Our thinking.

We tested Mistral's Timestral and Google's TimesFM against ETS on Walmart and fresh-food data. The new models made up to 7.8% less error, out of the box.

Why agents need optimisation to orchestrate a company’s resources.

Enterprise Orchestration is a single system of intelligence that spans the full chain. It optimizes for system-wide KPIs, not departmental ones. And it coordinates decisions faster and better than any human planning cycle can.

We benchmarked leading Retrieval-Augmented Generation (RAG) tools, including RAGLite, OpenAI, Azure AI Search, and LlamaIndex, across industry datasets. Discover which systems consistently deliver accurate results, where others fall short, and why retrieval choice is a strategic decision.

Discover how decision intelligence transforms supply chains by making decisions transparent, automated, and AI-driven. This article explores a real manufacturing case at CNH Industrial, where DI optimizes safety stock, reducing delays, costs, and inefficiencies.

Struggling with massive datasets, slow labeling, or inconsistent model performance? Accelerate your computer vision workflow with image embeddings. Learn how to streamline data selection, cut labeling time, boost model performance, and handle data drift.

Is your AI system prepared for Europe’s new regulations? The EU AI Act is now in effect, transforming how engineers must design, test, and deploy AI. From prohibited practices to high-risk system requirements, this practical guide outlines everything developers need to know to ensure AI Act compliance before the 2026 deadline.

AI in logistics and supply chain: Optimizing processes and driving impact. Explore how AI optimizes demand forecasting, production planning, and inventory management, leading to more responsive and resilient supply chains.

This guide walks you through the process of building a powerful RAG pipeline using RAGLite. From configuring your LLM and database to implementing advanced retrieval strategies like semantic chunking and reranking, this guide covers everything you need to optimize and scale your RAG-based applications.

Discover RAGLite, a lightweight toolkit that revolutionizes Retrieval-Augmented Generation (RAG). With features like semantic chunking, adaptive retrieval, and hybrid search, RAGLite overcomes traditional RAG limitations, simplifying workflows and ensuring fast, scalable, and accurate information retrieval for real-world AI applications.

Unsupervised anomaly detection advances quality control in manufacturing by enabling efficient and flexible product defect detection with a minimal labelling effort and the ability to handle changing products and various defect types.

Time series foundation models hold promise in forecasting, but remain underdeveloped. Superlinear, AI consultancy, tests three models, TimeGPT, Lag-Llama, and Chronos, revealing mixed results, with traditional methods still outperforming them in many scenarios.

Learn how to implement efficient operations research (OR) solutions using OR-Tools. This guide offers practical tips, covering key strategies like optimizing variables and constraints, trying different solvers, and adding symmetry-breaking constraints.

Learn how to efficiently forecast timestamped tabular data by combining time series and tabular models. This approach is useful for applications like demand forecasting and predictive maintenance.

Superlinear’s Poetry Cookiecutter simplifies GPU setup for machine learning projects while boosting reproducibility. Developers can run code on CPUs or GPUs without modification.

Dive into the technical details of continuously retraining a recommender system with MLOps. Learn how MLOps can improve the effectiveness of ML projects and ensure continuous optimization for ML Engineers.

Explore how to implement live predictions for key business metrics using MLOps. This in-depth post offers technical insights for Machine Learning Engineers on building effective MLOps Stacks for real-time applications.

Learn how to serve and scale multiple computer vision models for mobile apps with MLOps. This guide provides detailed technical insights for ML Engineers on how to build robust MLOps frameworks.

Understand the key principles shared between MLOps vs DevOps. This post explains how to apply DevOps best practices to MLOps for smoother AI integration and quicker model deployment.