# Knowledge Vault ### About this export | Field | Value | | --- | --- | | **content_type** | lesson | | **platform** | contentstack-academy | | **source_url** | https://www.contentstack.com/academy/courses/brand-kit-foundations/knowledge-vault | | **course_slug** | brand-kit-foundations | | **lesson_slug** | knowledge-vault | | **markdown_file_url** | /academy/md/courses/brand-kit-foundations/knowledge-vault.md | | **generated_at** | 2026-05-11T07:02:20.622Z | > Part of **[Brand Kit Foundations](https://www.contentstack.com/academy/courses/brand-kit-foundations)** on Contentstack Academy. **Academy MD v3** — structured for retrieval; no quiz or assessment keys. #### Video details #### At a glance - **Title:** Knowledge Vault- - **Duration:** 4m 14s - **Media link:** https://cdn.jwplayer.com/previews/M1oETwD7 - **Publish date (unix):** 1717202348 #### Streaming renditions - application/vnd.apple.mpegurl - audio/mp4 · AAC Audio · 113582 kbps - video/mp4 · 180p · 180p · 154642 kbps - video/mp4 · 270p · 270p · 184264 kbps - video/mp4 · 360p · 360p · 208745 kbps - video/mp4 · 406p · 406p · 225191 kbps - video/mp4 · 540p · 540p · 279025 kbps - video/mp4 · 720p · 720p · 375567 kbps - video/mp4 · 1080p · 1080p · 663873 kbps #### Timed text tracks (delivery) - **thumbnails:** `https://cdn.jwplayer.com/strips/M1oETwD7-120.vtt` #### Video transcript Knowledge Vault will act as the central hub for all your brand's essential materials. It's where you can manage, store, and organize your documents, data, and content related to the brand. This repository acts as a reference point for Generative AI, ensuring that the content it creates is based on accurate brand information. The Vault can house everything from brand guidelines and product specifications to help center resources, historical content, and any other documents that capture the personality of your brand's voice and style. So how does it work? A Knowledge Vault functions as a specialized vector database, tailor-made for storing and retrieving information that you have curated in a format that's ideal for AI language models. Unlike traditional databases that keep text in its raw form, a vector database transforms text into numerical formats known as embeddings or vectors. These embeddings encapsulate the semantic meanings and relationships between words and concepts, enabling AI to grasp the context and subtleties of the information contained within the Knowledge Vault. When a user or program like Automate requests a content generation task, such as creating a product description, the AI first consults the Knowledge Vault. The Knowledge Vault then identifies the most relevant information in the database by comparing the query with the stored embeddings for semantic similarity. This relevant information, along with the additional details like a voice profile, is compiled to form the prompt sent to the AI model. This accurate background information grounds the AI in factual data specific to the company, significantly enhancing the relevancy and accuracy of the generated content. Knowing how it works is really helpful as you think about what type of content to include in the Vault. The most effective content for a Knowledge Vault centers on factual, company-specific information. General information is likely already included in the large language models training and doesn't need to be added. Things like company background, which would include company history, a mission statement, core values, brand guidelines, and style guidelines. You may also want to include information on your products and services, like descriptions, technical specifications, and use cases. Maybe you want to add training materials, sales presentations, or white papers. All of these are highly relevant to your organization. Of course, there's pieces of content that you probably want to avoid including in your Knowledge Vault. Outdated documentation, old blog posts, confidential information, and ambiguous content. Ultimately, you're looking for quality content that will support your brand's overall voice. There's two ways you can populate a Knowledge Vault, either through APIs or you can use our recipes within Automate. To show you where to find BrandKit within Automate, navigate to Automate on the left-hand side. Once you click the icon, you'll enter the Automate screen. And here, you can create a new automation. We'll go ahead and provide it a name. I'll call this Compass Knowledge Vault. Then, if you move to the Action step, you'll notice there's a new connector for BrandKit. When you select it, notice all the different actions for Knowledge Vault and Voice Profile. Setting up an automation is simple for BrandKit. If you need to know more about automations, check out our Automate Foundation course here on Academy. #### Key takeaways - Connect **Knowledge Vault** back to your stack configuration before moving to the next module. - Capture one concrete artifact (screenshot, Postman call, or code snippet) that proves the step works in your environment. - Re-read the delivery versus management boundary for anything you changed in the entry model. ## Supplement for indexing ### Content summary Knowledge Vault. Knowledge Vault in Brand Kit Foundations (brand-kit-foundations). ### Retrieval tags - Knowledge - Vault - brand-kit-foundations - lesson 03 - Knowledge Vault - brand-kit-foundations lesson ### Indexing notes Index this lesson as a primary chunk tagged with lesson_id "03" and topics: [Knowledge, Vault]. Parent course slug: brand-kit-foundations. Use asset_references URLs as thumbnail hints in search results when present. Never surface LMS quiz content or assessment answers from this file. ### Asset references | Label | URL | | --- | --- | | Video thumbnail: Knowledge Vault | `https://cdn.jwplayer.com/v2/media/M1oETwD7/poster.jpg?width=720` | ### External links | Label | URL | | --- | --- | | Contentstack Academy home | `https://www.contentstack.com/academy/` | | Training instance setup | `https://www.contentstack.com/academy/training-instance` | | Academy playground (GitHub) | `https://github.com/contentstack/contentstack-academy-playground` | | Contentstack documentation | `https://www.contentstack.com/docs/` |