← Back to writing

2026 · 05 · Recap · 14 min read

From Empty Repo to Stable: Two Weeks Building a Multi-Agent Equity Workstation

Design trade-offs in financial-analyst — three trust tiers, the single-writer pattern, human-reviewed memory self-iteration, and why auto-accept is off.

[ Sample post. The repo already has a bilingual docs/journey.md you can fold in here. ]

Worth covering: why three trust tiers and isolating "reading untrusted content"; how the single-writer pattern keeps agents from fighting; and why the dream loop insists on human review.