Technology
7 min read9Apr 24, 2026
The AI Bill of Materials: Standardized AIBOM Formats Emerging in 2026
AIBOM is the SBOM equivalent for AI systems. The competing 2026 standards (CycloneDX-AI, SPDX-AI), what they capture, and which is winning.
All Posts
Technology
Conversational AI Technology
Deep dives into the technology behind AI voice agents — LLMs, speech-to-text, real-time voice processing, and more.
9 of 79 articles
Technology
8 min read5Apr 24, 2026
Agentic SDLC: How AI Changes Requirements, Design, Code Review, and Deployment
AI agents now participate at every SDLC stage. What changes in requirements, design, review, and deploy when agents are first-class collaborators.
Technology
8 min read4Apr 24, 2026
NIST AI RMF Generative Profile: Mapping Controls to Your LLM Stack
NIST's generative-AI profile updated the AI Risk Management Framework. How to map its controls to a real LLM stack in 2026.
Technology
9 min read10Apr 24, 2026
Claude Code, Cursor, and Windsurf: The 2026 AI IDE Landscape Benchmarked
The three AI IDEs that dominate developer workflows in 2026 — benchmarked on agentic capability, codebase awareness, and developer productivity.
Technology
8 min read7Apr 24, 2026
Choosing an Embedding Model in 2026: text-embedding-3, BGE, Voyage, Cohere
Embedding models are not interchangeable. The 2026 comparison of OpenAI, BGE, Voyage, Cohere, and the dimensions that matter for production RAG.
Technology
8 min read4Apr 24, 2026
RAG Privacy: Indexing Sensitive Data Without Leaking
RAG over sensitive data requires careful tenant isolation, embedding privacy, and access control. The 2026 patterns for safe RAG.
Technology
8 min read9Apr 24, 2026
Model Cards and System Cards 2026: What Regulators Now Expect by Default
Model cards graduated from research norm to regulatory expectation in 2026. The new schema, what to disclose, and what to keep proprietary.
Technology
8 min read7Apr 24, 2026
Prompt Caching Pricing 2026: Anthropic, OpenAI, Google, and the Savings Math
Prompt caching pricing varies a lot across providers in 2026. The numbers, the savings math, and how to architect for cache hits.