Writing on AI Engineering & Architecture
Articles on putting AI into real products: retrieval without a vector database, model running costs, typed decisions and agents, from systems we run.
Every figure sourced, every price from our published rates.
Showing 1–8 of 8 articles
Self-Hosted LLM: When Does Running Your Own Model Beat an API?
A self-hosted LLM keeps prompts on servers you control. See what it costs against an API, the hardware it needs and when the hosted model still wins.
AI app development cost: what you pay to build it, and every month after
AI app development cost is two numbers: the build, priced in people and months, and a running bill that never stops. How to estimate both, and cut them.
Jev by TypeSafe AI vs an LLM: Decisions, Not Text
TypeSafe’s Jev returns typed answers and probabilities in one pass. Where a System One model beats an LLM in a real product, and where it does not.
You do not need a vector database for your first RAG chatbot
RAG without a vector database: for a few hundred pages, BM25 keyword search is enough. No embedding bill, and no data leaving your own server.
What Is Agentic AI, and How Does It Work in 2026
Discover what Agentic AI is, how it works, and why autonomous AI agents are transforming business, automation, and decision-making in 2026.
How AI Is Transforming Software Development in 2026: What Businesses Must Know
Discover how AI is revolutionizing software development in 2026 with intelligent automation, faster delivery, and scalable solutions.
-1024x576.webp&w=3840&q=75)
Scaling AI Automation: Enterprise Integration with Model Context Protocol (MCP)
Connect AI automation to your existing tools with the Model Context Protocol, with secure access to your data.
Architecting Multi-Agent Systems for Complex Workflows
Learn how to architect multi-agent AI systems for complex workflows, improving automation, collaboration, scalability, and business efficiency.
Need this built?
We build websites and apps for businesses, and work behind digital agencies as their development team. Tell us where things stand on a 20-minute call.