FREE · prove

Coverage and Limitations Statement

Publish what the platform can observe, what it cannot observe, and where its answers must stop.

01 · THE SITUATION

“Security and the receiving team ask exactly what Onboard UX can see and what its answers can safely claim.”

An assistant can appear authoritative even when parts of the delivered system sit outside its evidence boundary.

REPOSITORY → ACTION → ARTIFACT → OUTCOME

02 · WHAT IT READS

acme-support-agent/fictional fixture

repo/adopt/boundary-answers.jsonApproved artifact access, deployment signals, and safe interaction.
outputs/connection.jsonThe repository shape used when applying observation limits.
repo/config/routing.tomlThe approved system and environment scope for collection.

03 · WHAT THE FDE DOES

cliVerified public-main primitive

                      adopt boundary --answers adopt/boundary-answers.json --archetype ai --write-statement ./onboard-output/coverage-boundary.md

Available boundary primitive; the guided Workbench review is planned.

workbenchIllustrative planned interaction

Planned local interface — illustrative.

04 · WHAT GETS PRODUCED

outputs/coverage-boundary.mdIllustrative fixture

Coverage and limitations statement

A client-readable declaration of observed sources, unavailable signals, safe claims, and known blind spots.

05 · WORK AVOIDED

You can state the evidence boundary clearly instead of letting confidence imply coverage.

06 · CREDIBILITY BOUNDARY

The statement reflects declared access and current observations; it is not a certification, compliance attestation, or proof about unseen systems.

07 · NEXT STEP

Use the fictional repository demo to inspect the whole free-layer sequence before touching a real project.