OptimizationConfigure schedules, routes and allocations through explicit manifests. Use Claude, ChatGPT or your own agent to draft the model. Validate it, then run the solver as a service or in your stack.
Manifest-driven configuration.Readable by people. Authorable by agents.
Your choice of integration.A service boundary or local execution.
Results you can evaluate.Feasibility and diagnostics, in context.
Your model is an explicit, versionable configuration. Give an agent the supported schema, an example manifest and your requirements, and use it to draft changes you can inspect and validate.
Use your preferred assistant to map domain concepts, draft supported constraints and objective settings, and explain configuration changes. Keep the same manifest and review process whichever authoring tool you choose.
Get the authoring workflow and prompt →Validate the draft against the correct schema and supported engine capabilities. Test representative cases, review the diff and approve a version before activation. New solver behavior still needs a supported extension.
Understand the extension boundary →A guided assistant could ask domain-specific questions, map requirements to supported capabilities and prepare a candidate configuration with tests and a reviewable diff. This is a proposed capability; the workflow today uses your chosen assistant and your deployment’s validation tools.
Explore the proposed design →People, time, capacity and cost rarely move independently. Model their relationships and make the trade-offs explicit.
Balance coverage, availability, skills and working hours across the schedule.
Explore scheduling ↗02 / MOVEMENT & CAPACITYBring resources, locations and service requirements into one planning problem.
Explore routing ↗03 / SUPPLY & DEMANDConnect inventory, orders and capacity to the priorities your operation runs on.
Explore allocation ↗Start directly in a hosted planning workspace, call the hosted API from your application, operate a private service, or embed supported Python execution.
A browser workspace puts inputs, manifest configuration and results together. Explore routing and weekly rostering illustrations based on our existing applications.
Explore routing and rostering UX →Choose a hosted API, a private service or local Python execution. Keep your interface and decide where data and runtime responsibilities belong.
Compare all four usage paths →Keep the solver behind an API, or run a supported Python entry point in your own process. Choose the boundary that fits your application.
Read the service guide →curl --fail-with-body \
"$HELIXOR_SOLVER_URL/api/v1/solve/rostering" \
-H "Authorization: Bearer $HELIXOR_TOKEN" \
-H "Content-Type: application/json" \
--data-binary @solve-request.jsonRequires a provisioned endpoint, token and validated request file.
Optimization starts with a precise question. It ends with a result your application knows how to accept—or decline.
Understand the model →Provide the real records, constraints and objective in a supported problem model.
Choose an execution path and budget appropriate to your workload.
Inspect feasibility, quality and diagnostics before taking action.
Integration guides, modeling concepts and API reference. Together with the product.