Agent GuardProtocolMCPGovGuardFinGuardDemoPricingDocsRequest Pilot
Comparison / Human-in-the-Loop

EMILIA Protocol vs DIY human-in-the-loop

Adding a Slack or email approval to your agent is the right instinct. EMILIA makes that approval accountable — bound to the exact action, replay-resistant, and provable offline — without you maintaining the trust plumbing.

The pattern you are reaching for

When an agent hits a risky action, post to Slack or email, wait for a click, then proceed. Homegrown wrappers and approval libraries do exactly this, and the instinct is correct: a human should stand between an agent and an irreversible action. It works — until you need to prove who approved what, stop a captured approval from being reused, or hand an auditor evidence that does not require trusting your own logs.

What a click in Slack is missing

A button press approves “an action.” It is usually not cryptographically bound to the exact parameters — the amount, the destination, the beneficiary — so the same approval can authorize a different action than the one the human saw. It can often be replayed. And the evidence it leaves is a row in a database you control, which is precisely what a regulator or an insurer will not take at face value.

EMILIA binds the signoff to the exact action, makes it one-time consumable, and mints a Trust Receipt anyone can verify offline (Ed25519 + Merkle, no account, no call home). The policy engine underneath is formally verified, not glue code you have to trust.

Side by side

DimensionDIY human-in-the-loopEMILIA Protocol
What gets approvedAn action, often coarse — approve once, broad scopeThe exact action — bound to actor, authority, policy, and parameters
Replay resistanceUsually none — an approval can be reusedOne-time consumable handshake
EvidenceA log line in your own system — trust usTrust Receipt — Ed25519 + Merkle, verifiable offline
Approver identityWhoever clicked the buttonA named principal bound into the signoff
AssuranceYour own glue codeFormally verified policy engine — 26 TLA+ theorems + 35 Alloy facts
What you maintainChannels, state, retries, audit storageA drop-in gate (MCP / SDK); receipts included
ComplianceAd hocMaps to NIST AI RMF + EU AI Act human-oversight and traceability

Keep your Slack approval — change what it means

EMILIA is not a different approval UX. Keep approving in Slack or email if your team likes it. The difference is what the approval is: instead of a click and a log line, it becomes a bound, replay-resistant, offline-provable artifact — the thing you can hand to an auditor, an insurer, or a counterparty without asking them to trust your systems.

See it in practice

Add it to your agentTry the live demo
EMILIA Protocol vs DIY Human-in-the-Loop — Make Agent Approvals Provable