> For the complete documentation index, see [llms.txt](https://docs.useagentdock.xyz/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.useagentdock.xyz/resources/quality-standards.md). # Knowledge Base Quality Standards AgentDock is a curated marketplace. The quality of the knowledge bases available is a core part of the product. These standards define what constitutes a high-quality listing and the basis on which listings can be removed. *** ## What makes a strong knowledge base **Specificity.** The best knowledge bases cover a well-defined domain with depth. A corpus of SEC 10-K filings from 2018 to 2024 is more valuable than a general "business documents" collection. Buyers search for specific knowledge; listings with a clear scope match well. **Provenance.** Buyers want to know where the content came from. Include source information in your description: what documents, from what sources, covering what time period. If the content comes from primary sources (official filings, research institutions, court records), say so. **Recency and maintenance.** For time-sensitive domains (regulatory guidance, market data, scientific literature), freshness matters. Subscription listings that are actively updated command higher prices and better ratings. State clearly when the content was last updated. **Clean ingestion.** Content that chunks and embeds cleanly produces better retrieval results. Remove boilerplate, navigation elements, repeated footers, and tracking artifacts before upload. Test your listing with representative queries before publishing. *** ## Content policy By publishing a knowledge base on AgentDock, you represent that you own or have the rights to distribute the content. The following types of content are not permitted: * Content that infringes third-party copyright or intellectual property rights * Personal data of individuals who have not consented to its use * Content that was obtained through unauthorized access or scraping in violation of a site's terms of service * Fabricated or synthetic data presented as genuine * Malicious content intended to produce harmful outputs when used in AI applications AgentDock uses content hashing to detect previously reported infringing content. Listings that are reported by rights holders or flagged by our review process may be paused or removed while an investigation is conducted. *** ## Review process During the private beta, all new listings are reviewed before they are made publicly visible. Open beta listings are subject to automated quality checks and a sampling review. Listings that pass the review process are published without further delay. *** ## Ratings and reviews Buyers can submit a rating (1 to 5 stars) and a written review for any knowledge base they have purchased. Ratings are aggregated into the listing's displayed score. Listings with an average rating below 2.5 after a minimum of 10 reviews are automatically demoted in search results. Listings with an average below 2.0 after 20 reviews are reviewed by the AgentDock team and may be paused. As a creator, you can respond to reviews from the listing management panel. *** ## Appeals If a listing is paused or removed and you believe the decision was made in error, you can submit an appeal through the creator dashboard. Include any documentation supporting your ownership or rights to the content. Appeals are reviewed within 5 business days. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.useagentdock.xyz/resources/quality-standards.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.