Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.meetzy.io/llms.txt

Use this file to discover all available pages before exploring further.

What is the Knowledge Base?

The Knowledge Base is where you provide your agent with information it can reference during conversations. This includes product documentation, FAQs, company policies, pricing information, and any other content your agent needs to answer customer questions accurately.
A well-populated Knowledge Base significantly improves your agent’s ability to provide accurate, helpful responses by giving it access to your specific business information.

Adding Documents

You can add knowledge to your agent in three ways:
Import content directly from web pages.
1

Click 'Add URL'

Open the Knowledge Base section and select the URL option.
2

Enter the URL

Paste the full URL of the webpage you want to import.
3

Configure Settings

Set the document name and choose the usage mode.
4

Confirm Import

The system will fetch and process the content automatically.
Best for: Product pages, help center articles, documentation sites, pricing pages.

Usage Modes

Each document in your Knowledge Base can be configured with one of two usage modes:
ModeIconDescriptionWhen to Use
Auto SearchπŸ”Agent searches this document only when relevant to the conversationLarge documents, extensive catalogs, reference materials
In PromptπŸ“‹Content is always included in the agent’s context for every conversationCritical info, company details, core policies

Understanding Usage Modes

Auto Search uses semantic search to find relevant portions of documents when needed, making conversations more efficient and cost-effective.
In Prompt mode includes the entire document content in every conversation, which can increase costs and slow responses for large documents. Use only for essential, concise information.

Auto Search Mode

  • How it works: The agent automatically searches through the document when it detects the conversation topic is relevant
  • Performance: Efficient for large documents - only retrieves relevant sections
  • Cost: Lower cost as only relevant portions are processed
  • Best practices: Use for comprehensive guides, product catalogs, detailed FAQs

In Prompt Mode

  • How it works: The document content is included in the agent’s context for every single conversation
  • Performance: Immediate access to information but can slow down responses
  • Cost: Higher cost as content is processed in every conversation
  • Best practices: Use only for critical information under 1000 characters

Managing Documents

Document List View

The Knowledge Base displays all your documents in a organized list showing:
ColumnDescription
NameDocument title (editable)
TypeVisual indicator: πŸ”— URL, πŸ“„ Text, πŸ“ File
ModeUsage mode: πŸ” Auto Search or πŸ“‹ In Prompt
PreviewFirst few lines of content
ActionsEdit (✏️) and Delete (πŸ—‘οΈ) buttons

Real-Time Editing

1

Click Edit Icon

Click the edit icon (✏️) next to any document to modify it.
2

Make Changes

Update content, name, or usage mode as needed.
3

Save Changes

Changes are processed immediately and integrated into your agent’s knowledge.
Document changes take effect immediately - your agent will have access to updated information in new conversations right away.

Dynamic Content Loading

For text and URL documents, the system provides:
  • Preview in the main list for quick reference
  • Full content loading when editing for complete document access
  • Real-time content updates that sync with your agent’s knowledge

Document Deletion

1

Click Delete Icon

Click the delete icon (πŸ—‘οΈ) next to the document.
2

Confirm Deletion

Confirm the action in the popup dialog.
3

Immediate Removal

The document is immediately removed from your agent’s knowledge base.
Deleted documents cannot be recovered. Make sure to export or backup important content before deleting.

Best Practices

Content Organization

  • Keep Current: Regularly update documents to reflect latest information
  • Be Specific: Include exact phrases and terms customers might use
  • Structure Well: Use clear headings, bullet points, and organized sections
  • Avoid Duplication: Don’t repeat the same information across multiple documents

Usage Mode Strategy

  • Auto Search for: Large documents, comprehensive guides, detailed product info
  • In Prompt for: Company name, key contact info, essential policies (keep under 1000 chars)

Performance Optimization

  • Test Regularly: Verify the agent can find and use information correctly
  • Monitor Conversations: Review how the agent uses knowledge base content
  • Optimize Content: Remove outdated or redundant information
Start with Auto Search mode for most documents. Only switch to In Prompt mode for absolutely critical information that must always be available.

Example Knowledge Base Structure

Here’s a recommended structure for organizing your knowledge base:
πŸ“š Knowledge Base
β”œβ”€β”€ πŸ“„ Company Overview (In Prompt)
β”‚   └── Essential company info, mission, key contacts
β”œβ”€β”€ πŸ”— Product Catalog URL (Auto Search)  
β”‚   └── Complete product listings and specifications
β”œβ”€β”€ πŸ“„ Pricing Information (Auto Search)
β”‚   └── Current pricing tiers and packages
β”œβ”€β”€ πŸ“ FAQ Document (Auto Search)
β”‚   └── Common customer questions and answers
β”œβ”€β”€ πŸ“„ Refund Policy (Auto Search)
β”‚   └── Terms and conditions for returns
β”œβ”€β”€ πŸ”— Support Articles URL (Auto Search)
β”‚   └── Help center and troubleshooting guides
└── πŸ“„ Contact Information (In Prompt)
    └── Phone numbers, hours, emergency contacts

Integration with Agent Context

Your Knowledge Base documents are dynamically integrated into your agent’s conversational context:
  • Semantic Search: Auto Search documents are searched based on conversation relevance
  • Context Injection: In Prompt documents are always available in the agent’s working memory
  • Real-Time Updates: Changes to documents are immediately available to the agent
  • Intelligent Retrieval: The system automatically selects the most relevant information

Troubleshooting

Common Issues

Agent can’t find information:
  • Verify the document is saved and shows in the Knowledge Base list
  • Try using Auto Search mode for better semantic matching
  • Include variations of keywords customers might use
Slow agent responses:
  • Check if you have too many In Prompt documents
  • Consider moving large documents to Auto Search mode
  • Review total character count of In Prompt content
Outdated information:
  • Update documents directly in the Knowledge Base
  • Changes take effect immediately in new conversations
  • Consider setting up regular review schedules

Next Steps

Actions & Tools

Configure integrations and external tools

Playground

Test your agent with the knowledge base