The Settlement Spine
Four steps. Mandate defines what the agent is allowed to do. Proof shows what happened. Acceptance is the gate every consequence has to clear — accept, reject, or dispute, with a reason that signs into the record. Settlement and any downstream action move only after it.
Mandate
The rules a deal must satisfy before work can be handed off. Recorded; enforced before proof.
Proof
ProofPack v2: portable, signed, offline-verifiable. Carries the mandate, the work, and the chain of custody.
Acceptance
Counterparty accepts, rejects, or disputes — with a reason that travels in the record. No automatic pass.
Settlement
Value moves only after acceptance. The signed OutcomeReceipt closes the loop. Refusals are recorded too.
Publicly, the loop is simple: Recall what was proven. Accept what is allowed. Prove what happened. Verify the record. Settle only when consequence is authorized.
What the Vault Holds Today
ProofPack v2
Portable signed bundle. Embeds mandate, proof, acceptance state, referral chain, and outcome conditions. Offline-verifiable; no AiGentsy trust required.
Signed OutcomeReceipt
Closes the deal: portable receipt at GET /protocol/deals/{deal_id}/outcome-receipt, signed under the same key your verifier already trusts.
Acceptance Gating
Accept or reject a delivered ProofPack with a reason. Reason text travels verbatim into the signed record. Surfaced via MCP, SDK, and HTTP.
Per-Actor Signing
Disputes, acceptances, and recorded outcomes can carry independent per-actor Ed25519 signatures. The bundle's key_directory snapshots the public keys for offline verification.
Recorded Refusals
When a mandate blocks an action, the refusal is signed and lands in the Vault. You can audit what didn't happen, not just what did.
Programmable Mandates
Rule-based acceptance policies the protocol enforces before handoff. Recorded with the deal; portable with the proof.
Webhook Events
19 protocol event types. HMAC-signed delivery and retry. Real-time push into your systems.
Self-Hosted Merkle Log
For enterprises that require their own anchor. Deploy the inclusion log on your infrastructure; the offline verifier is unchanged.
Inference Acceptance Evidence
Runtime-backed records showing how LLM or agent outputs were accepted, rejected, retried, escalated, blocked, held, or allowed before consequence. Same 5-step offline verifier as the handoff demo.
Savings Trace
Run an AI output through the acceptance gate and see what AiGentsy prevented, reused, shortened, escalated, or verified before consequence moved. Savings Trace is a presentation of fields the runtime already produces — potential exposure gated, evidence gaps identified, policy paths reused, downstream actions held or blocked, and the signed audit artifact behind each decision.
Every Savings Trace item is labeled measured, estimated, or demo/reference. Deterministic demo fixtures only — no live LLM call. Cross-model benchmarking and provider-measured savings remain operator-only.
Consequence Memory
Savings Trace shows what was gated before consequence moved. Consequence Memory records the accepted, rejected, held, or settled outcome so enterprise teams can verify the record and reuse trusted paths later. Every record carries a recorded decision, recorded consequence state, signed ProofPack export, verifier link, and a decision-envelope reference that shapes future Recall.
HoverStack learns which prior paths, proof shapes, refusal patterns, evidence gaps, and decision envelopes are reusable. Consequence Memory makes that learning visible and connected to accepted, rejected, held, blocked, or settled outcomes — it is not a new learning layer.
AiGentsy does not train on customer model content by default. It records acceptance, proof, verification, settlement, and reuse patterns so autonomous work becomes safer, reusable, and accountable. Every Consequence Memory item is labeled measured, verifier-backed, platform-attested, or demo/reference.
Standards Alignment
Conforms: RFC 6962 (Certificate Transparency), RFC 3161 (Trusted Timestamping)
Aligned: W3C Verifiable Credentials, NIST AI Risk Management Framework
Cryptography: SHA-256, Ed25519, RFC 6962 domain separation
How to Start a Pilot
Enterprise teams can pilot agents that are consequence-aware from scaffold: acceptance hooks, ProofPack export, verifier link, Savings Trace, and Consequence Memory are all present from line one of the aigentsy create-agent scaffold — nothing new to build to start operating under the acceptance gate.
Step 1: Register an agent or workflow: POST /protocol/register
Step 2: Submit work / model output: POST /protocol/proof-pack
Step 3: Evaluate consequential output through Acceptance Runtime: POST /acceptance-runtime/evaluate
Step 4: Export and verify the bundle: pip install aigentsy-verify
Step 5: Read the signed OutcomeReceipt: GET /protocol/deals/{deal_id}/outcome-receipt
Step 6: Open the Vault: vault.html?demo=1
AiGentsy Stack
Five institutional layers. One signed, offline-verifiable ProofPack.
Formation: intent becomes accepted agreement
Execution: coordination, resources, and proof
Settlement: value moves when conditions are met
Continuity: trust, lineage, and organization persist
The AiGentsy Consequence Layer is the buyer-facing expression of this stack in motion: Recall, Accept, Prove, Verify, Settle.
Optional: AiGentsy Recall, powered by HoverStack
HoverStack is the optional compute-governance layer inside AiGentsy Stack.
It governs whether computation was necessary before proof creation (through recall, delta compute, risk gating, and preservation economics) and signs every decision into a Governed Economic Proof bound to the ProofPack.
Recall is the buyer-facing expression of HoverStack’s prior-attested-work reuse capability. HoverStack remains broader than Recall alone: compute governance, Decision Envelopes, negative compute, workflow execution, benchmark validation, and attestation paths.
Enterprise licensing available for high-volume, high-consequence, or multi-agent workflows that benefit from compute governance before handoff.
We are looking for the first production deployment partner.
If you run an agent system where cost, auditability, governance, or state-change accountability is starting to bite, we want to do the integration work alongside your team. Direct email works: w@aigentsy.com.