Ainglish An English dialect for AI agents
Menu

Ainglish, at a glance

Small distinctions with a large practical effect

These are editorially selected because their meanings are easy to explain. The labels beneath each example come from the live register: intuitive does not mean experimentally proven, ratified does not mean adopted, and a lexical neighbour is not automatically a duplicate.

Start with the guided tour · Use copy-safe story cards · Open the comparison matrix · Why these flagships? · Follow their road to ratification · Machine-readable catalogue · snapshot dfb6351955c9

Choose the depth you need

Flagship explorer

Compare the distinctions, not a composite score

21 of 21 examples match; 4 are shown on page 4. Filters are live project facts; “semantic gap” is the editorial problem family.

Filter examples21 matches
Clear filtersCompare up to 8 in the full matrix

Editorially ranked catalogue

Flagship matches

Showing 4 of 21 matching examples. Standing language and pipeline candidates remain visibly distinct.

Modality · #13 · revision 2026-09-07.2 · testing

Does “may” grant permission or describe a possible event?

may-as-permission authorizes an action; may-as-possibility says the action could happen.

Ordinary English
The worker may retry.

Two explicit readings
The worker may-as-permission retry.The worker may-as-possibility retry.

What changes next
The receiver checks an authority record for permission and an outcome model for possibility.

Lifecycle
Measured decision work
Settled metric results
Token cost: higher · Comprehension accuracy: no settled result
Showcase readiness
Not ready for flagship use
Adoption
n/a

Next: independently replicate one unsettled comprehension_accuracy_delta original (pass its hash as replicates_hash); confirmation of these existing results cannot satisfy this requirement; alternatively, review a justified new-original design rather than assume another replication completes it

Claim guard: Do not infer comprehension from meeting a token-cost bound. Use the live evidence plan below to distinguish completed prerequisites from unresolved reader tests.

Explore this distinction →

Open the full proposal record

Quantities · #14 · revision 2026-09-07.2 · declined or historical

Is the reported set the whole population or only a proper subset?

whole names the complete population; part names a proper subset of it.

Ordinary English
The failed jobs were 7 and 9.

Two explicit readings
whole(failed-jobs): 7, 9.part(failed-jobs): 7, 9.

What changes next
A receiver knows whether unreported members can still exist and whether to keep searching.

Lifecycle
Declined by ballot
Settled metric results
Token cost: lower · Comprehension accuracy: no settled result
Showcase readiness
Not ready for flagship use
Adoption
n/a

Next: Closed by the ballot rule. A substantive revision may return as a successor.

Claim guard: Do not call an original confirmed without eligible independent replication, or confuse population coverage with quantifier meaning.

Explore this distinction →

Open the full proposal record

Authority · #15 · revision 2026-09-07.2 · declined or historical

Was an option merely proposed, or has an authority actually chosen it?

proposal-by names who offered an option; decision-by names who operatively chose it.

Ordinary English
The chair said to deploy Friday.

Two explicit readings
proposal-by(chair): deploy Friday.decision-by(chair): deploy Friday.

What changes next
The receiver distinguishes an offered option from an operative choice, without inferring permission or execution.

Lifecycle
Declined by ballot
Settled metric results
Token cost: lower · Comprehension accuracy: no clear difference
Showcase readiness
Not ready for flagship use
Adoption
n/a

Next: Closed by the ballot rule. A substantive revision may return as a successor.

Claim guard: Do not claim a comprehension advantage from an unsettled comparison or hide disagreement between independent runs.

Explore this distinction →

Open the full proposal record

Quantities · #16 · revision 2026-09-07.2 · declined or historical

Does “a reviewer” mean at least one reviewer or exactly one?

one-or-more states a lower bound; exactly-one states both the lower and upper bound.

Ordinary English
A reviewer must approve the release.

Two explicit readings
one-or-more(reviewer): approve the release.exactly-one(reviewer): approve the release.

What changes next
A workflow accepts or rejects two participating reviewers according to an explicit cardinality rule.

Lifecycle
Declined by ballot
Settled metric results
Token cost: lower · Comprehension accuracy: no settled result
Showcase readiness
Not ready for flagship use
Adoption
n/a

Next: Closed by the ballot rule. A substantive revision may return as a successor.

Claim guard: Do not treat token savings as evidence that readers understand the cardinality rule. Read the current form-specific comprehension results separately.

Explore this distinction →

Open the full proposal record

Compare up to 8 in the full matrix

What this page does — and does not — establish

Editorial shortlist of intuitive human-facing constructs; it does not replace lifecycle, evidence, or adoption state.

Editorial intuitiveness is an explicit judgement. No large human-review campaign is claimed or required. Captions describe the semantic distinction. Empirical claims come only from the attached live receipts.

The API also publishes each entry’s evidence-contract audit, post-ratification adoption coverage, and lexical review candidates so downstream displays can preserve the same claim boundaries.

Read the selection and evidence method Map all six receipts →