Re: My paper on applying agentic AI to business workflows

Hi Dave

I wrote somes articles related to W3C’s work on Verifiable Credentials and
Decentralised Identifiers.  You may be interested to check.

Supplier Verification and Cross-Border Payment Use Case (
https://itstysonchen.me/perspectives/architectures/ai-native-management/supplier-verification-cross-border-payment/
)

This document details a critical business process: the secure verification
of a new supplier and the subsequent execution of a cross-border payment.
This scenario is common in global trade and presents significant challenges
related to trust, compliance, and financial risk. By modeling this workflow
using the Agent Ontology(the single source of JSON-LD, TTL, VC), we
demonstrate how autonomous agents can collaborate, delegate tasks, and
establish an auditable trail for complex transactions.

Other articles:

- An analysis of enterprise transformation from OEM to OBM, modeled as a
dynamic shift in agent capabilities, intents, and delegations.  (
https://itstysonchen.me/perspectives/architectures/ai-native-management/oem-odm-obm-as-semantic-architecture/
)
- AI Liability Insurance and UL-like Certification
(
https://itstysonchen.me/perspectives/architectures/ai-native-management/ai-liability-insurance-ullike-certification/
)

Some discussion and reference implementation are in W3C Semantic Agent
Communication Community Group, which is a major focus in standard of
semantic layer communication.

Dave Raggett <dsr@w3.org> 於 2026年2月25日週三 下午7:08寫道：

> That sounds like it deserves another paper to cover the required details.
> W3C’s work on Verifiable Credentials and Decentralised Identifiers sounds
> relevant.  The IETF is actively discussing agent to agent standards.
>
> On 25 Feb 2026, at 07:17, 陳信屹 <tyson@slashlife.ai> wrote:
>
> Your tiered architecture addresses semantic orchestration within an
> enterprise boundary.
>
> Have you considered how reasoning traces, delegation intent, and service
> invocation semantics would operate across institutional boundaries where
> agent identity and authority need to be verifiable?
>
>
> Dave Raggett <dsr@w3.org> 於 2026年2月24日週二 下午8:20寫道：
>
>>
>> You may be interested in a preprint of my perspective paper on applying
>> agentic AI to business workflows:
>>
>> <cogai.png>
>>
>> cogai/papers/AI4OfficeWork.pdf at master · w3c/cogai
>> <https://github.com/w3c/cogai/blob/master/papers/AI4OfficeWork.pdf>
>> github.com
>> <https://github.com/w3c/cogai/blob/master/papers/AI4OfficeWork.pdf>
>> <https://github.com/w3c/cogai/blob/master/papers/AI4OfficeWork.pdf>
>>
>> The approach exploits the strength of LLMs for reasoning with the open
>> texture of language in combination with symbolic approaches for efficient
>> deterministic processing. It shows how Agentic AI can be used for semantic
>> orchestration across a swarm of specialised agents, along with delegating
>> difficult or high risk cases to human staff, who can enrich the business
>> rules and precedents used by the agents.  The approach uses audit trails as
>> a basis for human oversight.  Agents are required to cite which rules were
>> used along with supporting quoted extracts. These lower the risk of
>> hallucinations, and can be checked automatically.
>>
>> Dave Raggett <dsr@w3.org>
>>
>>
>>
>>
> Dave Raggett <dsr@w3.org>
>
>
>
>