Anaqua - Enterprise AI & RAG Systems for Legal Tech

At RightHub (acquired by Anaqua), we built the entire AI backend from the ground up. This wasn't about adding AI features to an existing product — it was about fundamentally transforming how the platform handled knowledge, search, and decision-making.

The challenge was significant: take a successful IP management platform and infuse it with generative AI capabilities that enterprise customers could trust with their sensitive intellectual property data.

Over 2+ years, we architected and shipped systems now processing thousands of daily queries, enabling legal and IP professionals to work 50% faster while maintaining strict compliance requirements.

What We Built

• Enterprise RAG systems enabling semantic search across millions of IP documents, patents, and legal filings
• Autonomous AI agents that analyze documents, extract entities, and make recommendations with human oversight
• Context-Aware Generation (CAG) pipelines leveraging prompt chaining and session memory for personalized AI
• Multi-LLM orchestration with intelligent routing between OpenAI, Anthropic, and Gemini

Key Achievements

• Achieved 50% faster search through vector-based RAG systems
• Processing 10,000+ daily AI-powered queries with 99.9% uptime
• Reduced LLM costs by 40% through intelligent caching and routing
• Pioneered CAG methodology that became a core product differentiator
• AI capabilities were a key factor in the Anaqua acquisition

Technical Challenges Solved

• Legal document RAG — custom chunking respecting document structure and citation networks
• Reliable AI agents — structured output validation and human-in-the-loop for enterprise workflows
• Multi-LLM cost control — intelligent routing and prompt caching reducing redundant calls by 60%

AI & LLM

• OpenAI GPT-4
• Anthropic Claude
• Google Gemini
• LangChain / LangGraph
• RAG Pipelines
• AI Agents
• Model Context Protocol (MCP)

Backend

• Python / FastAPI
• Java / Spring Boot
• TypeScript

Data & Vector Search

• PostgreSQL
• PGVector
• JSONB
• LangSmith

Infrastructure

• GCP / AWS
• Docker / Kubernetes
• GitLab CI/CD