You are here:
Intelligent Context in Data 360
Intelligent Context is an AI-powered workspace where you interact with prompts to process unstructured data and create search index configurations tailored to specific business contexts.
Before you create a full search index, test a search configuration on a small set of unstructured data. Start by adding a few supported files in the Intelligent Context workspace. Respond to a series of prompts to check how your unstructured data is processed and verify that you're getting the expected results. Intelligent Context automatically saves your configuration as you work, and the configuration appears in the list view.
After testing your configuration, apply it to an unstructured data model object to create a precise, relevant search index.
Key benefits include:
- Improved search accuracy: Give your teams and users quick access to accurate information with LLM-powered content understanding, domain-specific intelligence, and user feedback loops.
- Multiple file-types support: Upload a wide variety of file types, such as .docx, .html, .jpeg, .jpg, .pdf, .png, .pptx, and .txt.
- Customizable views: Gain multiple business perspectives from a single document. Design each lens to prioritize information critical to specific business functions, so your teams can access relevant information without mining raw data.
- Low-code experience: Work with a user-friendly interface to turn unstructured data into configurable and consumable search indexes without extensive technical expertise.
- Efficient problem resolution: Address common issues, such as malformed tables in search results, and enable immediate diagnosis and problem resolution.
Intelligent Context Requirements and Limitations
- Intelligent Context requires generative AI features available through Agentforce. If you haven’t already, enable Agentforce.
- Intelligent Context isn’t supported when platform encryption is turned on.
How to Use Intelligent Context
Consider these essential use cases for Intelligent Context.
| Use Case | Description |
|---|---|
| Content understanding and end-to-end validation | Before using content in your production systems, upload a few sample documents to quickly verify whether the search index can find critical information. |
| Prompt-based customization | Fix extraction issues, such as a malformed table, by adding simple prompts without rebuilding the entire search index. For example, "extract the drivetrain table as markdown". |
| Test-to-production deployment | Validate search quality on sample files, then scale to thousands of documents by applying configurations to unstructured data model objects (UDMOs). |
Example: Adapting a Product Specification Document
To understand the utility of Intelligent Context within the Salesforce platform, consider how two different teams can create their own lenses to use a product specification document.
- Sales: Configure a sales lens to automatically extract information valuable to sales professionals, such as competitive advantages, pricing structures, and customer value propositions. This enables sales teams to quickly identify and articulate product benefits.
- Service: Configure a service lens to emphasize critical details for service and support teams, including support prerequisites, troubleshooting steps, and maintenance guidelines. This empowers the service team with quick access to information needed for customer success.
This Intelligent Context framework eliminates the need for different document workflows across business departments. By providing customized views of the same underlying data, Intelligent Context provides all your users with insights aligned with their objectives.
- Create a Intelligent Context Configuration
Creating a Intelligent Context configuration includes these key steps: uploading sample documents for evaluation, configuring the Intelligent Context configuration, testing the results, iterating on the configuration, and publishing to a search index. - Billing Considerations for Intelligent Context
Use of Intelligent Context impacts the consumption of credits used for billing in these usage types.
