Notes from the engineering desk.
Opinionated, evidence-led writing on the systems we build — AI engineering, cloud and FinOps, modernization, and architecture.
What is agentic AI, and how does it work
Agentic AI takes actions, not just answers. Learn how the agent loop, tool use, memory, and multi-agent systems work in production.
Read more
What Is Jev AI and How Does It Make Decisions Without Text
Jev is TypeSafe AI's System One model: it answers typed questions with calibrated probabilities instead of text. Here's how it works and where it fits.
Read more
Designing AI Integration for Existing Products
Learn how to add AI to existing products using practical patterns like API wrappers, event-driven enrichment, and gradual rollout without rewriting your core system.
Read more
Security by Design for Fast-Moving Engineering Teams
Learn how fast-moving engineering teams can integrate threat modeling into modern development workflows without slowing delivery or compromising security.
Read more
RAG vs Fine-Tuning vs Prompt Engineering for Enterprise AI
RAG, fine-tuning, or prompt engineering? A decision framework covering production trade-offs, cost drivers, and failure modes for enterprise LLM systems.
Read more
Building Production-Ready AI Copilots: Architecture, Guardrails, and Scale
Learn how to build AI copilots for production using scalable architecture, guardrails, enterprise security, observability, and retrieval best practices.
Read more
Retrieval Optimization in RAG Systems for Better Accuracy
Improve retrieval optimization in RAG systems with practical methods to reduce latency, improve context quality, and increase retrieval accuracy.
Read more