Sebastian Schiller-Stoff

Practice note AI coding

EN — current language DE — Deutsch

Practice note · AI coding assistants

The assistant writes code. You sign it.

Since 2023 I have taught research teams to use coding assistants without handing over judgement: what the tools do, where they fail, and what a reviewed AI change has to pass. This page is the workshop record, the case behind it, and the limits I teach with it.

Practice note · record 2023–2025

What changed

In 2023 the question was whether autocomplete could finish a line; by 2024 whether a chat window could refactor a module; by 2025 the tools could read a repository and run a command.

The interface moved; the risk stayed the same: code that looks right in the editor and is wrong in the system. Teach the tools by their failure modes, not their feature lists.

What the tool is good at

  • Boilerplate
  • Test scaffolding
  • Unfamiliar APIs
  • Explaining legacy code

What it cannot see

  • The research question
  • The data model
  • The licence
  • The consequence of a publish

The curriculum

A workshop series, not a one-off demo. December 2023 to September 2025: autocomplete → chat → refactoring → review. Every step is open on Zenodo.

  1. Conference abstract

    Kann LLM generierter Code FAIR sein? Herausforderungen für das Forschungsdatenmanagement
  2. Presentation

    Der Einfluss von AI-Pair-Programmers auf die Digital Humanities: Potentiale und Limitationen
  3. Workshop

    KI gestützte Programmierung in den Digitalen Geisteswissenschaften
  4. Workshop

    AI coding assistants (advanced)
  5. Workshop

    AI coding assistants
  6. Presentation

    IDE-Integration of GitHub Copilot: Jetbrains IDEs
  7. Conference abstract

    Project Overhaul und Refactoring der digitalen Edition der „Urfehdebücher der Stadt Basel“ mithilfe von GPT-4 und LLM
  8. Workshop

    Legacy code and copilot technologies: AI-supported software maintenance
  9. Workshop

    Copilot technologies in the digital humanities

The series was taught with Münzer, Sagadin, Dittmann, Martin, Pollin, Scholger, Steiner, Lang and Galka.

The case

The Urfehdebücher der Stadt Basel edition needed an overhaul: data model, transformation, visualisation and the web application.

With the UFBAS team we used GPT-4 across those steps — TEI XML, categories and SKOS, an ontology, RDF, frontend work and data visualisation — and documented where it helped and where it did not.

The lesson was not that the model wrote the edition. It compressed the distance between a decision and its implementation, which made review the bottleneck and the most valuable part of the process.

What the model did

  • Draft transformations
  • Propose mappings
  • Generate frontend scaffolding
  • Explain unfamiliar code

What the team decided

  • The data model
  • Ontology commitments
  • The licence
  • What counted as a correct transformation
  • What shipped

The limits

The 2025 FAIR-code abstract names the failure modes: generated code with poor maintainability, missing metadata and licence uncertainty is hard to find and hard to reuse lawfully.

Insecure libraries and inconsistent standards compound it. In research that is a data-quality problem, not a style problem. Vibe coding is a starting point, not a method.

  1. The diff is small enough to read

    Review is a reading task, not a glance.

  2. The tests ran

    The check is a command, not a promise.

  3. The dependency and its licence are known

    Every new library is a legal and maintenance commitment.

  4. The prompt and sources are recorded

    Provenance is part of the artefact.

  5. A person signs the commit

    The signature is the method.

The signature

The assistant can write the code. It cannot sign.

The brief, the test, the licence and the signature stay with the person who ships. That is the whole method, and it is why the record above is a teaching record rather than a tool review.

Colophon

Method
A practice note, 14 November 2026. It describes the method I teach for reviewed AI changes; it is not a specification.
Sources
The nine records are all listed and linked in chapter 02; chapter 04 reads the FAIR-code abstract. All are open on Zenodo, and every claim in this note maps to one of them. The longer readings are Autocomplete was never the point and FAIR is a gate, not a badge.
Record titles
Titles follow the deposits. Normalised: typographic quotation and terminal punctuation. Type labels name the event form; the deposits’ own types are broader.
Authorship
Sebastian David Schiller-Stoff. The workshops and papers in the record were co-authored with Münzer, Sagadin, Dittmann, Martin, Pollin, Scholger, Steiner, Lang and Galka. This is a practice note, not a product claim: it describes a method I use and teach, not a standard or a certification.
JavaScript
None. The page is text, CSS and a small inline sprite.
Licence
Text and layout: CC BY-NC 4.0. The cited records keep their own Zenodo licences.

Back to the CV AI agent engineering