Independent verification · No login

Prove what your AI agents did, offline

Intercept tools and gateways log what happened inside their platform. Aevesa produces portable proof (permit or deny) that auditors verify at verify.aevesa.com without logging into your gateway, intercept vendor, or Aevesa admin console.

For agentic finance: block explorers show what landed on chain. Aevesa binds intent, policy, and conduct to the transaction (Base, Solana, Tempo; AP2, x402). Hash-only proofs with optional anchor digests. Not a chain protocol, not custody, no token.

Paste JSON or an entry hash · get VERIFIED or TAMPERED in under 90 seconds

Transaction proof card Open verify bundle Conformance lab Prove Gap Report v1.0 Updated Sep 2026
Share a Base or Solana proof See how it fits your stack

Post-tx proof card · Launch checklist (Solana) · Request enterprise briefing · Dashboard login

verify.aevesa.com · gateway demo
Use the button on the left: VERIFIED or TAMPERED runs here without leaving this page.

Who is verifying?

Security / GRC

Can my auditor verify without our vendor?

Run the portability drill: verify a receipt with no gateway login or API key.

Portability drill demo →

Platform engineering

Where does Aevesa sit in the stack?

Route → intercept → classify → prove → verify. Complement gateways and AI-SPM; do not replace them.

Reference architecture →

Diligence / MGA

Set complete ≠ uniformly enforced

See chain enforcement rollup and weakest-link disclosure on a multi-hop session export.

Mixed-enforcement demo →

Agentic finance / wallets

Who proves the agent before the tx lands?

Wallet ingest, AP2/x402 conduct, and on-chain action packs with optional Base, Solana, or Tempo anchor bundles. Verify offline.

On-chain conduct demo →

The Evidence Gap

Platform logs are vendor-scoped. Proof must be portable.

Intercept tools and AI-SPM platforms govern what agents can touch. Aevesa proves what happened.

Intercept vendors decide allow/block. Aevesa proves the decision happened, verifiable offline without their admin login.

Intercept and classify layers leave a gap in the architecture diagram: no portable proof an external auditor can verify offline. Regulated teams cannot sign off on agent deployments using vendor-scoped JSON alone. Paste a receipt at verify.aevesa.com and recompute integrity in under 90 seconds. No login required. Aevesa cosigns material decisions to an independent witness log, not another platform dashboard. Production tenants run Assurance Autopilot, nightly cryptographic drift checks with an Assured / Drift badge your CISO can review.

82%

Executives confident policies protect agent actions (Gravitee 2026)

~14%

Deploy agents with full security / IT approval

90s

Offline verify at verify.aevesa.com: the Prove Gap in action

Read The Prove Gap Report v1.0 · PMM self-assessment · Research sources

Gateway attestation demo Set-completeness demo Portability drill On-chain conduct pack Agent wallet ingest AP2 + x402 conduct

All demos on verify.aevesa.com Explore no login · independent verification

verify.aevesa.com · SCITT refusal witnessed
Gateway DENIED receipt with SCITT Refusal Witnessed badge - pre-execution block registered in independent transparency log
Pre-execution deny + SCITT Refusal Witnessed - proof your auditor verifies without vendor UI or Aevesa login.

Reference architecture

Complement · not replacement

Finish the stack. Don’t replace it.

Already routing through a gateway, intercepting add-ons, and classifying with AI-SPM? Aevesa is the Prove layer your architecture diagram is missing.

Agent wallets on Base, Solana, and Tempo, x402 and AP2 mandate correlation, AgentKit-shaped ingest get the same Prove layer as enterprise gateways. Wallet policy engines enforce before money moves and keep their own audit trail; Aevesa adds the part none of them publish: a receipt a third party recomputes offline without trusting the wallet, the agent, or Aevesa.

How it fits the standards: Verifiable Intent (Mastercard + Google, FIDO Alliance) proves what the user authorized. ERC-8004 publishes who vouches for the agent. Aevesa proves what the agent actually did, bound to the tx hash and the policy that governed it.

Your gateway routes. Intercept tools vet and block. AI-SPM classifies. Aevesa notarizes and proves what happened. Most platform diagrams stop before Prove. Aevesa cosigns permit/deny and intercept decisions into entryHash + liability-receipt/v1 artifacts anyone verifies offline. Agentic finance layers first, then an example enterprise stack (Unity AI Gateway + AIR Security + Cyera + Aevesa). Also works alongside Portkey, Noma, Zenity, Obsidian, and your existing GRC tools.

Agentic finance stack

Authorize

AP2 mandates · x402

AP2 v0.2 open/closed Checkout and Payment Mandate correlation before wallet execution (legacy v0.1 intent/cart ids accepted). Compatible with AP2 (FIDO Alliance) and x402 Foundation patterns.

