Keep only workshop option remove project dir, events dir will be used

Modellierung Fitnessclub is a monthly meeting where researchers talk about how they

build modelling workflows with coding harnesses (such as Claude code, OpenAI Codex,

cursor, Open code or Pi harness). This is a hands on meeting to share experience that is

transferable to other scientific domains. We are all learning how agentic coding is

going to disrupt computer programming and our modelling work as a result.

cursor, Open code or Pi harness). This is a hands on workshop to practice data science

skills that are transferable between scientific domains. We are all learning how agentic

programming is disrupting software engineering and our modelling work as a result.

- We can discuss about data representations (such as multidimensional arrays, vectors

  and tensors), input/output, file storage formats, databases, git version control and

  issue management, integration tests, CI, security aspects, visualisations plotting,

  workflow engines to run models in a dependency graph and about semantics how we name

  variables and functions .

- The 90 minutes meeting is a Hands on workshop on a modelling dataset and associated

  data analysis tools. For example playing with data visualisation based on an existing

  dataset with parallel agents generating plots. In 4 phases:

    1. 5 minutes. Round of introduction 1 minute per project (with timer). Group

       decision on the most mature or desirable project among the submitted ones.

    2. 15 minutes specification we discuss on a drawing board or sheet of paper what do

       we want to achieve in the session.

    3. 1 hour of Implementation with at least one, preferably two or more laptops which

       load the dataset, tools, and generate software with a coding agent. We push the

       code to this git repository under a new sub directory corresponding to the day of

       the event either directly or through a merge request.

    4. 10 minutes wrap-up what worked, what didn't work.

- Throughout the specification and implementation phase, we can discuss about data

  representations (such as multidimensional arrays, vectors and tensors), input/output,

  file storage formats, databases, git version control and issue management, integration

  tests, CI, security aspects, visualisations plotting, workflow engines to run models

  in a dependency graph and about semantics how we name variables and functions .

- Topics could also be extended to literature research with LLMs that ground their

  answers in existing literature such as Perplexity and to prompting techniques to avoid

  sycophancy (such as grill-me, expert panel, storm review, hostile review).

- The 45 minutes meeting could rotate between different forms: 20 minutes frontal

  presentation followed by a discussions, hands on workshop on a modelling tool (such as

  playing with data visualisation based on an existing dataset with parallel agents

  generating plots), completely informal lunch discussion, review of the methods section

  of a modelling paper.

    - The preferred meeting format is a hands on training camp on a modelling dataset.

# Next Meetings:

Every third Thursday of the month

- 2026 Thursday Sept 17 from 12:15 to 13:30

- 2026 Thursday Oct 15 from 12:15 to 13:30

- 2026 Thursday Nov 19 from 12:15 to 13:30

- 2026 Thursday Dec 17 from 12:15 to 13:30

- 2026 Thursday Sept 17 from 12:15 to 13:45

- 2026 Thursday Oct 15 from 12:15 to 13:45

- 2026 Thursday Nov 19 from 12:15 to 13:45

- 2026 Thursday Dec 17 from 12:15 to 13:45

# Participate in the hands on training camp

To participate

- Submit your sample dataset  in a new issue (also called a work item) at:

- Submit your sample dataset in a new issue also called a work item at:

  https://aidaho-edu.uni-hohenheim.de/gitlab/modellierung/modellierung_fitnessclub/-/work_items

    - Make sure your data file is smaller than 10Mb. If the sample data is larger than