> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.twelvelabs.io/v1.3/agents/recipes/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.twelvelabs.io/_mcp/server.

# Recipes

Recipes for common tasks that you can use in your applications.

#### [Generate a corpus overview](/v1.3/agents/recipes/get-a-corpus-overview)

Summarize all your videos and images - themes, subjects, patterns, and key statistics.

#### [Agentic search](/v1.3/agents/recipes/agentic-search)

Have [Jockey](/v1.3/agents/concepts/jockey) interpret your query, reason across your videos and images, and explain each match.

#### [Extract entities](/v1.3/agents/recipes/extract-entities)

List every person, place, object, brand, and concept across your library.

#### [Find organization axes](/v1.3/agents/recipes/find-organization-axes)

Discover the best ways to categorize your videos and images.

#### [Enrich content](/v1.3/agents/recipes/enrich-content)

Apply a domain-specific lens - compliance, education, accessibility, SEO - for deeper analysis.

#### [Track entities across videos](/v1.3/agents/recipes/track-entities-across-videos)

Follow a subject across multiple videos through space and time.

#### [Organize a video library](/v1.3/agents/recipes/organize-a-video-library)

Discover the contents of a collection, find the best organization strategy, and categorize every video.

#### [Assemble highlight reels](/v1.3/agents/recipes/assemble-highlight-reels)

Find and sequence moments into highlight reels or curated playlists.

#### [Build a content agent](/v1.3/agents/recipes/build-a-content-agent)

Build multi-step agents that synthesize structured output from video footage.

## Docs

- [Generate a corpus overview](https://docs.twelvelabs.io/agents/recipes/get-a-corpus-overview.md): Summarize all your videos and images (themes, subjects, content types, patterns, and key statistics) in a single request.
- [Agentic search](https://docs.twelvelabs.io/agents/recipes/agentic-search.md): Perform agentic search over a knowledge store. Jockey interprets your natural-language query, reasons across the content, and returns structured, explained results.
- [Extract entities](https://docs.twelvelabs.io/agents/recipes/extract-entities.md): List all entities found across your videos and images (people, places, objects, brands, and concepts) with their type, frequency, and the items they appear in.
- [Find organization axes](https://docs.twelvelabs.io/agents/recipes/find-organization-axes.md): Discover the best dimensions for organizing your videos and images, scored by effectiveness.
- [Enrich content](https://docs.twelvelabs.io/agents/recipes/enrich-content.md): Apply a domain-specific lens to produce richer, more targeted analysis of your videos and images.
- [Track entities across videos](https://docs.twelvelabs.io/agents/recipes/track-entities-across-videos.md): Follow a subject across multiple videos and build a chronological timeline of appearances with timestamps, locations, and context.
- [Organize a video library](https://docs.twelvelabs.io/agents/recipes/organize-a-video-library.md): Discover the contents of a video collection, find the best organization strategy, and categorize every video in a multi-turn session.
- [Assemble highlight reels](https://docs.twelvelabs.io/agents/recipes/assemble-highlight-reels.md): Find and sequence relevant clips from a video collection based on a theme, topic, or criteria.
- [Build a content agent](https://docs.twelvelabs.io/agents/recipes/build-a-content-agent.md): Build a multi-step agent that produces structured creative output from video footage using domain-specific ingestion, instructions, and multi-turn refinement.