update intro

Author: haesleinhuepf

docs/_config.yml

@@ -15,7 +15,7 @@ latex:
 
 # Information about where the book exists on the web
 repository:
-  url: https://github.com/ScaDS/llm-data-analysis-2026
+  url: https://github.com/ScaDS/git-ai-2026
   path_to_book: . # Optional path to your book, relative to the repository root
   branch: main  # Which branch of the repository should be used when creating links (optional)
 

docs/intro.md

@@ -1,69 +1,22 @@
-# Large Language Models for Data Analysis
+# Git+AI Training
 
-This page contains training materials for using Large Language Models for generating data analysis code.
+This page contains training materials for using Git in combination with modern AI-Agents such as 
+* [Github Copilot](https://github.com/features/copilot)
+* [Openhands / All-Hands](https://app.all-hands.dev/)
+* [Git-Bob](https://github.com/haesleinhuepf/git-bob) (developed in Leipzig, available on the Scientific Computing Gitlab sovereign IT infrastructure)
 
-## Target audience
-
-The notebooks are written for scientists with basic experience in Python programming. As we have only limited time during the hands-on tutorial, it is recommended that everyone picks some exercises according to their skill-level and needs.
-
-## How to use these materials
-
-On the top of the window, you find a Github-Button, which you can use to navigate the repository of the training materials. 
-
-![](00_setup/download1.png)
-
-Download the entire repository as ZIP and unzip the files in a place where you can find them. E.g. on your Desktop.
-
-![](00_setup/download2.png)
+The main rationale of using the AI-agents in the browser is to document reproducibly which parts of a work has been done by humans and which part was done by an AI-agent. Another advantage of this approach is that we  do not need to download anything, we typically can try out things in the browser first.
 
-After the ZIP has been unpacked, navigate to the `docs` folder of the repository using the terminal. E.g. if you downloaded and unpacked the ZIP file on your Desktop, you can do this like this:
+## Read more
 
-```
-cd Desktop
-```
-or (if you use OneDrive to sync your Desktop)
-```
-cd OneDrive/Desktop
-```
+Recommended literature:
+* [Jimenez et al "SWE-bench: Can Language Models Resolve Real-World GitHub Issues?", ICLR 2024](https://arxiv.org/abs/2310.06770)
+* [Wang et al. "OpenHands: An Open Platform for AI Software Developers as Generalist Agents", ICLR 2025](https://arxiv.org/abs/2407.16741)
+* [Haase "Towards transparency and knowledge exchange in AI-assisted data analysis code generation", Nat. Comput. Sci 2025](https://doi.org/10.1038/s43588-025-00781-1)
 
-```
-cd llms-data-analysis-2026-main
-```
-```
-cd docs
-```
-After arriving in this folder, activate your conda environment (if not installed yet, check the [installation instructions](00_setup/readme.md)):
-```
-conda activate llm-da
-```
-```
-jupyter lab
-```
-
-![](00_setup/terminal.png)
-
-After executing this, you can start Jupyter Lab. On the left side you find folders with exercise notebooks and on the right side you find the notebooks to work on.
-
-![](00_setup/jupyterlab.png)
-
-## Covered topics
-
-* Getting started with Jupyter notebooks
-* Image processing and visualization in Jupyter
-* Using artificial intelligence to generate image-analysis Python code
-
-## Covered Python libraries
+## Target audience
 
-* [bia-bob](https://github.com/haesleinhuepf/bia-bob): AI-assisted BioImage Analysis Code Generation
-* [numpy](https://numpy.org/): Basic numeric Processing
-* [napari](https://napari.org): An interactive nD image viewer
-* [napari-assistant](https://github.com/haesleinhuepf/napari-assistant): A pocket-calculator like user interface to build image processing workflows
-* [pandas](https://pandas.pydata.org/): tabular data processing
-* [pyclesperanto](https://github.com/clesperanto/pyclesperanto): GPU-accelerated image processing
-* [scikit-learn](https://scikit-learn.org/): Applied machine learning 
-* [scikit-image](https://scikit-image.org/): Scientific Image Processing
-* [scipy](https://scipy.org/): Scientific data processing
-* [stackview](https://github.com/haesleinhuepf/stackview): An interactive nD image viewer for Jupyter Notebooks
+The exercises are written for scientists with basic experience in programming and with git. Attendees can choose an AI-Agent system and follow exercises step-by-step. Afterwards, goal is to explore the limits of the technology. Only if we know, where it succeeds and fails we can use it responsibly.
 
 ## Acknowledgements 
 

readme.md

@@ -1,6 +1,6 @@
-# LLMs for Data Analysis
+# Git+AI Training
 
-This notebook collection introduces how to use large language models for data analysis code generation. The materials are rendered to this url:
+This notebook collection introduces how to Git in combination with modern AI agents. The materials are rendered to this url:
 
-https://scads.github.io/llm-data-analysis-2026/intro.html
+https://scads.github.io/git-ai-2026/intro.html
 

readme_dev.md

@@ -5,8 +5,8 @@ It is maintained using [Jupyter lab](https://jupyterlab.readthedocs.io/en/stable
 To edit this book, install dependencies like this:
 
 ```
-git clone https://github.com/scads/embo-repro-bia-2025
-cd embo-repro-bia-2025
+git clone https://github.com/scads/git-ai-2026
+cd git-ai-2026
 
 pip install -r requirements.txt
 pip install jupyterlab jupyter-book jupyterlab-spellchecker