Running an agent fleet
How one engineer steers a 1M line product with a fleet of coding agents: a Chief of Staff, Team Leads and leaves, hill climbing KPIs, and knowing when to parachute in.
Badges come from GitHub once the author claims this feed.
How one engineer steers a 1M line product with a fleet of coding agents: a Chief of Staff, Team Leads and leaves, hill climbing KPIs, and knowing when to parachute in.
Cost per successful task ranks GPT-6 Luna low first on my 24-task repo board, even though it loses to every other configuration head to head.
Across 24 tasks mined from my own Git history, model rankings correlate with Cognition's FrontierCode at 0.96 Spearman over 10 shared configurations.