
  • Choosing the right combination
Documents and knowledge base
  • What the knowledge base is
  • Uploading and managing documents
  • How search works during a call
  • Best practices
Calls
  • Call history
  • Transcripts and summaries
  • Audio recordings
  • Filters and search
  • Data export
Call transfers
  • When and why to transfer a call
  • Departments
  • System tools
  • AI after-hours
  • Routing rules
  • Operator app (iOS / Android)
WhatsApp
  • WhatsApp Business in yourang.ai
  • Real-time chat
  • Automations
  • Approved templates
  • WhatsApp contacts and lists
  • WhatsApp AI agents
Actions and campaigns
  • What actions are
  • SMS campaigns
  • Email campaigns
  • Scheduling and batch sends
Reservations
  • Calendar view
  • Availability rules
  • Confirmations and reminders
  • Changes and cancellations
Contacts
  • Customer directory
  • CSV import
  • Lists and segments
  • Custom fields
Shop and catalogue
  • The shop in yourang.ai
  • Product and service catalogue
  • Order management
  • OCR and price-list import
Integrations
  • Connect Apple Calendar
  • Connect HubSpot
  • Integrations overview
  • Calendar
  • WhatsApp
  • SMS and email
  • Business software and PMS
  • Outbound webhooks
Workflows
  • What workflows are
  • Nodes and blocks
  • Triggers and webhooks
  • Practical examples
Call center and dialer
  • What the yourang.ai call center does
  • Outbound campaigns
  • Human operators
  • Contact lists and live sync
  • Operator panel
External APIs and developers
  • yourang.ai for developers
  • API keys and authentication
  • Main endpoints
  • Incoming webhooks
Use cases
  • Hotels and accommodation
  • Restaurant
  • B&Bs and short-term rentals
  • Beauty center and spa
  • Travel agency
Pricing and plans
  • How pricing works
  • Subscription plans
  • Wallet and credits
  • Consumption and invoices
  • Changing, suspending, or cancelling the plan
Management
  • Account and organization
  • Billing and subscription
  • Team and roles
  • Security and privacy
  • Notifications
Business information
  • Business details
  • Location and address
  • Opening hours
  • AI assistant hours
  • Departments and team
Resources
  • Frequently asked questions
  • Complete glossary
  • Support
Documentation›Documents and knowledge base›What the knowledge base is

Documents and knowledge base

What the knowledge base is

How the knowledge base (RAG) works and why it's the most effective way to give the assistant your own information.

The knowledge base is the archive of documents, manuals, and procedures that your assistant consults in real time to answer customer questions. It's the simplest way to ensure the answers are consistent, up to date, and based on your own materials.

Difference between instructions and knowledge base

  • Instructions. Define the general behaviour of the agent: how it speaks, what it can do, what tone it uses. They are read on every call.
  • Knowledge base. Contains your business's domain knowledge: price lists, regulations, extended FAQs, service descriptions. It's consulted only when needed.

Together they form the assistant's 'personality': the instructions decide how it behaves, the knowledge base provides the concrete answers. Keeping the two separate makes maintenance much easier.

How retrieval (RAG) works

  1. 1

    Indexing

    When you upload a document, yourang.ai splits it into small blocks (chunks) and computes a semantic representation of each.

  2. 2

    Customer question

    During the call, the customer's request is matched semantically against the indexed chunks to find the most relevant ones.

  3. 3

    Response based on the chunks

    The agent formulates the answer using the retrieved chunks as its source, without inventing information missing from the documents.

Less invented, more reliable

The knowledge base drastically reduces 'made-up' answers. If the question doesn't match anything in your documents, the assistant says so rather than improvising.

Was this page helpful?

PreviousChoosing the right combinationNextUploading and managing documents