HelpCrunch AI Agents rely on data sources to generate accurate, helpful, and trustworthy responses. The quality and structure of your data directly impact how well your AI Agent performs.
🧠 What are Data Sources?
Data sources are the foundation of your AI Agent’s knowledge. These sources are used to find relevant answers when a customer asks a question.
There are currently two types of data sources (more coming soon):
-
Knowledge Base (KB): Pulls from your HelpCrunch knowledge base articles.
-
Custom Answers: Manually created Q&A pairs to guide or override AI behavior for specific questions.
🔁 Setting priorities between Data Sources
When creating an AI Agent (in the next step), you can set which source should be searched first by dragging the data sources up and down in the list.
For example:
-
Priority 1: Knowledge Base
-
Priority 2: Custom Answers
If no answer is found in the KB, the AI will check Custom Answers next. If no match is found at all, the AI will offer to connect with a human - instead of inventing a reply.
👉 Next Step
Create data stores to train your AI Agent
➡️ How to create an AI Agent and train it on specific data sources