Most AI models are built to be general. Enterprise work is specific. AISquared builds proprietary models for the real tasks that happen inside business systems: routing requests, applying guardrails, retrieving the right context, reading documents, and supporting workflow automation. These models are part of the Bolt model family and are built to work inside UNIFI, where data, context, models, actions, and feedback come together in one governed system. Instead of sending every request to one large model, UNIFI can use Bolt models to route each task to the right model or workflow. This helps teams improve speed, reduce cost, keep data under control, and get more reliable outputs in production.Documentation Index
Fetch the complete documentation index at: https://docs.squared.ai/llms.txt
Use this file to discover all available pages before exploring further.
Why Proprietary Models matter
Enterprises do not just need larger models. They need models that work well in their own environment. AISquared models are designed to:- Work with enterprise data and applications through UNIFI
- Produce structured outputs that business systems can use
- Support secure deployment, including on-prem, VPC, and restricted environments
- Improve RAG, document processing, and workflow automation
- Help control cost and latency through model routing
- Support guardrails, feedback, and ongoing quality checks
Introducing The Bolt Model Family
Our proprietary models are part of the Bolt family, built to support key parts of enterprise AI systems. Each model is focused on a specific job:Bolt Instruct
For structured outputs, routing, and guardrails Bolt Instruct models help UNIFI decide what should happen next. They support tasks where consistency, control, and safe behavior matter. Bolt Instruct can be used to:- Route requests to the right model or workflow
- Produce structured responses that systems can act on
- Classify tasks by type, risk, or complexity
- Detect sensitive data and unsafe content
- Support guardrails on inputs and outputs
- Power LLM-as-judge checks for quality review
- Support general chat and instruction-following tasks
Bolt Embedding
For accurate retrieval and context Bolt Embedding models help UNIFI find the right information before a model generates an answer. They are used to:- Retrieve relevant enterprise data
- Improve search across documents and systems
- Support RAG workflows
- Ground responses in trusted sources
- Reduce the risk of answers based on weak or missing context
- Bolt-Small for broad, fast candidate retrieval
- Bolt-Large for precision reranking
Bolt Vision
For document understanding and extraction Bolt Vision, also referred to as Bolt-VL in research, is built for business documents and visual content. It can be used to:- Extract fields from invoices, reports, and forms
- Read tables and layouts
- Convert unstructured documents into structured data
- Support approvals, data entry, and downstream workflows
- Answer questions about documents and images
How Bolt works within UNIFI
The Bolt model family is purpose-built to integrate seamlessly with the AISquared UNIFI platform, ensuring that AI outputs are securely and efficiently embedded into existing business applications. By excelling at targeted enterprise tasks, Bolt models are critical for maximizing UNIFI’s core value propositions: Model Flexibility, Enterprise Guardrails, and Closed-Loop Improvement.Bolt Instruct: Orchestration, Governance, and General Intelligence
Bolt Instruct models are the foundation for complex AI orchestration and governance within UNIFI.- General Chat & Instruction Following: Instruct models have been tuned to excel as conversational chatbots, able to respond to user requests quickly and effectively.
- Guardrails and Safety: Instruct models are used for providing guardrails on inputs and outputs, directly supporting UNIFI’s Enterprise Guardrails and Inline Governance features. The Guardrails and Safety Evaluation demonstrated that Bolt Instruct models achieve strong performance in detecting PII, unsafe content, and jailbreak attempts, even compared to larger production models. This ensures secure and compliance-aware operations for both enterprise and federal environments.
- Model Routing: By acting as the engine for routing requests to the appropriate downstream model(s), Bolt Instruct ensures optimal resource usage and cost efficiency. The Model Routing Evaluation confirmed the models’ effectiveness, achieving strong Strict and Lenient Accuracy metrics required for reliably orchestrating multi-model systems.
- LLM-as-a-Judge & General Capabilities: The models serve as a general chatbot, for translation, and for built-in LLM-as-a-judge functionality, which is vital for closing the feedback loop and iteratively tuning models. The models’ strong performance retention on reasoning benchmarks (ARC-Easy, BBH) ensures reliable decision-making and instruction-following for these complex, general-purpose tasks.
Bolt Embedding: High-Performance Retrieval for Enterprise RAG
Bolt Embedding models are essential for turning raw data into actionable knowledge within the UNIFI platform.- Search and Retrieval: Embeddings models convert ingested documents (from lakes, warehouses, and apps) to vector embeddings for search and retrieval. The model’s design for efficient, large-scale vector search supports UNIFI’s Plug-and-Play Data Integration.
- Reliable RAG: The Real-World RAG Evaluation is the key indicator of value. By achieving a lower average retrieval rank and more consistent performance on challenging queries than larger models like EmbeddingGemma, Bolt Embedding ensures that the UNIFI RAG pipeline retrieves the most relevant context reliably, leading to higher-quality, data-backed insights for end-users.
Bolt Vision: Unlocking Business-Critical Data from Documents
Bolt Vision models are designed to enable the ingestion and use of multimodal and unstructured data, a core requirement for enterprise intelligence.- Structured Data Extraction: Bolt Vision models are available to extract information from charts and tables, and to extract structured data from business documents like invoices, which UNIFI then sends to a downstream database. The Internal Invoice Benchmark validates this capability: the models exceeded the performance of Claude 4.6 Opus and GPT-5.2 on Line Item and Invoice Metadata Accuracy. This performance is critical for ensuring the extracted data is perfectly transcribed, preventing errors when added to downstream systems.
- Efficiency and Multimodality: The preserved general visual performance allows the models to answer multimodal chat queries. Furthermore, the model’s small size and efficiency—leading to over 60% reduction in hosting costs compared to other comparable models—supports UNIFI’s commitment to resource-constrained and on-premise deployment.