What are eDiscovery and DeepDive?
eDiscovery and DeepDive are AI-powered features within Cognitive CDE that help users find and understand information from project documents.
eDiscovery searches across all project documents to answer user queries. It scans multiple files and returns relevant information along with source references and AI relevancy indicators.
DeepDive allows users to select a specific file and ask detailed questions about its content. It provides responses based only on that file.
NOTE: eDiscovery and Deepdive are part of the Cognitive CDE add-on and incur commercial costs. Please contact your Asite representative or the Customer Success team for more details.
Prerequisites
Privileges
Role Privilege | Description |
Can Access Cognitive CDE | Allows users to access and use Cognitive CDE features. |
System Requirements
System Requirement | Description |
Project Vectorisation | Only vectorised Projects can be accessed by eDiscovery and DeepDive. |
TIP: For information on how to vectorise a Project, check Vectorising Project.
How Do I Access eDiscovery?
Navigate to the Files tab.
Click Cognitive CDE.
In the top bar, click the dropdown menu
.
Select the relevant, vectorised Project.
The Cognitive CDE screen will appear, where you can interact with eDiscovery for the selected Project.
Understanding eDiscovery
Once a Project is vectorised, eDiscovery allows users to ask questions and generate summaries across all files within that Project.
Users can interact with it conversationally and retrieve insights from multiple documents.
It works with the Translation Agent, allowing queries and responses in different languages.
Users can view conversation history and control how results are displayed.
The screen is divided into three sections:
Left section: Displays the selected Project, conversation history, and an option to start a new conversation.
Middle section: Displays the active conversation.
Right section: Displays source files used in responses, along with their AI relevancy percentages.
Number | Title | Description |
1 | Project Name | Displays the selected Project. |
2 | RAG (Retrieval Augmented Generation) Bar |
|
3 | Chat History | Lists all current and previous conversations. |
4 | New Conversation | Starts a new conversation. |
5 | View Controls | A set of controls to manage how results are displayed:
|
How Do I Access DeepDive?
Once you've implemented eDiscovery (refer to How Do I Access eDiscovery?), you can access DeepDive directly from the file list on the right-hand side:
Locate the File in the right-hand panel.
Click Explore with AI.
The file will open in full view with a chat panel on the right. You can ask questions and receive responses based only on that file.
Understanding DeepDive
DeepDive is designed for the focused analysis of a single file.
With DeepDive, users can:
Ask highly specific questions about file content.
Request clear explanations or summaries of complex sections.
Engage in a conversational back-and-forth, refining your questions as you go.
DeepDive provides context-aware responses based solely on the selected file, enabling detailed exploration without referencing other documents.
eDiscovery and DeepDive
Function | eDiscovery | DeepDive |
Scope of query | Processes queries across the entire vectorised project. | Restricts queries to a single file selected by the user. |
Summarisation | Generates summaries spanning multiple documents. | Generates focused summaries on an individual file. |
Interpretation style | Operates in retrieval mode (matches exact or similar content). | Operates in a contextual cognitive interpretation mode (understands structure and meaning). |
Metadata configuration | Customisable attributes in the RAG bar via the Customise button. | Not applicable. |
System prompts | Does not support system prompts. | Supports system prompts for more controlled output. |
Scalability | Suitable for large-scale Projects (hundreds of thousands of files). | Suitable for deep analysis of individual files, including lengthy reports and technical drawings. |
Intended use case | Breadth: discovery, analysis at the Project level. | Depth: exploration, interrogation of a single file. |
Related Articles: Cognitive CDE