Skip to content
Read the original: Elvis Saravia· Published 18/100AI score18/100

Viktor, a Slack AI employee, reviews overnight agent eval failures

Original titleReading eval results is now the slowest part of building agents.

AISummary

Elvis Saravia describes using Viktor, an AI employee in Slack, to review his nightly agent harness evaluation results. Viktor traces tasks that regressed from passing to failing back to the specific harness change that caused them and suggests reverting it, while the human makes the final decision. The post is a sponsored partnership, offering $100 in free credits with no card required.

Read the original x.com

Source: Elvis Saravia · x.comPublished · added here