B2A Agentic Commerce Implementation Record

A dated technical record of a working business-to-agent (B2A) commerce implementation and its public production tests. Version 1.3 documents a successful, externally initiated and publicly verifiable end-to-end production run completed on 21 September 2026. A third-party participant used its own AI agent and wallet. The agent received a neutral challenge and was not given a merchant, domain, destination, endpoint or checkout link. It independently discovered the public service 101Ts3t and completed a real EUR 0.99 purchase. The payment and completed fulfilment were matched to the same challenge. The provider transaction and discovery review were separately signed with Ed25519. The production verifier validated the signatures, hashes, challenge bindings, transaction references and evidence cross-links, and finalized all four required gates as PASS: discovery evidence, evidence integrity, transaction evidence and verified agentic commerce. The success criteria and protocol commitment were published before the transaction and attested through GitHub/Sigstore. After the result was finalized, the exact privacy-safe proof package was committed publicly and separately attested. Its digest matches the proof included in this deposit. The result can therefore be checked independently from the seller’s website against the pre-event rules, signed evidence, public verification record, repository history and external timestamps. This is a successful external validation of one concrete real-world agentic-commerce run. It demonstrates that an outside agent could discover the service without merchant guidance, complete a live payment and produce sufficient evidence for a public PASS under the previously published rules. The Zenodo deposit contains the complete version 1.3 record and the corresponding public proof archive, including checksums and both Sigstore bundles. It excludes the private observable trace, participant details, billing data, credentials, payment tokens, replay URLs and private signing keys. Versions 1.0–1.2 documented the implementation and the earlier production purchases. Version 1.3 adds the independently initiated public test and its externally timestamped proof chain. The result establishes this specific successful production run; it does not claim universal agent compatibility, statistical reliability or national or global precedence. Earlier versions remain permanently retrievable under their own identifiers.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-09-21
DOI
https://doi.org/10.5281/zenodo.22878834
Primary Topic
Multi-Agent Systems and Negotiation
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
article

B2A Agentic Commerce Implementation Record

Nikola Mishev
Zenodo (CERN European Organization for Nuclear Research)
Multi-Agent Systems and Negotiation
article

B2A Agentic Commerce Implementation Record

Nikola Mishev
article en

Abstract

A dated technical record of a working business-to-agent (B2A) commerce implementation and its public production tests. Version 1.3 documents a successful, externally initiated and publicly verifiable end-to-end production run completed on 21 September 2026. A third-party participant used its own AI agent and wallet. The agent received a neutral challenge and was not given a merchant, domain, destination, endpoint or checkout link. It independently discovered the public service 101Ts3t and completed a real EUR 0.99 purchase. The payment and completed fulfilment were matched to the same challenge. The provider transaction and discovery review were separately signed with Ed25519. The production verifier validated the signatures, hashes, challenge bindings, transaction references and evidence cross-links, and finalized all four required gates as PASS: discovery evidence, evidence integrity, transaction evidence and verified agentic commerce. The success criteria and protocol commitment were published before the transaction and attested through GitHub/Sigstore. After the result was finalized, the exact privacy-safe proof package was committed publicly and separately attested. Its digest matches the proof included in this deposit. The result can therefore be checked independently from the seller’s website against the pre-event rules, signed evidence, public verification record, repository history and external timestamps. This is a successful external validation of one concrete real-world agentic-commerce run. It demonstrates that an outside agent could discover the service without merchant guidance, complete a live payment and produce sufficient evidence for a public PASS under the previously published rules. The Zenodo deposit contains the complete version 1.3 record and the corresponding public proof archive, including checksums and both Sigstore bundles. It excludes the private observable trace, participant details, billing data, credentials, payment tokens, replay URLs and private signing keys. Versions 1.0–1.2 documented the implementation and the earlier production purchases. Version 1.3 adds the independently initiated public test and its externally timestamped proof chain. The result establishes this specific successful production run; it does not claim universal agent compatibility, statistical reliability or national or global precedence. Earlier versions remain permanently retrievable under their own identifiers.

Zenodo (CERN European Organization for Nuclear Research)
Brandman University (US)
Partnerships for the goals
Openalex Percentile: Top 8%
Multi-Agent Systems and Negotiation
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.