JupyterLab + AI assistant as Data Steward Workbench

Annotation: The overall aim is to introduce data stewards to JupyterLab as a potential workbench for practical, reproducible workflows supporting a range of tasks (e.g. data intake and exploration, documentation, and DMP drafting), with an integrated AI assistant.

The session will cover JupyterLab essentials for data stewardship work, including workspace organisation, notebooks versus files, kernels, and exporting or sharing outputs. It will also introduce the AI assistant within JupyterLab, focusing on how it can support the drafting and structuring of stewardship artefacts, as well as code generation and explanation. In addition, a hands-on example workflow will be included, based on participants’ needs; this may cover dataset intake and exploration, visualisation, documentation, and creating “starter text” for a data management plan.

Depending on the audience and environment, we may also explore Python and R side by side by running equivalent workflows in separate notebooks within JupyterLab, with R support provided via IRkernel. Note: AI assistant capabilities in JupyterLab are not yet fully supported when using R.