Andreas Belitz
Blog Notes Projects About

All Posts

All AI Engineering 3D Printing & Making Tools & Workflow LLM Patterns Career & Thinking Infrastructure
More agents, less cost
Feb 27, 2026 · 5 min read · LLM Patterns

More agents, less cost

Running three AI agents sounds expensive. It's cheaper than running one — if you put the right model in each role.

agents claude-code cost llm-patterns
When one context window isn't enough
Feb 26, 2026 · 5 min read · LLM Patterns

When one context window isn't enough

Splitting a single AI agent into a team didn't just change the workflow — it changed how context flows through the whole system.

context-management agents claude-code architecture
I was the validator all along
Feb 25, 2026 · 5 min read · LLM Patterns

I was the validator all along

My AI coding setup worked — until I noticed I was spending more time checking output than building. The fix was giving the validation job to another agent.

agents claude-code workflow migration
What happens when the apprenticeship gets automated?
Feb 22, 2026 · 7 min read · Career & Thinking

What happens when the apprenticeship gets automated?

The tedious work of program management was never just overhead. It was also how we learned the craft. AI is automating that path — and nobody's talking about what replaces it.

program-management agile ai-tools career
Your .md files are a memory architecture (you just don't call it that)
Feb 19, 2026 · 8 min read · LLM Patterns

Your .md files are a memory architecture (you just don't call it that)

The manual context management patterns that work today map surprisingly well to the agent memory architectures being built for tomorrow.

context-management agents memory rag architecture
A starter prompt that actually remembers what you told it
Feb 18, 2026 · 7 min read · LLM Patterns

A starter prompt that actually remembers what you told it

I rebuilt my Claude Code starter prompt around .md files as external memory. Here's why and how.

claude-code context-management prompting workflow
Context hygiene: why your AI forgets what matters and what to do about it
Feb 17, 2026 · 10 min read · LLM Patterns

Context hygiene: why your AI forgets what matters and what to do about it

The biggest bottleneck in long-running AI sessions isn't model intelligence — it's context management. Here's what I've learned about keeping AI on track across complex, multi-sess...

context-window prompting workflow claude gemini
Hacking the Heat: Retrofitting Adax Heaters with ESPHome and Custom PCBs
Feb 12, 2026 · 8 min read · 3D Printing & Making

Hacking the Heat: Retrofitting Adax Heaters with ESPHome and Custom PCBs

A multi-phase journey from cloud-dependent heating to fully local, custom-hardware control.

esphome home-assistant pcb-design esp32 adax smart-home
Why I built this blog with Express instead of a static site generator
Feb 10, 2026 · 4 min read · Infrastructure

Why I built this blog with Express instead of a static site generator

There are faster ways to ship a blog. I picked Express + Handlebars anyway — here's why.

express architecture self-hosting
← Newer Page 2 of 2 Older →

© 2026 Andreas Belitz v:4e77f4b

RSS GitHub LinkedIn