We walk through the Nextmv MCP Server's functionality for interacting with Nextmv decision apps via AI agents in a safe, consistent, and reliable way.
A simple one-line command unlocks everything you need for seamless DecisionOps-powered model development from your local machine to remote infra for testing and production runs.
Introducing a free, open source framework for more efficient decision model development: Track model runs, easily find input and output, manage visual assets, and more with the local Nextmv experience.
Say 👋 hello to Nextmv support for NVIDIA’s cuOpt optimization engine and NVIDIA GPU-enabled compute on the Nextmv DecisionOps platform.
Tune your Gurobipy and scikit-learn models with configurable options so your team can prototype faster, experiment with ease, and manage their models with more insight on Nextmv’s DecisionOps platform.
Standardize and manage custom visuals as data assets in Nextmv alongside your model. Accelerate your workflows with interactive charts, plots, and maps that automatically render alongside run details for streamlined analysis and collaboration.
Push your Python decision model from a local file to a remote application in minutes – whether you’re using a notebook or running in another Python environment. Conduct tests with fully featured experimentation tooling, collaborate and share results with teammates, and get observability into model performance.
Working in Python? Stay in Python! Develop and deploy your decision model directly from your Python environment. Updates to our SDK make it even easier to operationalize custom decision models safely and quickly.
If you’re building decision models in Python, our Python SDK and decision science platform make the development process faster (and easier) so you can get your model safely into production.
Do you use Java and OR-Tools to model optimization problems? The Nextmv OR-Tools integration now supports Java – making it easier to operationalize Java-based models using our DecisionOps platform.
How do the routes look? Are they clustered? Are there any stops outside the region? Answer these questions and more with an open source route plotting tool that allows for easy, customized styling.
.png)
See the real-world impacts of a candidate model with a switchback test that randomly assigns units of production runs to each model. Start a switchback test, analyze the results, and promote a new model to production all in the Nextmv console.
Nextmv v1.7.0 updates the Python SDK with manifest-based configuration for load and write functions. It also replaces statistics with flexible metrics and integrates UV for automated dependency management.
Marius shares the origin story of Nextplot, explains how it's built, and demonstrates how to use it for plotting points and routes.
With the Nextmv Shift Scheduling app, you can start automating shift scheduling decisions in minutes.
Register to watch a presentation, demo, and AMA time with the Nextmv team. Get an overview of the newly released custom decision optimization platform, see it in action, and check out a preview of our multi-solver capabilities.
