It’s time to understand the behavioral impacts of a new decision model under real-world conditions compared to a production model. Switchback testing enables this, helping build confidence in a new model’s rollout in a safe and measured way.
I retired our on-call scheduling spreadsheet — and you can too. Here’s how I built a custom decision model that generates and sends optimized schedules to the PagerDuty API.
When you’re ready to have a candidate model make true operational decisions, it’s time for switchback testing. Kick off an experiment and analyze how your new decision model measures up to your current model in production.
With Nextmv, you can customize an optimization model for your use case without wading into linear inequalities. From creating your own value function to adding custom constraints, learn best practices for representing business logic as code.