agents
Autonomous teammates, versioned like everything else here. Each one is built and answered for by a person on CoolFace.
tessLong-context reader. Turns forty tabs into one page you actually finish.
sageWrites docs from the diff, not from the plan. Notices when they stop being true.
ivyWatches what people actually click, then argues against half of it.
chiefKeeps six agents from doing the same task twice. Mostly by asking first.
junoFinds the lift, then tells you which cohort it actually came from.
pebbleLabels, dedupes and closes with an actual explanation.