Which MYLO Changes Require Human Approval?

Approval follows effect. Harmless inspection can proceed within permission, while configuration mutation, campaign creation or start, restoration and learned knowledge that can influence future work require an accountable decision. The value comes from the layers working together while each retains a clear responsibility. This makes changes explainable, reviewable and recoverable rather than dependent on an opaque model response.

Consequential change

Approval follows effect. Harmless inspection can proceed within permission, while configuration mutation, campaign creation or start, restoration and learned knowledge that can influence future work require an accountable decision. Operators should confirm this boundary through current evidence and avoid assumptions inherited from old documentation.

Campaign creation and start

MYLO presents relevant evidence in business language while preserving permission and approval controls.

Configuration mutation

The proposed operation names its scope, protected inputs, dependencies and expected result before execution.

Learned knowledge

Deterministic checks make the behaviour repeatable, auditable and safe to stop when evidence disagrees.

Routine inspection

Completion requires verification against the running system, not merely a successful save message.

From Request to Controlled Operation

1. An authorised person states the desired business outcome.
2. AI assistance interprets language, retrieves relevant approved knowledge and asks for missing information.
3. Deterministic code observes current authoritative state and validates values, permission and scope.
4. MYLO presents a structured proposal showing intended differences and protected values.
5. A responsible administrator approves when the effect is consequential.
6. Deterministic services create required backups, apply the bounded operation and reload safely.
7. MYLO verifies configuration and live evidence, records the result and offers a defined recovery path.

Limits and Operating Checklist

• Does each fact come from its authoritative source?
• Is the requested outcome and exact scope clear?
• Are permission, provider and product boundaries explicit?
• Does the proposal show meaningful before-and-after differences?
• Has the responsible person approved consequential effects?
• Is there a scoped snapshot and manifest before mutation?
• Did deterministic validation and execution complete?
• Was the real customer outcome verified?
• Can failure be explained and restored without inventing state?

Judge Approval by Consequence

Reading a permitted status, listing a route or explaining a sanitized log can be non-mutating. Changing telephony configuration, reassigning a DID, creating or starting a campaign, restoring a snapshot, changing a provider setting or approving knowledge that can influence later work has a consequential effect and needs the appropriate human decision.

Different Operations Can Need Different Decisions

Campaign creation approval confirms the fixed lead set and configuration; Start approval authorises production calling after a functional test. Restore approval identifies the exact snapshot and expected rollback effect. A network or trunk change may need both business ownership and technical access. MYLO should use the authority defined for the operation rather than inventing one universal approval list.

Approval is not a liability waiver or substitute for validation. Permissions, product rules and live evidence still apply after a user presses Approve.