From one prompt to three supply variants, in under ten minutes.
Sympheny's API is fully documented, so an AI assistant can build a project, set up scenario variants and start an optimisation run. What comes back is unchanged: the same engine solves the model, whether a person or an assistant set it up.
An assistant sets the model up. Sympheny solves it.
One prompt, three supply variants — gas boiler, heat pump with rooftop solar, and district heating — set up through the documented API. Silent clip; every step is captioned on screen.
Get the details and the full setup guide in our documentation →Five steps, from a written brief to three scenarios ready to optimise.
A real setup, start to finish: a brief written in plain language, the assumptions the assistant checks back on, and three scenarios ready to optimise.
“Add a new step after step 1 that lists every project…” — and the wizard has one.
AI helps you build the interface. Sympheny optimises deterministically, as always.
A light app is a small, focused interface built on top of Sympheny — a wizard shaped like the study your team actually runs, rather than the whole platform. You build one, and change it, in the Light App Editor.
The clip shows one being changed. A written instruction adds a step to a four-step wizard that is already live, the steps below it renumber, and the new screen is deployed two seconds later. The new step is real, not a mock-up: it lists every project in the account, straight from Sympheny.
A four-step wizard that is already live gains a fifth from one written instruction, deployed two seconds later and loading straight from Sympheny. Silent clip; every step is captioned on screen. It shows an existing app being extended, not one built from empty.
Talk to us about using AI for your own light app →Everything an agent needs is already documented.
Two of the three are live today. The MCP server, which lets an assistant connect with nothing to wire up on your side, arrives in the coming weeks.
REST API
Everything the platform does is reachable through the documented API — projects, scenarios, optimisation runs and results. You can try it in the browser before writing any code.
REST API reference →Python SDK
sympheny-toolbox, the official Python client. Worked guides take you from installing it to a finished optimisation run, with the login handled for you.
Python SDK guide →MCP server
A standard connection, so an assistant reaches Sympheny with nothing to wire up on your side. Setup is already documented; the server ships in the coming weeks. Until then the REST API and the SDK do the same job.
MCP setup, documented ahead of launch →The documentation is written to be read by machines as well as people.
docs.sympheny.com publishes llms.txt and llms-full.txt: the whole documentation in a form an AI assistant can read in one go, following the llms.txt convention.
So you can hand an assistant a single URL and it has the platform in context — endpoints, model structure and worked examples — instead of crawling the site or guessing at the shape of an API.
The parts of the work worth automating.
Working with AI assistants and agents.
Can I use Sympheny with an AI assistant or agent?
Yes. Sympheny publishes a documented REST API and Python SDK, so an assistant can create scenarios, start optimisation runs and read results back. An MCP server arrives in the coming weeks. Nothing is connected by default — you decide whether to use it.
Can I edit a light app with an AI assistant?
Yes. The Light App Editor takes an instruction in plain language and changes the app — the clip above adds a wizard step listing every project in the account, deployed in two seconds. What it shows is a change to an app that already exists; building one from empty is a longer job. Either way the optimisation behind it is unchanged: the same deterministic MILP engine solves the model.
If I connect an assistant, where does my data go?
To whichever provider you connect. The scenario data an assistant sends and receives passes through that provider under your agreement with them, not ours. Sympheny does not choose the provider for you.
Does connecting an assistant change my results?
No. An assistant can build or modify a scenario, but the optimisation always runs on the same deterministic MILP engine. A scenario assembled by an assistant and the same one assembled by hand produce identical results.
Note: An assistant can set the model up. It never solves it.
Do I need to be a developer to use this?
For the API and the SDK, yes — or someone on the team who is. Having the assistant write the script lowers the bar a lot, but somebody still has to run it. The MCP server removes that step when it ships. Everyone else works in the web app, where the same optimisation runs.
Is under ten minutes realistic?
For the setup shown, yes: three variants with demand from the database, with the API available to the assistant and someone who knows what they want to model. A first attempt takes longer, and the optimisation run is on top of it. It is a claim about scenario setup, not about a finished energy concept.
When does the MCP server launch?
In the coming weeks. Client setup is already documented, and the endpoint starts answering when the server ships. Everything the walkthrough above shows works today without it. Tell us on a demo call if you want to know when it lands.
Want to try it on a project of your own?
Start a free trial and drive it through the API, or book a free 30-minute quick start and we will walk through the setup on a project that mirrors yours.