​
Overview

A Knowledge Pack is a structured collection of business-specific information that your AVA agents can reference during live calls. This could include documents, manuals, FAQs, policies, pricing sheets, and even entire web pages. By attaching a Knowledge Pack to an inbound agent or outbound project, you ensure that the AI responds with accurate, context-specific information every time. Key capabilities:
  • Attach to both inbound and outbound configurations.
  • Upload multiple supported file types.
  • Use URL scraping to pull and reference live web content.
  • Enable or disable packs without losing stored content.
  • Edit, refresh, and manage packs directly from the configuration panel.
  • Maintain separate packs for different products, brands, or departments.
Supported file types:
  • .csv, .xlsx, .pdf, .txt, .docx (up to 50MB per file; 500MB total per pack)
  • Web page content via URLs.
Plan limits:
  • Business Professional – 1 Pack
  • Business Growth – 2 Packs
  • Agency Lite – 1 Pack
  • Agency Unlimited – 2 Packs
🚫 Note: Sub-accounts cannot access Knowledge Packs created by an agency’s main account.

​
Setting Up a Knowledge Pack

​
Plan Credits and Transfers

Your Knowledge Pack usage is tied to your account’s plan credit allocation. Each pack consumes credits when processing calls that require its data. You can monitor your remaining credits from the Payments screen. Credit counter: Displays in real-time how many credits remain for the billing cycle.
Credit transfers: If you manage multiple sub-accounts, you can transfer credits between them to balance usage across projects and agents.

​
Optimization

Knowledge Packs work best when the content is clean, concise, and well-structured. Following these guidelines helps optimize accuracy and minimize latency (expect ~100ms additional latency, generally not noticeable). Best Practices:
  • Use .md (Markdown) as the preferred format.
  • Avoid images and tables — agents may struggle to process these formats.
  • Keep information relevant to the Knowledge Pack’s purpose.
  • Write in short paragraphs and lists; concise information “chunks” are easier to process.
  • Use clear, descriptive headings:
    • Start each section with a ## heading and keep it focused.
    • If a section is long, break it into ### subheadings.
  • Group related information under the same section to clarify relationships.
  • Be specific — avoid ambiguous pronouns like “it” or “this”; instead, use explicit names, dates, or units.
  • If the agent provides inaccurate answers, review the source formatting. Clean Markdown with well-structured paragraphs works best.
  • Use granular, page-specific URLs instead of broad site URLs.
  • Supply knowledge, facts, and supporting information — avoid including instructions or prompt text.
Example format: 
# Who we are
Company description here...

### Company Vision
Details here...

​
FAQs & Troubleshooting

​
General Questions

​
Configuration

​
Usage and Results

For additional questions or guidance, try using our Virtual Support Agent! Available 24/7 to help resolve most issues quickly at thinkrr.ai/support. If you still need assistance, visit our support site at help.thinkrr.ai and submit a Ticket or contact our team directly at hello@thinkrr.ai.