Sebastian Schiller-Stoff

Selected writing AI agents

EN — current language DE — Deutsch

Selected writing · AI agent engineering

Agents are roles, not robots.

The 2025 agent-engineering workshop did not start with a framework. It started with a question: which human role does this agent stand in for? That question still decides whether an agent is useful.

Source record · 10 March 2025 · CC BY 4.0

Why it exists

“Agent” arrived in the Digital Humanities as a vendor word.

In early 2025 the word was doing two jobs at once: a product category and a design pattern. The workshop — a section of the advanced prompt and agent-engineering workshop at DHd 2025 in Bielefeld — tried to separate them. Its showcase was not a chatbot. It was a group of cooperating agents producing teaching material for DERLA, the digital memorial landscape.

The audience was mixed: people who wrote Python and people who commissioned it. So the workshop taught one language for both — Python, a commercial model provider, and an object-oriented model of the work.

The aim was deliberately modest: a basic understanding of agent engineering, enough to build a semi-automated system and enough to judge one.

The argument

Three words, three disciplines: AI, agent, engineering.

The AI part is the smallest. Prompting, context and evaluation are the everyday skills; training and inference are the machine room. The workshop spent its time on the difference between using a model as a knowledge base and using it as an interface to a system.

The agent part is software design. The workshop’s definition is narrow on purpose: an agent is a code abstraction around an LLM, built around a human role in a domain — data stewardship, cataloguing, research assistance — and it should mirror how that domain divides its labour. A framework is optional. Full autonomy is optional. A role is not.

The engineering part is research software engineering: versioning, tests, cost, evaluation. The demonstration was a small crew — a planning agent, a scanner, price analysts, an ensemble that compares them, and a messaging agent. Each one is legible on its own.

In the workshop’s definition

  • a named role
  • a domain division of labour
  • explicit tools
  • a written task
  • an evaluation step

Not required

  • an agent framework
  • full autonomy
  • one vendor
  • a chat window

That is the whole argument. The model is a component. The role is the design.

What holds in 2026

The tools moved faster than the definition.

Two years on, the frameworks have consolidated and the interfaces have moved from chat to the change set. What did not move is the useful unit of design. An agent that cannot name the role it stands in for is a demonstration.

The 2026 GAMS paper asks the same question one level up: where the sweet spot lies between reusing model building blocks and building your own, and how to integrate either without technical debt. The workshop’s answer was to keep the boundary small.

What I would change: teach cost and evaluation first, not last. In 2025 the pricing slide came after the architecture; in 2026 the bill is part of the architecture.

And I would say the quiet part louder: a role is also an accountability. Someone signs the output. The workshop said this in its engineering section; it belongs at the front.

The record

The deposit is a lesson, not a paper: slides and four notebooks, open for reuse.

Title
Introduction to AI-Agent-Engineering
Type
Lesson
Deposited
DOI
10.5281/zenodo.14999965
Co-authors
Martina Scholger, Christopher Pollin
Licence
CC BY 4.0
Reach
3,154 downloads, 2,760 of them unique (Zenodo, 15 November 2026)
Contents
slides (PDF) and four Jupyter notebooks

Colophon

Method
A reading, 15 November 2026. It describes what the workshop argued and what I would teach differently now; it is not a reprint.
Sources
The 2025 workshop deposit, its four notebooks, and the 2026 GAMS paper and talk, which extend the same question to system level.
Authorship
Sebastian David Schiller-Stoff. The workshop was co-authored with Scholger and Pollin. The reading is mine.
JavaScript
None. The page is text, CSS and a small inline sprite.
Licence
Text and layout: CC BY-NC 4.0. The cited record keeps its own CC BY 4.0.

All writing Back to the CV