# AI models, vector and hybrid search

*Data 360 Consultant Study Guide · Data Enhancements, Sharing, and Analysis · Last updated October 16, 2026 · https://www.certifyforce.com/study-guide/data-360-consultant/data-enhancements-sharing-and-analysis/ai-models-vector-and-hybrid-search*

Matching customer scenarios to Data 360 AI tooling: AI Models sources and capabilities (regression, binary classification), where active predictions are used, and vector versus hybrid search indexes with their chunk and index objects and use cases.

- Certification: Salesforce Data 360 Consultant
- Exam section: Data Enhancements, Sharing, and Analysis
- Study guide: https://www.certifyforce.com/study-guide/data-360-consultant

**Official exam objective:**

> Apply predictive and generative AI tooling capabilities of Data 360 to customer scenarios.

## What the exam expects

- Choose the AI Models (formerly Einstein Studio) capability for a prediction: regression for a number, binary classification for one of two outcomes.
- Distinguish Custom, Connected and Salesforce-Enabled models, and say where an active model's predictions can be used.
- Choose vector or hybrid search from how users phrase queries, and explain how each index is built and stored.
- Match Data 360 (formerly Data Cloud) search to RAG, service, sales, automation and analytics use cases, and name the apps that query an index.
- Explain legacy "Data Cloud" and "Einstein Studio" labels during the rebrand.

Key terms:
- **AI Models:** the Data 360 tab for building, connecting and managing predictive and generative models.
- **Vector embedding:** a numerical representation of a unit of text that captures its semantic meaning.
- **Chunk DMO (CDMO):** stores the content chunks of a search index.
- **Index DMO (IDMO):** stores the vector embeddings of a search index.
- **Hybrid search:** vector search plus keyword search, with merged and ranked results.

## Key facts

| Fact | Detail | Source |
|---|---|---|
| Regression | Predicts a number | [Get to Know AI Models](https://trailhead.salesforce.com/content/learn/modules/build-ai-models-in-einstein-studio/get-to-know-einstein-studio) |
| Binary classification | Predicts one of two outcomes | [Get to Know AI Models](https://trailhead.salesforce.com/content/learn/modules/build-ai-models-in-einstein-studio/get-to-know-einstein-studio) |
| Active model predictions | Used in flows or batch transforms | [Get to Know AI Models](https://trailhead.salesforce.com/content/learn/modules/build-ai-models-in-einstein-studio/get-to-know-einstein-studio) |
| Connected model platforms | AWS SageMaker, Google Vertex AI, Databricks | [Get to Know AI Models](https://trailhead.salesforce.com/content/learn/modules/build-ai-models-in-einstein-studio/get-to-know-einstein-studio) |
| Einstein Studio rename | AI Models, spring 2026 | [Analyze Data and Build Predictive Models](https://trailhead.salesforce.com/content/learn/modules/data-cloud-analyze-and-predict/analyze-data-and-build-predictive-models) |
| CDMO | Stores content chunks | [Use Search for AI](https://help.salesforce.com/s/articleView?id=data.c360_a_search_index_ground_ai.htm&language=en_US&type=5) |
| IDMO | Stores vector embeddings | [Use Search for AI](https://help.salesforce.com/s/articleView?id=data.c360_a_search_index_ground_ai.htm&language=en_US&type=5) |
| Index consumers | Prompt Builder, AI agents, Tableau | [Vector Search](https://help.salesforce.com/s/articleView?id=sf.c360_a_search_index_vector_index.htm&language=en_US&type=5) |
| Hybrid ranking factors | Configurable, such as recency or popularity | [Use Search for AI](https://help.salesforce.com/s/articleView?id=data.c360_a_search_index_ground_ai.htm&language=en_US&type=5) |
| Data 360 rebrand | October 14, 2025; functionality unchanged | [Use Search for AI](https://help.salesforce.com/s/articleView?id=data.c360_a_search_index_ground_ai.htm&language=en_US&type=5) |

## Check yourself

- Why does a CDMO show text but no vectors?
- When is vector search enough without hybrid?
- Where can an active AI Models prediction be used?
- Which apps run vector searches on a Data 360 index?

## Sources

- [Use Search for AI, Automation, and Analytics](https://help.salesforce.com/s/articleView?id=data.c360_a_search_index_ground_ai.htm&language=en_US&type=5)
- [Vector Search](https://help.salesforce.com/s/articleView?id=sf.c360_a_search_index_vector_index.htm&language=en_US&type=5)
- [Get to Know Search Index Types in Data 360](https://trailhead.salesforce.com/content/learn/modules/search-index-types-data-cloud-quick-look/get-to-know-search-index-types-in-data-cloud)
- [Using Unstructured Data in Data 360](https://help.salesforce.com/s/articleView?id=data.c360_a_unstructured_data_connect_overview.htm&language=en_US&type=5)
- [Ground with Knowledge Using Retrieval Augmented Generation](https://help.salesforce.com/s/articleView?id=ai.prompt_builder_ground_rag.htm&language=en_US&type=5)
- [Get to Know AI Models](https://trailhead.salesforce.com/content/learn/modules/build-ai-models-in-einstein-studio/get-to-know-einstein-studio)
- [Analyze Data and Build Predictive Models](https://trailhead.salesforce.com/content/learn/modules/data-cloud-analyze-and-predict/analyze-data-and-build-predictive-models)
- [Bring Your Own Large Language Model](https://help.salesforce.com/s/articleView?id=data.c360_a_ai_foundation_models.htm&language=en_US&type=5)
- [Data 360 Limits and Guidelines](https://help.salesforce.com/s/articleView?id=data.c360_a_limits_and_guidelines.htm&language=en_US&type=5)

## About the full unit

The "Core concepts", "Exam traps" and "Worked scenario" sections of this unit, its 13 linked practice questions, and unlimited timed mock exams are included with the Data 360 Consultant pack (USD $19): https://www.certifyforce.com/practice-exams