Stay organized with collections
Save and categorize content based on your preferences.
Overview
Knowledge documents are articles (for use with
Article Suggestion) or FAQ documents
(for use with FAQ Assist) that make up a
knowledge base. Agent Assist analyzes
an ongoing conversation between a human agent and an end-user and
suggests relevant knowledge documents or FAQ answers to the agent. For more
information on creating a knowledge base, see the
knowledge base tutorial. This document
highlights best practices that help to optimize the quality of suggestions.
Content
We recommend that you remove irrelevant content from your knowledge documents,
particularly at the beginning of documents. Article Suggestion shows the first
few sentences of a document to human agents as snippets to help the agents
understand what the document is about. If the beginning of a document
contains with irrelevant information, it could mislead the human agents. Common
irrelevant content includes: A navigation bar, last-modified dates, feedback
forms, and so on.
Format
Exclude documents with content that is mostly audio-, video- or image-based.
Article Suggestion and FAQ Assist process text content only.
If some of your documents are very long (more than 1000 words), we suggest that
you break them down into multiple short documents. This helps document
suggestion quality and also makes it easier for agents to find answers in the
suggested documents.
Document usefulness
We also recommend that you include only your most useful and frequently-visited
documents in the knowledge base. Which documents are most useful depends on
who will be seeing suggestions based on that knowledge base. For example, if you
intend to have tier-2 technical support agents seeing suggestions, you should
make sure to include documents that contain technical information and are often
viewed by the agents receiving the suggestions.
In addition to including useful docs, we also recommend that you exclude
documents that are inactive, out of date or very rarely visited. Such documents
are unlikely to be useful to agents.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-28 UTC."],[[["\u003cp\u003eKnowledge documents in Agent Assist are used for Article Suggestion and FAQ Assist, analyzing conversations to suggest relevant documents to human agents.\u003c/p\u003e\n"],["\u003cp\u003eIt is recommended to remove irrelevant content, especially at the beginning of documents, as these sections are shown as snippets to agents.\u003c/p\u003e\n"],["\u003cp\u003eDocuments containing mostly audio, video, or image content should be excluded, as Article Suggestion and FAQ Assist only process text content.\u003c/p\u003e\n"],["\u003cp\u003eLong documents (over 1000 words) should be broken down into shorter ones to improve suggestion quality and agent accessibility.\u003c/p\u003e\n"],["\u003cp\u003eKnowledge bases should contain the most useful and frequently-visited documents, tailored to the agents who will see the suggestions, and exclude inactive, outdated, or rarely visited documents.\u003c/p\u003e\n"]]],[],null,["# Best practices: Knowledge documents\n\nOverview\n--------\n\nKnowledge documents are articles (for use with\n[Article Suggestion](/agent-assist/docs/article-suggestion)) or FAQ documents\n(for use with [FAQ Assist](/agent-assist/docs/faq)) that make up a\n[knowledge base](/agent-assist/docs/knowledge-base). Agent Assist analyzes\nan ongoing conversation between a human agent and an end-user and\nsuggests relevant knowledge documents or FAQ answers to the agent. For more\ninformation on creating a knowledge base, see the\n[knowledge base tutorial](/agent-assist/docs/knowledge-base). This document\nhighlights best practices that help to optimize the quality of suggestions.\n\nContent\n-------\n\nWe recommend that you remove irrelevant content from your knowledge documents,\nparticularly at the beginning of documents. Article Suggestion shows the first\nfew sentences of a document to human agents as snippets to help the agents\nunderstand what the document is about. If the beginning of a document\ncontains with irrelevant information, it could mislead the human agents. Common\nirrelevant content includes: A navigation bar, last-modified dates, feedback\nforms, and so on.\n\nFormat\n------\n\nExclude documents with content that is mostly audio-, video- or image-based.\nArticle Suggestion and FAQ Assist process text content only.\n\nIf some of your documents are very long (more than 1000 words), we suggest that\nyou break them down into multiple short documents. This helps document\nsuggestion quality and also makes it easier for agents to find answers in the\nsuggested documents.\n\nDocument usefulness\n-------------------\n\nWe also recommend that you include only your most useful and frequently-visited\ndocuments in the knowledge base. Which documents are most useful depends on\nwho will be seeing suggestions based on that knowledge base. For example, if you\nintend to have tier-2 technical support agents seeing suggestions, you should\nmake sure to include documents that contain technical information and are often\nviewed by the agents receiving the suggestions.\n\nIn addition to including useful docs, we also recommend that you exclude\ndocuments that are inactive, out of date or very rarely visited. Such documents\nare unlikely to be useful to agents."]]
