Glossary Updates16 new terms added to the glossaries · November 12, 2026, 21:23 CET
AI TechDocKnowledge
  • English (US)
  • English (UK)
  • Deutsch
All context cards

Role card

Information user: the functional role

Whose questions drive an adaptive semantic architecture — and what may the system do with them?

A role card explains a functional role: what has to be done, not a job title. One person can hold several of them, and one can be spread over several people.

By knowledge.aitechdoc.world

Reviewed

Review log and changes

The short answer

The information user is the functional role of everyone who asks the system for information to do a job: technicians, engineers, content developers and other users, as Michael Iantosca’s white paper names them. Their recurring questions — such as which procedure to perform after replacing a component — are the evidence the evolution cycle learns from. They decide whether an answer helped them do the job; they don’t decide what is technically correct or deviate from required safety information because an agent said so.

For: Technical writers, technical project managers and documentation systems developers

Key points

  • Technicians, engineers, content developers and other users who ask for information to do a job.
  • Their recurring questions and feedback are evidence for gaps, not commands to change the model.
  • What is recorded about their use is agreed beforehand and used for the model, not to profile people.

Functional role

Information user

The role in one sentence

The function of everyone who asks the system for information to do a job — technicians, engineers, content developers and other users — whose questions are the evidence the evolution cycle learns from.

Responsibilities

  • Use the information to perform the task, following the instructions for use and the safety information.
  • Ask in their own words and say when an answer was incomplete or didn’t help.
  • Report recurring needs through the agreed feedback channels.

Decides

  • Whether an answer helped them do the job.

Does not decide

  • Changes to the model.
  • What counts as technically correct information.
  • Deviating from required safety information because an agent said so.

Receives

  • Answers, procedures and the applicable content.

Hands over

  • Questions and feedback.
  • Recurring patterns of questions, as agreed evidence.

Typically held by

Reader roles of the pathway map that usually take on this function.

Technical writers
When they test the system as readers.
Technical marketers
When they bring in customers’ questions.
Technical project managers
When they set up the feedback channels.

On the map

The context

Why the user is a role on the map

The white paper starts from the people AI systems serve: technicians, engineers, content developers and others who need to find information, answer complex questions and perform tasks. In an adaptive architecture they do more than read. When a technician repeatedly asks which procedure follows the replacement of a component and the model can’t express it, that pattern is the first signal of a semantic gap.

What the system may do with their questions

Questions and feedback become evidence only in the form agreed beforehand. They inform the modeling decision; they don’t make it. And whatever an AI agent answers, the instructions for use and the safety information of the product remain what the user follows.

Questions readers ask next

Are information users one of the four reader roles?
Mostly not. They are usually technicians, service engineers and operators; technical writers and marketers take on the role when they test the system as readers or bring in customers’ questions.
Does recording questions mean monitoring people?
It must not. What is recorded, for how long and for which purpose is agreed beforehand; the evidence serves the model, not the assessment of individuals.

Sources

  1. From knowledge graphs to adaptive semantics: evolving DITA and iiRDS digital twins for AI (white paper) — Michael Iantosca, September 25, 2026
  2. EvoOntology vs. iiRDS: understanding two divergent ontology paradigms — AI TechDoc Press (Saina Veigel), September 23, 2026

Review log and changes

Every context card is checked against its sources before it is published, and again whenever it changes; the date under the byline is the last review. Corrections (something was wrong) and additions (something was missing) are logged below with date and time (Berlin time). Typos, formatting and link fixes are not listed.

Reviewed

No corrections or additions since publication.