TessPay: Verify-then-Pay Infrastructure for Trusted Agentic Commerce

TL;DR

TessPay tackles the trust gap in agentic commerce by introducing a Verify-then-Pay infrastructure with a two-plane architecture that separates control/verification from settlement. The system anchors agents in a canonical registry, converts user intent into verifiable mandates, locks funds in escrow, and releases payment only after cryptographic Proof of Task Execution (PoTE) backed by TLS Notary and TEE attestations. Its architecture supports chain-agnostic settlement through modular Rail Adapters and Wallet Abstraction, and it maintains a tamper-evident audit trail for dispute resolution. The paper presents threat modeling, tiered verification, and two practical use cases (an e-commerce shopping agent and a portfolio manager) to demonstrate how TessPay enables verifiable, interoperable, and secure agentic payments across heterogeneous ecosystems. Overall, TessPay offers a holistic endpoint for end-to-end agentic transactions, with potential to standardize cross-chain, trust-enabled agent commerce at scale.

Abstract

The global economy is entering the era of Agentic Commerce, where autonomous agents can discover services, negotiate prices, and transact value. However adoption towards agentic commerce faces a foundational trust gap: current systems are built for direct human interactions rather than agent-driven operations. It lacks core primitives across three critical stages of agentic transactions. First, Task Delegation lacks means to translate user intent into defined scopes, discover appropriate agents, and securely authorize actions. Second, Payment Settlement for tasks is processed before execution, lacking verifiable evidence to validate the agent's work. Third, Audit Mechanisms fail to capture the full transaction lifecycle, preventing clear accountability for disputes. While emerging standards address fragments of this trust gap, there still remains a critical need for a unified infrastructure that binds the entire transaction lifecycle. To resolve this gap, we introduce TessPay, a unified infrastructure that replaces implicit trust with a 'Verify-then-Pay' architecture. It is a two plane architecture separating control and verification from settlement. TessPay operationalizes trust across four distinct stages: Before execution, agents are anchored in a canonical registry and user intent is captured as verifiable mandates, enabling stakeholder accountability. During execution, funds are locked in escrow while the agent executes the task and generates cryptographic evidence (TLS Notary, TEE etc.) to support Proof of Task Execution (PoTE). At settlement, the system verifies this evidence and releases funds only when the PoTE satisfies verification predicates; modular rail adapters ensure this PoTE-gated escrow remains chain-agnostic across heterogeneous payment rails. After settlement, TessPay preserves a tamper-evident audit trail to enable clear accountability for dispute resolution.

Figures (2)

• Figure 1: TessPay Internal Architecture : TessPay separates coordination from value movement: the Control and Verification Plane (identity/authorization, orchestration, verification/audit services) governs mandates, A-JWT issuance, PoTE validation, telemetry, and audit rails; the Agent Runtime (user agent → facilitator → worker agent) executes tasks and produces receipts; and the Payment and Settlement Plane uses an escrow smart contract and rail adapters to lock and settle funds across external chains. Green/blue/red arrows denote payment, orchestration, and verification flows respectively.
• Figure 3: TessPay Payment Flow: TessPay end-to-end transaction lifecycle across four phases - (1) discovery and mandate creation (Intent/Cart/Payment), anchored off-chain and user-approved; (2) scoped authorization (A-JWT) and escrow fund lock; (3) delegated task execution with “glass-box” verification via TLSNotary receipts and runtime checksums; and (4) PoTE-gated settlement, releasing funds to the worker agent on valid proof or refunding the user on failure.