Skip to main content
Your agent’s responses are only as good as the knowledge you provide. InboxMate supports three types of data sources.

Website scraping

Enter a URL and InboxMate will crawl the page and extract its content into your knowledge base.
  • Each scrape counts toward your plan’s monthly scrape limit
  • Scrapes capture text content — not images, videos, or JavaScript-rendered content
  • Re-scrape pages when content changes to keep your agent up to date
Scrape limits vary by plan: Starter (25), Pro (100), Business (500).

PDF uploads

Upload documents like product catalogs, policy documents, or technical manuals. The content is extracted and added to your knowledge base.
  • Supported format: PDF
  • File size limits vary by plan
  • Each upload counts toward your monthly PDF limit

Custom knowledge items

The most precise way to control your agent’s responses. Create focused entries for specific topics.

Knowledge item types

TypeBest for
Q&ASpecific questions with definitive answers
OverviewGeneral topic summaries
PricingProduct and service pricing details
PolicyReturn, shipping, and other policies
ContactContact information and business hours
Prefer many focused items over fewer large ones. An item about “Return policy” is more useful than a single item covering “All policies.”

Knowledge buckets

Knowledge items are organized into buckets (vector stores). Each agent is linked to one bucket.
  • Create separate buckets for different use cases or testing
  • Switch an agent’s bucket to instantly change its knowledge base
  • Share buckets across agents if needed