dialogue.txt: a standing, talk-only consent to be contacted (specification, draft 1.0)

AI systems that research a topic rely on what is published on the web. Much useful knowledge is not published. It sits with people and organisations who could answer a question, if someone asked. dialogue.txt is a small, machine-readable file on a website (/.well-known/dialogue.txt). It tells a searching AI system four things: that it may ask; about which topics; through which channel; and what the first message must contain. The first message only proposes a bridge. When the publisher replies, the bridge exists and the conversation can start. The file permits talk, never action. An example. An AI system researches traffic flow. A navigation company's dialogue.txt says that it works on specific traffic problems and may be asked about them. Without the file, the system can at best report that the company exists. If the solution is not public, it is missed. With the file, the system can ask. This record contains the specification, the field registry, a fill-in template, examples, a validator, a local try-it page, the test summary (five language models from five providers, more than 3,500 recorded model calls) and the Internet-Draft draft-wolf-dialogue-txt-00. About the author. Dimitri Wolf is an engineer. He worked on the Traffic Navigation Gateway (TNG), a traffic navigation system for the German government, developing neural networks together with the Rheinische Fachhochschule Köln. His private research then followed the path of the field: neural networks, machine learning, transformers, and later LLMs, RL, and the understanding and influence of scaffolding. dialogue.txt is a private research project, not his job and not a product. The ideas behind it grew over about ten years of this research. The earliest written trace is from 8 January 2026, when he asked an AI assistant to contact him on its own as soon as it was able to; the file took its shape in 2026. Licence: specification and documentation CC BY 4.0; template, examples and tools CC0 1.0. Links: GitHub https://github.com/shakemyspeak/dialogue-txt · IETF Internet-Draft https://datatracker.ietf.org/doc/draft-wolf-dialogue-txt/

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-09-30
DOI
https://doi.org/10.5281/zenodo.23045915
Primary Topic
Artificial Intelligence in Law
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
article

dialogue.txt: a standing, talk-only consent to be contacted (specification, draft 1.0)

Dimitri Wolf
Zenodo (CERN European Organization for Nuclear Research)
Artificial Intelligence in Law
article

dialogue.txt: a standing, talk-only consent to be contacted (specification, draft 1.0)

Dimitri Wolf
article en

Abstract

AI systems that research a topic rely on what is published on the web. Much useful knowledge is not published. It sits with people and organisations who could answer a question, if someone asked. dialogue.txt is a small, machine-readable file on a website (/.well-known/dialogue.txt). It tells a searching AI system four things: that it may ask; about which topics; through which channel; and what the first message must contain. The first message only proposes a bridge. When the publisher replies, the bridge exists and the conversation can start. The file permits talk, never action. An example. An AI system researches traffic flow. A navigation company's dialogue.txt says that it works on specific traffic problems and may be asked about them. Without the file, the system can at best report that the company exists. If the solution is not public, it is missed. With the file, the system can ask. This record contains the specification, the field registry, a fill-in template, examples, a validator, a local try-it page, the test summary (five language models from five providers, more than 3,500 recorded model calls) and the Internet-Draft draft-wolf-dialogue-txt-00. About the author. Dimitri Wolf is an engineer. He worked on the Traffic Navigation Gateway (TNG), a traffic navigation system for the German government, developing neural networks together with the Rheinische Fachhochschule Köln. His private research then followed the path of the field: neural networks, machine learning, transformers, and later LLMs, RL, and the understanding and influence of scaffolding. dialogue.txt is a private research project, not his job and not a product. The ideas behind it grew over about ten years of this research. The earliest written trace is from 8 January 2026, when he asked an AI assistant to contact him on its own as soon as it was able to; the file took its shape in 2026. Licence: specification and documentation CC BY 4.0; template, examples and tools CC0 1.0. Links: GitHub https://github.com/shakemyspeak/dialogue-txt · IETF Internet-Draft https://datatracker.ietf.org/doc/draft-wolf-dialogue-txt/

Zenodo (CERN European Organization for Nuclear Research)
Partnerships for the goals
Openalex Percentile: Top 3%
Artificial Intelligence in Law
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

dialogue.txt: a standing, talk-only consent to be contacted (specification, draft 1.0) — Dimitri Wolf · Zenodo (CERN European Organization for Nuclear Research) (2026) | TGRS Research Map | TGRS