Anthropic automated 95% of internal analytics queries using Claude agents but saw accuracy drop to 65% in a month without maintenance

Data agents strike again!! Some more interesting tips on improving the accuracy and alignment of your data agent. One interesting bit I haven’t seen people talk about: “Skill docs describe a data model that changes daily, so without active maintenance they're wrong within weeks. We watched our offline accuracy drift from ~95% at launch to ~65% over a month” …. “Roughly 90% of our data-model PRs now include a skill change in the same diff. We also regularly prune skill scaffolding as models improve and previous failure modes no longer apply.”