Insights on AI development, technology choices, and business outcomes
Our AI development platform once pushed a live API key - despite having a secret scanner. The fail-open gap we found, and the fail-closed fix any AI pipeline can copy.
Multi-agent AI systems split work across a lead and sub-agents with isolated context. We build software this way — here's how super-agent harnesses really work and where the design choices matter.
Real-time RAG keeps an AI's knowledge current by indexing changes as they happen. We evaluated live-data indexing, hybrid retrieval, and reranking against how we build it.
