Articles

Notes from building real things

Web, React and Next.js, AI and RAG, and mobile. Written from production work, not tutorials about tutorials.

Our LLM Fallback Worked Perfectly. That Was the Problem.

During a model outage, a fallback on a review-reply product I lead posted generic English replies to Swedish businesses' Google profiles for days, and every dashboard stayed green. This is the publish gate and the per-path fail-closed rule I use now.

Sep 21, 2026· 11 min read

Isometric pipeline of glowing message blocks passing through a gate, with one block held in a side tray under a warning beacon.

Agents in Production

Context Rot Is Killing Your Long-Running Agent: A Compaction Playbook That Survives 100k+ Tokens

Long-running agents do not fail because they run out of tokens. They fail because accuracy drops as the context grows. Here is the compaction playbook I use to keep agents reliable past 100k tokens: trigger-based compaction, anchored iterative summarization, per-tool context feedback, and offloading state to external memory.

Jun 29· 9 min read

Agents in Production

Claude Opus 4.8 Dynamic Workflows: How to Run Hundreds of Parallel Subagents Without Burning Your Budget

Opus 4.8 makes hundreds of parallel subagents practical for codebase-scale work. Here is how I scope the fan-out, why the verification gate matters more than the model, and a real token and cost model with the fast mode that runs roughly 3x cheaper, plus where it overspends.

Jun 15· 9 min read

Building something similar?

I take on a few projects at a time: web apps, AI features, and mobile. Tell me what you are working on.

Start a conversation