SURF AI-Assistant
Ask questions, explore sources, and build ocean downscaling experiments.
Ask the SURF 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.
Ask the SURF Assistant about platform features, workflows, data, and configuration.
Build a SURF experiment
About the Build configuration workflow
Build configuration helps you create a SURF JSON draft from a plain-language experiment description.
Describe the model, region, dates, resolution, forcing products, bathymetry, tides, and output needs. The assistant extracts the main settings, selects the appropriate schema, and prepares a draft you can review, validate, refine, and export.
Describe your experiment to build a SURF JSON configuration draft.
Could not generate the draft
Affected fields
Technical details (for debugging)
Generated draft
This is a draft generated from your description. Review and validate it before use — nothing has been saved or run.
Generated SURF JSON