Optimization
Let’s talk ↗
DOCUMENTATION

Build with
Helix Optimization.

From your first problem model to an integration you can operate. Choose a starting point, including agent-assisted manifest authoring.

Start here ↗

Start here

7 MIN READ ↗

Configure the solver with an agent

Use Claude, ChatGPT or your own agent to draft manifest-driven configuration, then validate and review it before execution.

4 MIN READ ↗

Start with a real problem

Go from an operational planning problem to a first integration with Helix Optimization.

Integration

6 MIN READ ↗

Call the solver service

Discover enabled problem types and submit structured requests to a provisioned solver endpoint.

5 MIN READ ↗

Embed the Python solver

Run a supported local solver entry point inside a Python process you control.

4 MIN READ ↗

Choose a deployment model

Choose direct hosted workspace use, a hosted API, a private service or local Python execution.

Concepts

5 MIN READ ↗

Model inputs and constraints

Separate facts, decisions, hard requirements and preferences in a reusable problem model.

4 MIN READ ↗

Interpret results and feasibility

Understand the difference between execution success, a feasible plan and evidence of optimality.

4 MIN READ ↗

Extend a problem family

Use versioned manifests and supported extension packs to model new operational requirements.

Reference

4 MIN READ ↗

Handle errors and refusals

Distinguish invalid requests, unavailable capabilities and problems with no acceptable result.

5 MIN READ ↗

Service API reference

The core discovery and solve routes, request fields and integration boundaries.

Examples describe the supported interfaces found in the solver source. Match them to the contract and enabled capabilities of your provisioned release.