AI Assistant
AI AssistantChoose your modelling platform
Select one or both modelling frameworks the AI Assistant should use for this session.
At least one panel must remain visible.
Ask the AI Assistant
How this assistant finds answers
This assistant uses retrieval-augmented generation (RAG): before answering, it searches the SURF documentation and knowledge base, then bases its reply on what it finds. Each question goes through these steps:
- Understands your question Follow-ups like “and for SHYFEM?” are rewritten into a complete, standalone search using the conversation so far.
- Searches two ways at once It combines keyword matching (exact terms like namelists or version numbers) with meaning-based search, so relevant passages are found even when your wording differs.
- Ranks the best matches The top candidates are re-scored for how well they actually answer your question, and only the strongest are kept.
- Answers from the sources Those passages are given to a Large Language Model, which writes the reply grounded in them — not on general knowledge alone.
When sources are used they appear as numbered citations (e.g. [1]) — click any one to open that source beside the chat.
Build a SURF experiment
About “Send”
Send turns a plain-language scientific objective into a complete, validated SURF configuration draft.
Describe what you want to investigate — the area, period, physical process, and intended use. The assistant recommends a model, infers a domain, selects forcing products, explains its choices, and prepares a draft you can review, refine, validate, analyze, and report on. Technical parameters are optional: every value you don't state is labelled with its origin and stays adjustable.
Could not generate the draft
Affected fields
Technical details (for debugging)
Generated draft
Generated SURF JSON