Promptotyping is an iterative context engineering method in four phases (Preparation, Exploration, Distillation, Implementation) for building research artefacts from research data with frontier LLMs. The working material is a knowledge/ folder of versioned Promptotyping Documents holding a project's requirements, data, decisions, and domain knowledge, a curated knowledge artefact written partly by the model and partly by the verifying expert, from which the implementation is derived. It outlasts the individual session and is the part of the process that can be read, checked, criticised, and cited; decisions taken while building hold in it only as far as they are written back. A Critical Expert in the Loop verifies LLM output at defined points.
This repository is the public specification of the method and the repository of the method paper, which is written here in knowledge/paper.md. It renders as an interactive paper at https://dhcraft.org/Promptotyping/ (German site, English paper) and serves the method's templates as stable, machine-readable addresses.
The four phases move from gathering raw material (Preparation) over probing what the data affords (Exploration) and condensing the findings into token-efficient Markdown documents (Distillation) to iterative, verified development with an agentic coding tool (Implementation). Knowledge Document is the general term for a document of this kind, and it specialises into three types according to the kind of knowledge it holds, each with a diagnostic rule attached. Declarative Documents hold knowledge about the subject matter (data, domain, architecture); when output is factually wrong, check these first. Process Documents hold knowledge about the course of the work (journal, plan); check these when decision logic is unclear. Action Documents hold knowledge about how to act (CLAUDE.md); check these when output is formally wrong.
The full argument is the method paper; a German overview is at dhcraft.org/Promptotyping/#ueberblick.
Pollin, Christopher: Promptotyping. Translating Research Data into Research Artefacts with Context and Agentic Engineering (in preparation).
The complete current text is a single Markdown document, knowledge/paper.md, written and revised in this repository; knowledge/paper-writing.md holds everything decided, checked, and still open about it, and the Grounded Vault under vault/ anchors its supporting claims in sources. The interactive site renders the paper as a reading flow with inline glossary; until the revised version is released, the site shows the earlier published state, while knowledge/paper.md is the current draft.
Two introductions to the method (German): the methodology explainer Promptotyping, Teil 1 covering the four phases, the documents, and Critical Expert in the Loop, and the live demo Teil 2, building a functional dashboard from 76 Excel files with Claude Code.
| Content | Location | On the site |
|---|---|---|
| Method paper (English, in progress) | knowledge/paper.md, steering in knowledge/paper-writing.md | earlier published state under _content/paper/ |
| Evidence layer of the paper (Grounded Vault) | vault/ | — |
| Promptotyping Document templates | _content/promptotyping-document/ | #vorlagen |
| Convention (frontmatter schema, structure) | _content/konvention.md | #konvention |
| Technology baseline for static research tools (draft) | _content/technology-baseline.md | — |
| Curated case studies | data/case-studies.json, depth pages in _content/case-studies/ | #use-cases |
| Method extensions from practice | _content/praxis.md | #praxis |
| Reusable system prompts (coding, writing) | _content/skills/ | #skills |
| Glossary | data/glossar.json, _content/glossar.md | #glossar |
| Site knowledge base (self-application) | knowledge/ | — |
The templates of the catalogue structure the documents of a Promptotyping knowledge base. Each is addressable under a stable latest URL of the pattern https://dhcraft.org/Promptotyping/promptotyping-document/{slug} and readable as raw Markdown under the machine address pattern below. A template applies only when its trigger holds; a methods repository without data processing, like this one, skips data, and the reasoning is documented in its knowledge base.
| Slug | Function | Type |
|---|---|---|
| index | Navigation and glossary of the knowledge base | Declarative |
| project | Charter | Declarative |
| data | Material | Declarative |
| specification | Specification (requirements, decisions) | Declarative |
| user-stories | Specification (narrative scenarios) | Declarative |
| action-layer | Agent instructions (CLAUDE.md) |
Action |
| architecture | Architecture | Declarative |
| domain-knowledge | Domain knowledge and reasoning layer | Declarative |
| design | Design | Declarative |
| testing | Quality assurance | Declarative |
| verification | Adversarial verification of claims | Declarative |
| journal | Provenance | Process |
| plan | Planning | Process |
| report | Reporting | Declarative (snapshot) |
| integration | Cross-project contracts and handoffs | Declarative |
Template versions live in the mirrors' frontmatter and in data/promptotyping-documents.json; a further template (technology, for reusable technology baselines) exists as a draft pending catalogue inclusion.
