Author
Tseka Luk
7 posts
All articles
7 of 7
June 1, 20262 min read
Putting 1,000 Agents Inside One Task: The Engineering Logic of Claude Subagents and Workflows
When AI does deep research, the system behind the answer is often not one chatbot but a temporary team of parallel AI workers. This article explains Claude subagents, workflows, context isolation, parallel tool use, structured outputs, reliability, and token economics.
Tseka Luk
May 23, 20262 min read
An Autopsy of Three Claude Code Skill Frameworks: superpowers, gstack, and ECC
A practical dissection of superpowers, gstack, and Everything Claude Code: what actions they actually change, how much context tax they charge, and which workflow each one fits.
Tseka Luk
May 21, 20262 min read
Think Different: In the Age of AI Homogenization, Independent Thinking Is Differentiated Positioning
When anyone can ship an AI SaaS in 48 hours, real differentiation is no longer a feature. It is judgment, taste, speed, and identity.
Tseka Luk
May 18, 20262 min read
Inside 2026 AI SaaS Blog Design: From Geist to LXGW WenKai
A field report on the visual language and engineering stack behind 2026 AI SaaS blogs, docs, and changelogs, plus the CJK layer needed to make the pattern work in Chinese.
Tseka Luk
May 17, 20262 min read
The Nine-Layer Founder Design Stack: A Unified China-US Venture Vocabulary
Mission, vision, values, positioning, narratives, user stories, OKRs, and brand identity are often mixed together. This essay organizes the shared founder vocabulary across Chinese and Silicon Valley venture practice into one nine-layer operating model.
Tseka Luk
May 16, 20262 min read
Why We Are Building Nebutra
On the strange moment that is 2026: too much technology, too little judgment, and more opportunity than ever.
Tseka Luk
May 16, 20262 min read
Why Nebutra Sailor Exists
Nebutra Sailor is a production-minded SaaS monorepo for teams that need AI-native features, multi-tenant foundations, and deployment discipline from day one.
Tseka Luk