> For the complete documentation index, see [llms.txt](https://academy.shade.inc/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://academy.shade.inc/guides/search-ai-and-archives/build-a-searchable-archive.md).

# Build a searchable archive

Combine transcripts, AI search, face recognition, filters, and saved views so anyone can find any shot in seconds.

**Outcome:** a library where you can find footage by what's in it ("drone shot of a forest in autumn"), by what was said ("basketball"), by who's in it, and by your own fields, and where the searches your team runs every week are saved as views.

**Who it's for:** archivists, librarians, and teams with years of footage that's hard to find.

**Time:** about an hour of setup. Indexing a large library takes longer and runs in the background.

## Before you start

* Get your media into Shade. See [Migrate from Dropbox or Google Drive](/guides/setup-and-migration/migrate-from-dropbox-or-google-drive.md) or [Mass migrating data to Shade via Rclone](/guides/setup-and-migration/mass-migrating-data-to-shade-via-rclone.md).
* Decide what shouldn't be searchable, such as HR material, raw card dumps, or render caches.

## Steps

{% stepper %}
{% step %}

### Keep noise out of the index

Right-click folders that shouldn't appear in AI search and choose **Exclude folder from AI**. To check or undo this later, open the drive's menu in the sidebar and choose **View AI Excluded Folders**. Faces in excluded folders aren't detected either.
{% endstep %}

{% step %}

### Let transcription do the logging

Shade transcribes video and audio that contains speech automatically, with time codes and speaker labels. Add the names, brands, and jargon Shade mishears to the workspace **Dictionary** (in the **Transcript options** menu of any transcript), so later transcripts get them right.

To find a spoken word across the whole drive, search for it in quotes, for example `"basketball"`.
{% endstep %}

{% step %}

### Teach Shade the people who matter

In **People**, create profiles for the people your team searches for most, with two or three clear photos each. Then you can search for a person doing something, for example `JJ throwing a football`. See [Facial Recognition](https://academy.shade.inc/ai-tools/facial-recognition).
{% endstep %}

{% step %}

### Add a few fields AI can fill

Add AI-filled fields for the things your team filters by, such as Shot type, Location type, and Tags. See [Design a metadata schema that scales](/guides/custom-objects-and-metadata/design-a-metadata-schema-that-scales.md).
{% endstep %}

{% step %}

### Teach your team to search in sentences

Press `Cmd/Ctrl + K` to search the drive, or `Cmd/Ctrl + F` to search the current folder. Describe the shot instead of listing keywords:

* Do: `drone footage of a forest in autumn on a mountain`
* Don't: `forest, trees, drone`

Then narrow the results by asset type, and right-click a good result and choose **Find Similar Assets** to find more like it. See [AI Search Best Practices](https://academy.shade.inc/ai-tools/ai-search-best-practices).
{% endstep %}

{% step %}

### Save the searches you repeat

Combine precision filters (date, extension, EXIF and IPTC data, your fields) into views for the requests you get every week, such as "Approved B-roll, 4K, last 12 months" or "Interviews with the CEO". See [Search and Discovery](https://academy.shade.inc/assets/search-and-discovery-transcription-and-precision-filtering).
{% endstep %}
{% endstepper %}

## Variations

* **Ask in plain language from an AI assistant:** connect the Shade MCP and ask Claude or ChatGPT to find footage for you. See [Use the Shade MCP with Claude or Cursor](/guides/search-ai-and-archives/use-the-shade-mcp-with-claude-or-cursor.md).
* **Keep it tidy:** run a duplicate check every few months. See [Clean up storage](/guides/search-ai-and-archives/clean-up-storage.md).

## Related guides

* [Design a metadata schema that scales](/guides/custom-objects-and-metadata/design-a-metadata-schema-that-scales.md)
* [Get alerted when a person appears in footage](/guides/automations/get-alerted-when-a-person-appears-in-footage.md)
* [Send Shade metadata into your editing app](/guides/editing-integrations/send-shade-metadata-into-your-editing-app.md)


---

# 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 following URL with the `ask` and `goal` query parameters:

```
GET https://academy.shade.inc/guides/search-ai-and-archives/build-a-searchable-archive.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `build a script that syncs our docs to a CMS` lets GitBook tailor the answer to that use case.

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.