Agents in Sales

AWS: pre-launch evals caught its sales agent reporting $410.08 as $410.08 million

AWS's sales operations team says testing its Customer Insights Agent found it inflating revenue figures and inventing an ARR estimate while monitoring stayed green. It now runs a nine-stage eval loop on Bedrock AgentCore.

Why it matters: AWS says one release mismatch alone dropped a test pass rate from 78 percent to 38 percent: uptime dashboards can't tell you if answers are right.