Long-form, evidence-backed writing on agentic AI — newest first.
Exploring the rise of single-cell foundation models like scGPT and Geneformer, spatial transcriptomics, and how transformer architectures are deciphering the complex language of gene expression.
DNA foundation models can now predict gene expression, identify regulatory elements, and classify variants from raw sequence alone. We review the major models—DNABERT-2, Nucleotide Transformer, Evo, and HyenaDNA—and what …
Claims of AI breakthroughs in biology are only as strong as their evaluation. This post critically examines benchmarks, metrics, and common pitfalls in evaluating biological AI models.
The bottleneck for AI in omics is often not the model but the data. This post covers the infrastructure, standards, and preprocessing pipelines that make omics data AI-ready.
Why transformer-style foundation models work so well on biological data, where the analogy to language breaks down, and which genomics, proteomics, and single-cell models matter most in 2026.
Before diving into AI, we need a clear map of what 'omics' actually covers. Each discipline studies a different layer of biological information, and AI readiness varies dramatically across them.
From multi-agent teams to self-architecting infrastructure, we explore the long-term vision of Agentic SRE and the challenges awaiting platform teams in 2027.
Agentic SRE doesn't eliminate SRE teams—it transforms them. As AI handles the pager, the human role shifts from firefighter to fire marshal, from operator to supervisor. Here is how team structures, on-call rotations, …
Building an SRE agent that works in a demo is easy. Building one that runs 24/7 without becoming a reliability problem itself requires a new architectural discipline. We explore the patterns for scalable, safe, and …
Disaster recovery plans are only as good as their last test. Most organisations test DR annually at best. Agentic SRE can run DR drills continuously, verify recovery procedures, and maintain an always-ready disaster …
