The model assistant

The model assistant, a new feature from an unspecified developer, lets users describe model changes in plain language and generates a proposal of nodes, states, relationships, and equations for review before applying. The bundled Local demonstration configuration requires no API key, but the flow works identically with real providers such as Ollama, OpenAI, NVIDIA, Hugging Face, or Gemini. Proposals are broken into individual ADD/UPDATE steps, validated, and can be applied as a single transaction, with an Assumptions section clarifying ambiguous interpretations.

Every model so far has been built by hand — right-click, fill in a builder, click Create. The model assistant is a second way in: describe a change in plain language, and it proposes the same nodes, states, relationships, and equations you'd otherwise author yourself, for you to review before anything actually changes. This page uses the bundled Local demonstration configuration, which needs no API key — it's a real, working assistant configuration, just not backed by an external model. Everything shown here the proposal structure, the diffs, the apply/discard flow works identically with a real provider — Ollama running locally, or a hosted OpenAI, NVIDIA, Hugging Face, or Gemini configuration. Open the assistant from the toolbar and describe what should change, in words: "Add an ambient boundary at 298 K and connect it to the battery with a conductance of 15 W/K." The proposal is never applied silently. It's broken into individual ADD/UPDATE steps — here, a new node, a state on it, a relationship connecting it to the battery, a parameter, and the equation that uses it — and validated against the same native validator every hand-built model goes through. Revise proposal re-asks with adjusted wording without losing the conversation so far. The panel collapses to a small status card, so a pending proposal doesn't have to block looking at the rest of the canvas. Apply changes commits every step in the proposal as one transaction — one undo, not five. A request doesn't have to add anything — asking to change an existing value produces a proposal too, shown as a direct before-and-after. Worth noticing here: an Assumptions section "The requested temperature applies to the initial state, not a live simulation value" — the assistant states the interpretation it chose for an inherently ambiguous request, rather than silently picking one. The full conversation stays visible above the current proposal, so a follow-up request reads in context rather than starting fresh each time. Everything on this page still started from a plain-language description you wrote. The last piece works in the opposite direction: recovering a causal graph from data instead of from a description of one.