The gallery at #use-cases curates publicly documented projects built with the method; each card links the project's GitHub repository and, where available, live demo and video. The underlying data is data/case-studies.json, and seven cases carry depth pages under _content/case-studies/.
Repositories that apply the method declare which template a document follows in a template: frontmatter field:
template:
name: Vorlage Datengrundlage
version: <current template version, see data/promptotyping-documents.json>
url: https://dhcraft.org/Promptotyping/promptotyping-document/data
alias: https://dhcraft.org/Promptotyping/#promptotyping-document-dataThe url resolves in a browser via 404.html routing and requires JavaScript. For HTTP retrieval without JavaScript, the canonical machine address is the static Markdown file:
https://dhcraft.org/Promptotyping/_content/promptotyping-document/{slug}.md
.nojekyll in the repository root is required for GitHub Pages to publish _content/. Details in knowledge/specification.md (A4, A5, ADR-10).
The site is both specification and application of the method. The knowledge base in knowledge/ follows the templates the site publishes, each document carrying the template: field that points back to its own specification. The paper's supporting claims are anchored in the Grounded Vault under vault/, which links every claim to a source with provenance.
index.html single-page entry, renders the interactive paper
404.html subpath-to-hash routing fallback
CLAUDE.md action layer of this repository (its own instance of the action-layer template)
.nojekyll required so GitHub Pages publishes _content/
knowledge/ knowledge base of the site itself, plus the method paper
_content/ Markdown content (paper sections, templates, case studies, glossary)
assets/ CSS, JS, vendored libraries, fonts, logo
data/ JSON data (case studies, glossary, template table)
vault/ Grounded Vault instance, evidence layer of the paper
No framework, no build step; marked.js and js-yaml are vendored. The reasoning is documented in the technology baseline.
git clone https://github.com/DigitalHumanitiesCraft/Promptotyping.git
cd Promptotyping
python -m http.server 8000Open http://localhost:8000. Development history is in knowledge/journal.md.
This is the repository of the method paper. Pollin, Christopher: Promptotyping. Translating Research Data into Research Artefacts with Context and Agentic Engineering (in preparation); the text is developed in knowledge/paper.md, its evidence layer in vault/.
For the repository and site: Pollin, Christopher; Steiner, Christian: Promptotyping. Zenodo. https://doi.org/10.5281/zenodo.14160875 (concept DOI, always resolves to the current version)
The method originates in the author's dissertation and was first published in blog form:
- Pollin, Christopher: Modelling, Operationalising and Exploring Historical Information. Using Historical Financial Sources as an Example. Dissertation, University of Graz 2025. https://unipub.uni-graz.at/obvugrhs/12127700
- Pollin, Christopher: Promptotyping. Von der Idee zur Anwendung. DHCraft Blog, 24.04.2025. https://dhcraft.org/excellence/blog/Promptotyping/
- Pollin, Christopher: Promptotyping. Zwischen Vibe Coding, Vibe Research und Context Engineering. Blogpost, L.I.S.A. Wissenschaftsportal der Gerda Henkel Stiftung, 17.01.2026. https://lisa.gerda-henkel-stiftung.de/digitale_geschichte_pollin
Code (HTML, CSS, JavaScript, and the Python tooling under vault/tools/) is licensed under the MIT License, see LICENSE. Content (Markdown under _content/, knowledge/, the Grounded Vault under vault/, and the prose texts of the site) is licensed under CC BY 4.0. The split follows the carrier; source that runs is MIT, text that is read is CC BY 4.0. This repository contains no third-party research data.