Core Capabilities
1. AI-Driven Document Review- Identifies responsiveness, privilege, and issue relevance
- Supports multiple issues simultaneously
- Tailored to client protocols with minimal prompt engineering
- Allows case teams to ask natural language questions across document sets
- Answers are grounded in retrieved evidence and tailored to matter-specific knowledge
- Ideal for early case assessment, investigations, and fact discovery
- Structured knowledge entities from diverse sources (documents, facts, prior knowledge)
- Instructs the model through transparent, editable prompts
- Promotes consistency and auditability in outcomes
- Modular architecture for chat, search, and classification
- Flexible tuning for task-specific prompts
- Human-in-the-loop mechanisms embedded across flows
Key Components
Models
| Name | Capabilities | Version | Context (GPT tokens) |
|---|---|---|---|
| GPT-5.4 | Chat | 2026-03-05 | 272K tokens |
| Llama 3.1 70B | Chat | llama-3.1-70b-turbo | 32K tokens |
| AIDA Reasoning Model | Workflow, Search, Classification, Extraction | 2.0 | 128K tokens |
| AIDA Extraction Model | Search, Extraction | 2.0 | 128K tokens |
| AIDA Embedding Model | Search, Classification | 1.0 | - |
| Whisper Large V3 | Transcription | large-v3-turbo | - |
Security & Governance
- Secure cloud deployment options
- Full audit trail and role-based access control
- Model behavior can be reviewed and adapted by case teams
Extensibility
- Supports API integration with Relativity and Epiq Discovery
- Protocols and prompts are user-editable and version-controlled
- Custom classification model and knowledge management per matter or client
Use Cases
- Responsiveness/Issue Classification
- Privilege Classification
- Fact Discovery & Investigations
- Early Case Assessment
- Deposition Preparation