Kjell Tore Guttormsen ffd3ad4dd7 docs: plain-text brief — goal + two approaches (MAF vs Claude Agent SDK) + learning goal ... Framework-neutral narrative of what portfolio-optimiser aims to achieve and the two hypothesised approaches to the same method. Claude Agent SDK paragraphs corrected by the user: the SDK spans both emergent (one agent + subagents) and explicit orchestration (hand-written or agent-authored workflow script with a non-LLM validator gate). The real difference vs MAF is ready-made named constructs vs building blocks — not emergent vs explicit. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Fif1r1En5W542HbZV88yMH		2026-06-24 09:21:31 +02:00
..
plan	docs: add cost-discipline + 90% principle as locked decisions (D5, D6)	2026-06-23 22:11:48 +02:00
research	docs(research): MAF vs Claude Agent SDK comparison + D7 sibling-impl decision	2026-06-24 06:51:24 +02:00
2026-06-24-two-approaches-brief.md	docs: plain-text brief — goal + two approaches (MAF vs Claude Agent SDK) + learning goal	2026-06-24 09:21:31 +02:00