forecasting

The headline horizon is a 50% success rate on someone else's tasks. Plan on the 80% horizon for your own tasks, break long jobs into checkpoints and keep long-autonomy features as dated bets.

Two forecasts make errors in opposite directions. Calculate the operational consequences before deciding which evaluation metric should control the release.

Cheaper tokens bring longer prompts, more steps and more tasks, and some prices rise. Forecast spend as price times tokens per task times tasks times users, in bands, with caps per feature.