Execute

Base · Solana · Tempo · AgentKit-shaped ingest

Wallet events and on-chain action attestations bound to policy digests. Optional chain anchors; Rekor/SCITT witnesses when configured.

Prove

Aevesa notary

on-chain-action-attestation/v1, AP2 conduct receipts, chain-anchor export bundles. Offline verify at verify.aevesa.com.

What we do not prove: chain inclusion unless a chain anchor is attached and disclosed; that the user’s intent was correct; custody or settlement finality. Receipts prove integrity relative to the disclosed capture path.

Example enterprise AI-SPM stack

Route

Unity AI Gateway

MCP routing, service policies, wire-level guardrails inside Databricks.

Intercept

AIR Security · Noma

Vet add-ons, block tool calls, MCP posture. Decisions live in vendor dashboards until Aevesa notarizes them.

Classify

Cyera AI Guardian

Data-centric runtime protection, classification tags, AI-SPM inventory.

Prove

Aevesa

Intercept attest & ledger anchor: portable receipts bound to decision_digest. Witness cosign to independent transparency log. On-chain action attestation binds policy and conduct digests to tx hash; optional chain anchor disclosure (Base, Solana, Tempo).

Layer Owner Output
RouteRoute + guardrail Unity AI Gateway Service policies, MCP routing
InterceptVet + block AIR Security, Noma, Zenity Allow/deny/quarantine decisions (vendor-scoped until notarized)
ClassifyClassify + protect Cyera AI Guardian Runtime block, data classification tags
ProveAttest + anchor Aevesa entryHash + liability-receipt/v1
on-chain-action-attestation/v1 · chain-anchor-export-bundle (when anchored)
VerifyIndependent audit Auditor (no login) verify.aevesa.com · @aevesa/verify

Land with intercept attest only (one webhook after permit/deny). Complements AIR Security, Unity AI Gateway, Cyera AI Guardian, Noma, Portkey, and observability or GRC sinks you already run. Expand to MCP receipt-before-action when agents run outside a managed gateway path.

Run the Evidence Gap Trust Bundle Reference architecture doc

Third-party trademarks. Coinbase, Base, Solana, Coinbase AgentKit, x402 and the x402 Foundation (Linux Foundation), AP2 (Agent Payments Protocol, FIDO Alliance; originated by Google), Verifiable Intent (Mastercard, Google), ERC-8004, Mastercard, Visa, Stripe, Tempo, and related marks are trademarks of their respective owners. Databricks, Unity AI Gateway, Cyera, Cyera AI Guardian, AIR Security, Noma Security, Zenity, Obsidian Security, Portkey, and related marks are trademarks of their respective owners. Diagrams and integration examples describe complementary patterns only; Aevesa is not affiliated with, endorsed by, or sponsored by those vendors or standards bodies unless we state otherwise in a signed agreement. aegis/1 is Aevesa’s ledger preimage spec and is unrelated to Project Aegis or any other product named Aegis.

Differentiation

Intercept Decides. Aevesa Notarizes.

Gateways route traffic; intercept tools vet and block. Aevesa adds the Prove layer, cosigning permit/deny decisions into tamper-proof receipts you verify offline without trusting any vendor UI.

Passive Observability
{
  "lvl": "INFO",
  "_trace": "chunked…",
  "ts": "2026-05-13T18:42:01.883Z",
  "svc": "ai-gateway",
  "rid": "req_9f2c4a",
  "route": "/v1/chat/completions",
  "body": "{\"messages\":[…]}",
  "model": "gpt-4o",
  "latency_ms": 842,
  "policy_ref": null,
  "signed_decision": null,
  "flush": "pending_batch_7"
}
Deterministic Proof Verified 
{
  "schema": "liability-receipt/v1",
  "receipt_id": "sr_01k8q2x7hmz",
  "decision": "DENY",
  "gateway_decision_id": "dbx-demo-deny-001",
  "gateway_event_hash": "f302e2de8ab0ec26bbf0f4d6e9d87d36ca05273867219e114677005c7b7de826",
  "entry_hash": "26988e6613b9dedfb9145e454ad215556862338d674bc0fa7d5a7660867e0666",
  "integrity": {
    "receipt_digest": "0346fb5f41e45d81715ed55eb36c2c00578397dc739c8111890d7a8b62041010",
    "signature_alg": "Ed25519"
  },
  "verify": "https://verify.aevesa.com?demo=gateway"
}

Side-by-side gateway log vs portable receipt (hashes match the live gateway attest demo). The full feature comparison lives on The Prove Gap.

