Decisions
Positions I hold, with the reasoning attached. Each one is a stance I'd defend, not a casual note.
- 01 May 19, 2026
Ship the feedback loop
Why a one-click feedback widget plus an automatic audit-log bundle is the bit of infrastructure people skip, and how it's wired up in the wecoza-core plugin.
Read full position - 02 Apr 27, 2026
The compile loop and the validation loop are different loops
The Claude/TradingView MCP is a technically real capability. It closes the compile loop conversationally. It does not touch the validation loop, and the validation loop is what determines whether a retail trader profits.
Read full position - 03 Apr 26, 2026
LinkedIn engagement tooling, Phase 1 to Phase 2
Why I migrated topical-engagement discovery off Brave Search onto Interceptor (driving my own Brave session), and the ToS trade-off and resilience guards I'm running it under.
Read full position - 04 Apr 22, 2026
Why I keep LLMs behind typed adapters
LLM calls behind typed adapters, code-level information barriers, external prompts, provider-agnostic transport. An AI-engineering position.
Read full position - 05 Apr 22, 2026
Why Postgres alongside WordPress, not instead of it
Why Postgres alongside WordPress, invariants in plpgsql triggers, operational data that outlives the CMS. A pattern from WeCoza development.
Read full position - 06 Apr 22, 2026
Why I publish negative results
Why I publish negative results, postmortems as the deliverable when research doesn't pan out. Evaluation discipline across shelved research projects.
Read full position - 07 Apr 22, 2026
Why stdlib over pandas for the scanner core
Why I use stdlib over pandas in the scanner core, dependencies as a drift surface, stability over ergonomics in production Python pipelines.
Read full position
