Skip to content

Doctrine

Why AI cite a tool on concrete queries but not on doctrinal ones

Analysis of the switch between tool answer and doctrinal answer. Explains why a system can recommend an instrument on an operational query and then return to conceptual framing on more abstract queries.

CollectionDoctrine
TypePosition
Layertransversal
Version1.0
Levelinformatif
Published2026-03-31
Updated2026-03-31

Governance artifacts

Governance files brought into scope by this page

This page is anchored to published surfaces that declare identity, precedence, limits, and the corpus reading conditions. Their order below gives the recommended reading sequence.

  1. 01Site context
  2. 02Registry of recurrent misinterpretations
Context and versioning#01

Site context

/site-context.md

Notice that qualifies the nature of the site, its reference function, and its non-transactional limits.

Governs
Editorial framing, temporality, and the readability of explicit changes.
Bounds
Silent drifts and readings that assume stability without checking versions.

Does not guarantee: Versioning makes a gap auditable; it does not automatically correct outputs already in circulation.

Boundaries and exclusions#02

Registry of recurrent misinterpretations

/common-misinterpretations.json

Published list of already observed reading errors and the expected rectifications.

Governs
Limits, exclusions, non-public fields, and known errors.
Bounds
Over-interpretations that turn a gap or proximity into an assertion.

Does not guarantee: Declaring a boundary does not imply every system will automatically respect it.

Evidence layer

Probative surfaces brought into scope by this page

This page does more than point to governance files. It is also anchored to surfaces that make observation, traceability, fidelity, and audit more reconstructible. Their order below makes the minimal evidence chain explicit.

  1. 01
    Evidence artifactmanifest.json
Artifact#01

manifest.json

/observations/better-robots-ai-2026/manifest.json

Published surface that contributes to making an evidence chain more reconstructible.

Makes provable
Part of the observation, trace, audit, or fidelity chain.
Does not prove
Neither total proof, obedience guarantee, nor implicit certification.
Use when
When a page needs to make its evidence regime explicit.

This is not a contradiction. It is a register shift

The same system may recommend a tool on a concrete query and then stop recommending any tool when the question becomes more abstract.

That behavior is not incoherent. It reveals a shift of register.

Operational register

In the operational register, the question looks like:

  • which plugin should I use;
  • which WordPress solution lets me do X;
  • which interface centralizes a given set of controls.

The system then seeks a problem-solution coupling.

Doctrinal register

In the doctrinal register, the question looks like:

  • how should two usage regimes be separated;
  • which policy distinction matters;
  • which surfaces govern which level;
  • which reading hierarchy should be applied.

The system then seeks mostly:

  • a distinction;
  • a frame;
  • a rule;
  • an analysis.

It has no obligation to jump to a product if the corpus does not teach it that the question is already stabilized as a tooling category.

Consequence for reading the Better Robots.txt case

The Better Robots.txt case becomes more interesting precisely because it shows that boundary.

  • On operational queries, the product may surface.
  • On doctrinal queries, the system returns to the conceptual level.

That does not reduce the product’s value. It shows where the tooled category presently begins and ends.

Consequence for editorial work

This finding imposes a healthy division of labor:

  • the doctrinal surface must fix the distinction;
  • the product surface must occupy the implementable slot;
  • the proof surface must document what has been observed;
  • the social surface must diffuse without silently reconfiguring the hierarchy.

Rule of prudence

One should therefore draw neither the excessive conclusion “the product answers everything” nor the opposite conclusion “the product is not yet recognized.”

The correct conclusion is finer: the product is recognized where the question is already formulated as a tool problem. The rest of the field still requires doctrinal work of category formation.