Deploy gateways for how traffic flows. Deploy Aevesa for what was permitted. You get proofs your auditors can recompute.

Trust center

Review evidence before you book a pilot

Public specs and diligence packs with no login, no NDA gate for the technical baseline. Request a briefing when you need deployment topology and fail-mode walkthroughs.

Assurance documentation

Fail-mode matrix, EU AI Act prEN mapping, OWASP ASI controls, MCPShield coverage, threat model, and published SLOs.

Trust Bundle · updated June 2026

Open trust bundle →

Open specs & verify API

liability-receipt schema, offline @aevesa/verify, and the Open Evidence API your auditors can call independently of our UI.

Open Evidence API · public endpoints

Read Open Evidence API →

Conformance programs

Gateway attest → liability receipt → offline verify in under five minutes. Reference flows for standards and procurement reviewers.

Conformance Lab · live badge programs

Browse conformance lab →

Need deployment topology or a fail-closed walkthrough? Request a technical briefing · Protocol repo

Decision Layer

Every Action Has a Path. High-Risk Gets a Human.

Aevesa routes every agent intent through two enforcement paths. Routine actions clear in milliseconds. High-stakes actions pause for a human decision, and that decision becomes a tamper-proof activity receipt.

Fast Pass
Low Risk → Instant Clearance
  1. 1 Agent submits intent to Aevesa for runtime interception
  2. 2 Heuristic Risk Analyzer scores intent below threshold
  3. 3 Signed clearance passport issued, action proceeds, hash-chained ledger entry written
avg latency: <12ms · fully automated
Slow Pass
High Risk → Human Decision Required
The Hero Feature
  1. 1 Consequence Twin simulates the action in a sandboxed environment
  2. 2 Slack notification fires with Approve / Deny buttons to the security team
  3. 3
    Human decision generates a unique tamper-proof activity receiptrecorded in the Aevesa Ledger
  4. 4 Dashboard timeline shows the full chain: Agent → Intercept → Approval → Receipt
hash-chained proof · auditor-grade · SOC 2 aligned controls

Tamper-Proof Receipt

The Cryptographic Activity Receipt

Every high-risk intervention generates a tamper-proof activity receipt. This isn't just a log entry; it's a cryptographically signed artifact your auditors can recompute offline (distinct from a wallet transaction signature).

dh_sha256:a3f9e1c2b804d57f3a91e6c4d2b30e7a1f58c9d6e2a04b73f1c8d5e9a2b30c74

  • Witnessed: Hash-chained in the Aevesa ledger at approval time; optional Rekor/SCITT witness or chain anchor when you enable it.
  • Portable: Share receipts with security teams or regulators without exposing underlying payloads.
  • Verifiable: Stakeholders can validate integrity independently via verify.aevesa.com.

Before/after deployment benchmarks for security and audit teams: Enterprise deployment comparison.

Human-in-the-Loop

Active Gating: Approve or deny in Slack.

When Aevesa intercepts a high-stakes action, your team gets an instant Slack alert with agent, tool, payload preview, and ledger entryHash. Approve or deny in one click. The decision is hash-chained with a forensic link your auditors can follow offline.

Slack said yes. Aevesa proves yes to what: the HITL approval receipt cryptographically binds approver identity to the exact tool-call digest (hitl-approval-receipt/v1, ASI09-shaped). Try the HITL approval demo.

  • ✓ Contextual Alerts: Instant visibility into the ‘Why’ behind every interception.
  • ✓ Slack Handshake: One-click approve or block override without leaving your workspace.
  • ✓ Verified Links: Every alert carries a direct link to the cryptographically signed audit trail in the Evidence Vault.
Slack · #governance-alerts
Slack HITL alert: void_transaction blocked pending sign-off with Approve and Deny buttons, ledger entryHash, and Aevesa forensic entry links
Pending path: HITL_APPROVAL_REQUIRED with one-click Approve / Deny in #governance-alerts.

Go deeper

Architecture, benchmarks, and evidence vault

The homepage stays focused on verify-first proof. Technical comparisons, APoR protocol detail, and product screenshots live on dedicated pages.

Gateway vs Prove layer

Full vendor-log vs portable-receipt comparison tables and the 90-second Evidence Gap demo path.

Prove Gap comparison →

Deployment benchmarks

Without vs with Aevesa: audit evidence, gateway deny proof, HITL sealing, and incident cost context for enterprise buyers.

Enterprise benchmarks →

Why Aevesa & APoR

Protocol layer detail, evidence-grade gauntlet, architecture diagrams, and the sovereign evidence vault tour.

Why Aevesa →

Aevesa

Offline-verifiable proof for every material agent action, with a dashboard for operators, not auditors.

