Sep
1,
2025
AI Security in Focus: Managing Identity, Model Drift, and LLMOps Risks
In this blog, we share two in-depth articles: one explores the AI triple threat and why identity security must be the cornerstone of adoption, while the other looks at LLMOps and how to manage model drift for the safe use of large language models. Together, they highlight the dual challenge...
The Expanding Scope of Observability for AI Systems
Observability is undergoing a big change in the era of AI and must now cover model and data drift, autonomous decision making, intent and outcome alignment, and more. This article gives some best practices for the next-generation of AI-native observability, examines potential challenges, and looks towards the future of achieving...
Jul
30,
2025
Are AI Tools Hurting Developer Productivity?
A recent study [1] suggests that developers may become less productive when using AI tools. We've asked our experts to weigh in: Is this a temporary setback, a methodological flaw, or a sign of things to come?
Jul
21,
2025
MCP vs A2A: Architecting AI Agent Communication for Enterprise
The AI landscape is shifting towards collaborative, specialized agents. This article provides an essential comparative analysis of emerging AI agent communication protocols: Anthropic's Model Context Protocol (MCP) and Google's Agent-to-Agent (A2A). For ML/AI developers and technical leaders, understanding these frameworks is crucial for building scalable, secure, and composable AI systems....
Jul
17,
2025
Can GenAI Build Satellites?
How can engineers use GenAI, RAG, and MLOps to tackle the complexity of aerospace projects? From managing thousands of documents to building smarter systems faster, this session shows how AI is transforming the future of systems engineering.
Jul
7,
2025
RAG & MCP for ML Devs: Practical AI Implementation
This article, featuring insights from Robert Glaser at JAX Mainz, dives into practical AI implementation strategies. We explore why Retrieval-Augmented Generation (RAG) is a foundational technique and how the emerging Model Context Protocol (MCP) is poised to revolutionize AI agent development.
Apr
29,
2025
Deep Learning with Category Theory for Developers
This article looks under the hood of deep learning and is perfect for any machine learning developers looking to understand the basics. We’ll show that deep learning can also be approached differently (and much more simply), using slightly more advanced (but not complicated) mathematics and functional programming.
Mar
13,
2025
Exploring DeepSeek: How a New Player is Challenging AI Norms
In this interview, Dr. Pieter Buteneers shares his thoughts on the emerging AI company DeepSeek. We explore the technology behind it, discuss its potential impact on AI development, and touch upon the opportunities and challenges of this innovation.
Feb
26,
2025
Agentic AI: The Future of Business Process Automation
This article explores how Agentic AI revolutionizes the business process layer, enabling companies to achieve greater efficiency, adaptability, and competitive advantage. We will uncover how enterprises can transition towards self-optimizing, AI-driven workflows by examining its foundational principles, real-world applications, and future implications.
How Ollama Powers Large Language Models with Model Files
The rise of large language models (LLMs) has transformed the landscape of artificial intelligence, enabling advanced text generation, and even the ability to write code. At the heart of these systems are foundation models built on transformer models and fine-tuned with vast amounts of data. Ollama offers a unique approach...