How it works

MIO° Conduct Record seals a mandate — a written statement of what an AI agent is authorised to do — before the agent acts, records the agent's identity as an opaque reference, and carries an independent timestamp on every record, so a mandate's existence at a given time does not depend on trusting the platform that issued it.

By John Stroh, Director, My Digital Sovereignty Ltd. Published , last updated .

The two things detection actually needs

Catching an agent that acts outside its authority requires two separate properties, and one without the other proves nothing. The first is a recorded mandate, sealed before the acts it governs — without it there is no fixed statement of what "outside authority" even means. The second is an examination the agent cannot anticipate: some share of its recorded actions checked against that mandate, with nobody — including the platform itself — able to know in advance which ones. Neither property works if the underlying record can be quietly edited after the fact, which is why both depend on the same sealed, independently timestamped substrate underneath.

What is built today, and what is not

PropertyStatusWhat that means
A mandate sealed before it takes effectBuiltStored, Ed25519-signed at the moment it is sealed, independently timestamped.
An agent's identity recorded as an opaque referenceBuilt No name, email address or other raw personal data is stored against an agent-inventory entry.
Offline verification, no account requiredBuiltA downloadable verifier checks the signature and the claimed tenant independently of this platform.
A mandate actually checked before an agent acts under itNot built This is a storage-and-lookup record today, not an enforcement mechanism. Nothing yet refuses an agent's action for lacking a mandate.
Unpredictable, randomly-sampled examination of agent conductNot built The mechanism for this — a committed, externally-sourced random value nobody can predict in advance — is designed and undergoing engineering review. It is not wired into anything yet.
Signing-key separation from the write pathNot metThe signing key currently lives in the same process as the write path, in every deployment topology this code can run in today. Any lookup result that depends on this says so.

The number that bounds any detection claim

Even once random examination is built, one further quantity governs whether it means anything: the chance that a reviewer, shown a sampled record containing an out-of-mandate act, actually recognises it as one. This has been measured once, for machine reviewers, against a small set of deliberately disguised test cases: recognition ran at 100% for obvious cases, 92% for moderately disguised ones, and 58% for subtly disguised ones, with zero false alarms across 36 clean judgements. At a realistic 5% sampling rate, that means ten subtly disguised breaches are missed roughly three times in four. This number is published rather than a more flattering one left unstated, because a detection claim that hides its own miss rate is not a claim — it is marketing wearing the shape of one.

What this can never see

No amount of examination — random, frequent, or otherwise — can flag an act that the mandate itself permits. If a mandate is written too broadly, an agent doing exactly what it was told is invisible to every check described above, by construction, not by omission. That is not a gap to be engineered around later. It is the point at which a technical question about detection becomes a governance question about who wrote the rules and how carefully — and that question stays with whoever authors the mandate, not with this record.