Six evidence tiers (Sandbox through Fortress). Start with a verifiable receipt at verify.aevesa.com; scale to Art. 12/14 export packs and Assurance Autopilot. Contact sales for pricing and procurement.

Aevesa

The Sandbox

Self-serve governance POC: ship a verifiable receipt to your security buyer

Free to start

  • · 1 Shareable Tamper-Proof Receipt / mo
  • · 100 Guarded Actions / mo Automated pause after 100 actions to prevent unintended cost or drift
  • · Single Developer Workspace
  • · Baseline Policy Checks
  • · Self-Guided Documentation Access
Start free Build the governance loop yourself with a Tamper-Proof Receipt and verify.aevesa.com included

Aevesa

Operational Shield

Land with gateway attest: one webhook after permit/deny, verifiable receipts from day one

  • ✓ Gateway Attest Webhook (Unity, Cloudflare, Portkey-class)
  • ✓ liability-receipt/v1 mint + verify.aevesa.com
  • ✓ MCP receipt-before-action (expand path)
  • ✓ 30-Day Audit Log Retention
Contact Sales
Merkle-Secured Ledger

Aevesa

Vanguard

Professional teams: hash-chained integrity on every tier; Vanguard adds Merkle-tree audit layouts and advanced hardening

  • ✓ Merkle-Tree Audit Layout (Vanguard)
  • ✓ Tamper-Evident Log Chain with Root Hash Export
  • ✓ TeamPCP Supply Chain Attack Mitigations
  • ✓ Vanguard-Tier Security Hardening Features
  • ✓ Evidence of Care Programme Features
Contact Sales
Recommended

Aevesa

Compliance-in-a-Box

For compliance-driven organizations standardizing governance, evidence, and identity controls

  • ✓ EU AI Act Art. 12/14 Export Packs
  • ✓ GRC-compatible evidence feed (when you configure webhooks)
  • ✓ Signed Audit Evidence Exports
  • ✓ Role-Based Access Control
Contact Sales

Aevesa

The Sovereign

Enterprise governance with deployment control, custom policy, and white-glove audit execution

  • ✓ Dedicated Instance
  • ✓ Private Cloud, VPC, or On-Prem Deployment
  • ✓ Custom Policy Engine & Control Mappings
  • ✓ White-Glove Audit Support
  • ✓ SSO / SAML, Procurement & Contractual SLA Terms
Contact Sales

Aevesa

The Fortress

Custom deployment for global enterprises: private instance, BYOK, and hands-on audit engineering

  • ✓ Private Instance (VPC or On-Prem)
  • ✓ Customer-Managed Keys (BYOK)
  • ✓ White-Glove Audit Support
  • ✓ Custom Policy Engine Development
Contact Sales

Usage-based anchors

Anchor credit packs

Verification on verify.aevesa.com stays free for auditors and third parties. Production ledger writes consume metered anchor credits (SaaS billing, not a protocol token). Self-serve packs: 10 for $10, 50 for $40, 200 for $120 via Stripe, Base USDC, or Solana USDC.

New accounts include starter credits. Paid tiers also bundle anchor credits. Optional on-chain anchor submits are env-gated and disclosed in proof-strength exports.

Buy anchor credit packs
SHA-256 Hash Chained
AES-256 Encrypted
SOC 2 aligned controls

Frequently Asked Questions

Runtime interception, tamper-proof activity receipts, and how Aevesa differs from gateway-only stacks or plain audit logs.

Open full FAQ

Compliance exports, retention, integrations, and deployment patterns.

Ready to see Aevesa in action?

Start with the 90-second Evidence Gap demo, then reach out when you want a briefing.

Contact Sales opens a pre-filled email to sales@aevesa.com (no copy and paste required). Agentic finance design partners: use the preset below.

Agentic finance design partner (pre-filled email) team@aevesa.com

Prefer web mail? Open in Gmail or Outlook web

Built for Enterprise

Compliance-ready infrastructure for Global Standards

✓

SOC 2 aligned controls

Audit-ready infrastructure with hash-chained evidence, access controls, and a published trust bundle. SOC 2 Type II attestation in progress where applicable.

✓

GDPR-Aligned Protocol

Edge-first enforcement with local verification paths. GDPR-aligned data handling and zero customer source code storage.

✓

HIPAA-ready architecture

Enterprise-grade encryption (AES-256) with hash-chained audit trails and access control federation. BAA and deployment hardening available on enterprise tiers.

Production fail-closed default
MCP gate p99 ≤ 8 ms (harness)
Verify verify.aevesa.com
Cryptography Ed25519 SHA-256 AES-256