Public guide / no provider effect
Assurance

What happened, why, and who allowed it.

Guth assurance makes AI-assisted work inspectable before it becomes an action, a memory, or a published claim. It does not promise that a model is always right. It preserves enough evidence and control to test the work, reject it, repair it, and understand its effects.

This page is an explanatory public surface. Its examples are deterministic local demonstrations and create no external effect.

The short version

Four questions stay visible.

Assurance becomes practical when it is attached to the work instead of added as a vague review at the end. Guth follows the input, admitted evidence, authority, and resulting effect as one record. A receipt can therefore explain both what the system did and what it deliberately refused to do.

01 / INPUT

What entered?

The user request, source material, tools, model route, and relevant settings are identified.

02 / EVIDENCE

What supports it?

Claims remain attached to exact sources, qualifiers, contradictions, and missing evidence.

03 / AUTHORITY

Who allowed it?

Model output is not permission. Human and system authority are stated separately.

04 / EFFECT

What changed?

Drafting, storage, sending, publishing, spending, and deletion are distinct effects with distinct gates.

Receipts

The work leaves an inspectable record.

A receipt is not a screenshot of a confident answer. It is a structured account of the request, the evidence admitted, the route taken, any human review, and the effect boundary. Open each tab below. The card stays the same size so comparison does not move the surrounding page.

Run receipt / public sample / ASR-001Held
Claim examiner

Can the answer be supported?

Stable receipt ID / deterministic fixtureLocal UI / no external effect
Evidence

Sources survive the answer.

Ordinary model output often compresses many sources into one fluent paragraph. That makes the answer easy to read but difficult to audit. Guth keeps source identity, admitted spans, dates, revisions, and qualifiers available after synthesis. A reader can return from a claim to the exact material that supported it.

This matters when a source changes, when two sources disagree, or when the model quietly fills a gap. Unsupported language is held as a proposal rather than promoted into memory or authority.

01Source enters
→
02Exact span retained
→
03Claim compared
→
04Receipt links back

The prose may change. The source locator, admitted evidence, and qualification state do not disappear with it.

Authority & effects

Ability is not permission.

An agent may know how to send a message, modify a database, publish a page, or call a paid service. That capability does not grant authority to use it. Guth separates tools from permissions and distinguishes reversible local drafting from consequential external effects.

The effect gate evaluates the requested action at the moment it would occur. Missing authority fails closed: the useful draft can remain available while the send, purchase, publication, deletion, or identity change stays held.

LOCAL

Draft

Prepare text, organize a proposal, or preview a change without leaving the current surface.

RECORDED

Store

Write to an authorized record with provenance, ownership, and recovery information.

EXTERNAL

Send

Transmit information to another person, system, provider, or public destination.

CONSEQUENTIAL

Commit

Spend, delete, deploy, publish, alter identity, or perform another difficult-to-reverse effect.

Qualification

Approval can expire.

Evidence-backed work can still become stale. Guth records the conditions under which a claim, model route, instrument, or workflow was accepted. A changed source, model, dependency, permission, or deployment environment can trigger requalification rather than silently inheriting an old result.

TESTMeasure behavior
→
COMPARECheck requirements
→
REVIEWAdmit or hold
→
REQUALIFYRepeat after change
Rejection harness

Try a bounded decision.

Move the controls and watch the decision update. This is a simplified deterministic example of the same basic rule: evidence quality, authority, and effect severity are evaluated separately. Strong evidence cannot manufacture permission, and permission cannot repair missing support.

CURRENT DECISIONHELD

Authority is missing. The local draft may remain visible, but no canonical or external effect can proceed.

Instruments

Assurance is assembled from inspectable tools.

Guth instruments are small, named mechanisms with explicit inputs, outputs, limitations, and receipts. They can be used alone or combined into stacks. The four examples below cover source retention, claim support, authority, and failure collection; other instruments address memory, privacy, routing, drift, experiments, and requalification.

Source Lock

Preserves exact locators and source identity so a claim can return to the material it relied on.

Claim Examiner

Compares proposed language with admitted evidence, qualifiers, and unresolved gaps.

Authority Gauge

Separates capability from permission and identifies the principal required for an effect.

Failure Harvester

Retains rejected, repaired, and contradictory cases as evidence for future testing instead of hiding them.

Glossary

Terms used on this page.

The system uses precise words because “the AI did it” is not a sufficient technical explanation. These definitions are intentionally short; future glossary pages will connect each term to examples, diagrams, instruments, and implementation references.

Admitted evidence

Source material explicitly accepted as support for a particular claim or decision.

Authority

The permission to perform an effect, distinct from the technical ability to perform it.

Canonical record

The controlled record treated as current after ownership, provenance, and review requirements are met.

Effect

A change caused outside model reasoning, such as writing, sending, publishing, spending, or deleting.

Held

A useful proposal that cannot advance because evidence, authority, review, or another gate is incomplete.

Qualification

Evidence that a model, workflow, instrument, or claim met defined requirements under stated conditions.

Receipt

A structured record linking inputs, evidence, route, review, decision, and effect state.

Requalification

Repeating qualification after a meaningful source, model, dependency, permission, or environment change.

Source-bound

Retaining enough source identity and location information to inspect where a statement came from.