Insights
Product, design, AI, and engineering perspectives from our team.
AI in production29 Mar 2026
Building Production RAG Systems: Beyond the Demo to Reliable Scale
Most RAG demos work beautifully with perfect documents and cherry-picked queries. Production RAG systems face messy reality — document diversity, edge cases, and 99%+ accuracy expectations that require systematic engineering across chunking, embedding, retrieval, and monitoring.
11 min readSarah Mitchell
AI in production29 Mar 2026
AI-Powered Document Processing: How We Handle 50,000 Documents a Month
Our AI-powered document processing pipeline handles 50,000 documents monthly with 94.3% accuracy, reducing processing time from 15 minutes to 2 minutes per document. This case study shows how we built an end-to-end solution delivering 367% ROI for an Australian logistics company.
8 min readChris Kerr