I do agree that some scepticism is due here but how can we tell if we're treading into "moving the goal posts" territory?
Everyone who has used AI coding tools interactively or as agents knows they're unpredictably hit or miss. The old, non-agent Copilot has a dashboard that shows org-wide rejection rates for for paying customers. I'm curious to learn what the equivalent rejection-rate for the agent is for the people who make the thing.