Jul 23, 2026·1 MIN READ
Build your observability to fail loud
A silent failure is worse than a crash. How one invisible outage forced an AI pipeline's observability to fail loud instead of lying with a green light.
Jeff Liu
·AI-Native UX Engineer · Multi-Agent SystemsField notes from building AI-native products end to end, the pipeline, the interface, and the reading experience.
How I BuildBuild Log
12 EntriesJun 4, 2026·2 MIN READ
Using AI Without Losing Your Humanity
Everyone has the same AI tools now. The thing that sets you apart is no longer how much you generate, it's who can still make someone feel something, and that's...
Jun 4, 2026·2 MIN READ
AI Native, Human First
You can outsource thinking and execution to AI. What you can't outsource is understanding, and that's the difference between the teams keeping up with it and th...
Apr 16, 2026·3 MIN READ
The Accountability Layer I Built for My AI Agents
When AI is wrong, it is wrong with the same confidence it has when it is right. The accountability standard and observability built around the agents so that co...
Apr 15, 2026·1 MIN READ
Exploring Higgsfield: Creative Video Generation Examples
A hands-on look at Higgsfield for AI video generation. Real prompts, real outputs, and why speed of iteration across models is the thing that actually decides w...
Apr 15, 2026·3 MIN READ
The Real Skill Behind Getting Good Work Out of AI
Prompting isn't the gap with AI, judgment is. The pattern recognition you only get from real reps is what lets you catch the subtle, confident errors models mak...
Apr 11, 2026·3 MIN READ
The AGENT Rule Refactor: Cutting 45 Files Halved My Context Load
45 rule files were telling the AI how to behave, and the output was getting worse. Measuring it showed 170KB of context loading per session. Here's what happene...
Apr 1, 2026·2 MIN READ
Why I Let AI Fight With Itself Before I Ship Anything
Two models run against each other before anything ships. One builds the plan, a different one interrogates it. Why the second read is the closest thing to a rea...
Apr 1, 2026·2 MIN READ
How I Keep AI Output Sharp Across Long Sessions
AI output degrades as a session runs, not because the model forgot but because the signal-to-noise ratio collapses. The context-fatigue meter and token-budget s...
Mar 31, 2026·1 MIN READ
Routing Across Models When a Provider Hits Capacity
A single-provider AI setup is a single point of failure. Why model routing belongs in the infrastructure from the start, so a rate limit slows you down instead...
Mar 28, 2026·2 MIN READ
Why Polished AI Output Still Hides Structural Bugs
AI output can look brilliant and still be spaghetti underneath. The fix is documenting your anti-patterns, the traps and bad shortcuts, so the model stops repea...
Mar 22, 2026·2 MIN READ
What a Decade in Adtech Taught Me About the AI Adoption Cycle
Banners, mobile, programmatic. Every cycle felt too fast from the inside, and every time you adjust. AI is the same, with one difference, the gap between what i...