Skip to main content

Autoresearch Loop

Seven skills span two repos. None of them chain. What breaks when the conductor is missing?

Scorecard

DimensionScoreEvidence
Pain4/57 skills exist across 2 repos but run in isolation. Every step requires human trigger. Every North Star in priorities/index reads "Queryable: No".
Demand4/5All 7 active PRDs need queryable metrics. Karpathy's autoresearch validated the pattern at scale. The factory is blocked on activation, not new builds.
Edge5/5The skill chain already exists — pain-signal-extractor through proof-to-story. Others build from scratch. We wire what's built.
Trend5/5Autoresearch, Devin, overnight agents — the industry moves toward autonomous loops. Manual triggers are the gap.
Conversion3/5Infrastructure play. Revenue path is indirect: the loop produces proven-demand stories for marketing. Meta-capability, not product feature.
Composite1200Prepare

Context

Questions

What compounds faster — building new skills or wiring existing ones into a loop?

  • If every overnight session produced a structured experiment log, what would you learn by morning?
  • Which dormant algorithm in libs/agency/ would benefit most from 100 automated iterations?
  • When the loop runs, who edits the program.md — and what does that make you?