→ Engineering notes
How we build AI that ships to production.
Cost models, architecture patterns, eval, observability, and the integration work that decides whether an AI feature ever reaches real users. Written for engineers and the people who buy engineering.
- StrategyMay 21, 2026 · 8 min
Open-Source vs Closed-Source LLM for Business: A 2026 Decision Guide
Closed-source frontier models win on day one for most teams. Open-weights win when data residency, customization, or unit economics force the move.
Read post
- OperationsMay 20, 2026 · 9 min
How to Evaluate an LLM in Production: A Practical Eval Guide
Most teams skip eval until the model breaks in production. By then they cannot tell why. Here's the eval pipeline we build into every project.
Read post
- IntegrationMay 20, 2026 · 8 min
LLM Integration Services in 2026: How to Add AI to Your Business Without Creating Chaos
Adding a chatbot to your site is the easy part. Real LLM integration is a serious software engineering project that starts with the business process, not the model.
Read post
- OperationsMay 19, 2026 · 8 min
AI Cost Optimization in Production: Where the Money Actually Goes
Token spend is the part most teams discover too late. Here are the seven moves we apply on every production AI build to keep unit economics healthy.
Read post
- ArchitectureMay 19, 2026 · 9 min
RAG Implementation Services in 2026: How to Build AI That Understands Your Business Data
Most companies do not need an AI that knows the internet. They need an AI that understands their own documents, contracts, and support history. That is what RAG is for.
Read post
- ArchitectureMay 18, 2026 · 7 min
How to Choose a Vector Database for AI Search in 2026
Most teams overthink this. pgvector on the Postgres you already operate handles 95% of B2B use cases. Here's when the other options actually win.
Read post
- PricingMay 18, 2026 · 9 min
How Much Does It Cost to Build an AI Agent in 2026?
Simple AI agents start around €3,000. Production AI agents for real business work can hit €100,000 or more. The bracket depends on responsibility, not number of prompts.
Read post
- ArchitectureMay 15, 2026 · 8 min
Claude vs GPT-4o vs Open-Weights LLMs: Picking the Right Model in 2026
The right LLM depends on the task, not the brand. Here's the decision tree we use when scoping production AI builds for B2B teams.
Read post
- InfrastructureMay 15, 2026 · 8 min
Lambda Labs for AI Products in 2026: When Your AI App Needs Dedicated GPU Infrastructure
Lambda Labs gets mentioned the moment a team thinks about GPUs. The real question is whether the AI product actually needs dedicated GPU infrastructure, or whether managed APIs are still the right call.
Read post
- StrategyMay 14, 2026 · 7 min
How Long Does It Take to Build an AI MVP in 2026?
Three weeks from kickoff is realistic for a focused scope. Six is realistic for a real production system. Here's what each week actually contains.
Read post
- ArchitectureMay 13, 2026 · 9 min
RAG vs Fine-Tuning in 2026: A Decision Framework for Production AI
Almost every team gets this call wrong. The default answer is RAG, and fine-tuning is the last resort , but there are specific cases where the opposite is true.
Read post
- PricingMay 12, 2026 · 8 min
How Much Does a Custom AI Agent Cost in 2026? A Defensible Breakdown
The honest answer is between €15,000 and €120,000+, but the bracket depends on five inputs nobody quotes up front. Here's the breakdown we use when scoping.
Read post
Want this applied to your project?
Read the notes, then send the brief. We come back with a preliminary scope and a budget bracket within one business day.