Agentic AI

The genome is the ultimate source code. For decades, computational biologists have relied on alignment algorithms, hidden Markov models, and specialized machine learning to decode it. Today, a new paradigm is taking hold: DNA foundation models. By treating the genome as a vast, continuous text and training large language models (LLMs) on billions of nucleotides, researchers are teaching AI to “read” the book of life in its native language. In this fifth installment of our Agentic Omics series, we examine the state of the art in genomic AI. We explore how models like DNABERT-2, Nucleotide Transformer, Evo, and HyenaDNA are moving beyond sequence classification to predict gene expression, identify regulatory elements, and quantify variant effects. Crucially, we will dissect the architectural innovations that make this possible—and the biological complexities that still confound these models. ...

When a new foundation model in computational biology is released, the accompanying paper inevitably features tables of bolded numbers demonstrating state-of-the-art performance. Whether it is predicting protein structures or annotating single-cell data, the claims are often spectacular. But how do we truly know if these AI systems work in ways that matter to biology, rather than just optimizing arbitrary computational metrics? For the vision of Agentic Omics to become reality—where autonomous agents orchestrate models like AlphaFold and DNABERT-2 to drive drug discovery—we need a rigorous understanding of when these models succeed, when they hallucinate, and when their benchmarks deceive us. Claims of AI breakthroughs are only as strong as their evaluation methodologies. ...

The bottleneck for AI in computational biology is rarely a shortage of sophisticated models; it is the sheer difficulty of making biological data AI-ready. The “Agentic Omics” vision—where autonomous AI agents orchestrate domain-specific models to accelerate drug discovery—fundamentally rests on the assumption that these agents have access to standardized, clean, and computable data. In this post, we explore the unglamorous but critical foundation of omics AI: the data infrastructure. We trace the journey from raw sequencing reads to the structured tensor formats required by modern foundation models, exploring the evolving standards, the scale of the challenge, and how cloud infrastructure is adapting. ...

Welcome back to Agentic Omics: When AI Reads the Book of Life. In our first post, we mapped the complex, multi-layered territory of modern biological data. We saw that while fields like metabolomics are still wrangling with extreme chemical complexity, disciplines defined by sequences—genomics, transcriptomics, and proteomics—are experiencing a massive influx of AI-ready data. But data alone isn’t enough. The true catalyst of the current biological AI revolution is a specific architectural breakthrough originally designed to translate English to French: the Transformer. ...

Welcome to the first installment of Agentic Omics: When AI Reads the Book of Life. In this 24-part series, we will systematically review the state of the art of Artificial Intelligence (AI) across all major omics disciplines. We will explore how large language models, foundational transformer architectures, and eventually fully autonomous “Agentic Omics” systems are orchestrating domain-specific models to accelerate drug discovery, personalized medicine, and our fundamental understanding of biology. ...

As we conclude our series on Agentic SRE, it’s time to pull back and look at the broader horizon. Over the past 11 posts, we’ve explored how autonomous agents are transforming incident response, change management, chaos engineering, and disaster recovery. But what happens when these point solutions fuse into a cohesive, system-wide paradigm? The transition from human-driven runbooks to AI-assisted operations was profound, but the shift from single-agent task execution to multi-agent, self-architecting systems will redefine the very nature of infrastructure. As we look toward 2027 and beyond, the technological landscape is shifting from fragmented AIOps tools to dynamic “agentic ecosystems” [1]. ...

If you ask an SRE in 2026 what their biggest fear is, it’s rarely “the site is down.” Agents like Sherlocks.ai or Azure’s SRE Agent handle that before the human even wakes up. The new fear is subtler: de-skilling. In the previous posts of this series, we’ve built a technological marvel: autonomous incident response, self-healing infrastructure, and AI-driven chaos engineering. But technology doesn’t exist in a vacuum. As we hand the pager to AI agents, the role of the human Site Reliability Engineer is undergoing its most radical shift since Google coined the term in 2003. ...

It is relatively easy to build an SRE agent that can solve a single, well-defined problem in a demo environment. You give it a prompt, access to a few tools, and watch it restart a pod or query a log file. It feels like magic. But taking that agent and asking it to run 24/7, monitor thousands of services, handle concurrent incidents, and never hallucinate a destructive command is a different engineering challenge entirely. It moves us from the realm of “AI scripting” to distributed systems architecture. ...

Disaster Recovery (DR) has traditionally been the “eat your vegetables” of IT operations: universally acknowledged as vital, but often neglected until a crisis forces the issue. In the pre-agentic era, DR testing was a high-stakes, high-effort event—a “Game Day” that required weeks of coordination, executive sign-off, and often a weekend of anxious monitoring. The result? Most organizations test their full DR plans annually at best. Between these rare tests, infrastructure drifts, configurations change, and the “tested” recovery plan slowly decays into fiction. ...

When Netflix introduced Chaos Monkey over a decade ago, the premise was radically simple: randomly terminate instances in production to force engineers to build resilient systems. It was blunt, effective, and terrified everyone who wasn’t Netflix. Over time, chaos engineering matured. We moved from random destruction to controlled experiments. Tools like Gremlin, Chaos Mesh, and LitmusChaos allowed SREs to precisely target blast radiuses—injecting latency into a specific microservice or dropping packets between two zones. But even with these tools, chaos engineering remained a high-friction activity. It required an SRE to hypothesize a failure mode, write the experiment code, schedule a “game day,” run it manually, and analyse the results. ...