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.
Source: Elvis Saravia · x.comPublished · added here