For the complete documentation index, see llms.txt. This page is also available as Markdown.

What are contents and why they matter

AIsuru lets you enrich your Agent's knowledge base with precise, personalized information through contents. This feature is essential for building a conversational AI that's truly tailored to your needs.

What are contents?

"Contents" are question-and-answer pairs that the Agent uses to respond to users. Having more contents increases the accuracy and precision of your Agent.

Why do they matter so much?

When a user asks your Agent a question, it will use all the tools at its disposal to respond:

  1. Contents come first: if the user's question is very similar to one already in the contents, AIsuru will respond with the answer already saved there

  2. If AIsuru can't find a matching content, it will pass the most relevant contents to the generative AI, which will respond based on: instructions, relevant contents and functions (advanced)

Creating and maintaining contents is essential for improving the quality of your Agent's responses.

Confidence threshold for contents

The confidence threshold is a parameter that determines how confident the Agent needs to be in order fo it to find the right content before delivering a content-based response.

How it works:

  • Low threshold: the Agent will respond even with content that only partially matches the user's question

  • High threshold: the Agent will only respond when it's very confident the content is relevant to the request

When to adjust it:

  • Raise the threshold if you notice the Agent giving irrelevant or incorrect answers

  • Lower the threshold if the Agent says "I don't know" too often, even for questions it should be able to answer

How to configure it:

  1. Go to your Agent's Settings

  2. Select the General section

  3. Find "Confidence threshold" and choose the level you want: Very low, Low, Normal, High, Very high

NOTE: Changing the confidence threshold can significantly affect response quality. We recommend testing your Agent carefully after each change and adjusting gradually.

Last updated