Re: Agentic Linked Data

> agents can only do what they have the right to
>
Agreed 100%!

I don’t see about it as trust of the agent – just that the Agent (human, AI or other) has the rights/permissions to do something.  Trust is something that only a human can establish – not machines.


> The reference around authenticity is a property of a (certain type of) object.
>
Authenticity is a property of any object – digital or physical.  And authenticity is not the same as trust – something can be 100% authentic, but you (as a human) can choose to still not trust it!


Leonard

From: Joshua Cornejo <josh@marketdata.md>
Date: Monday, January 13, 2025 at 8:39 AM
To: public-solid <public-solid@w3.org>
Subject: Re: Agentic Linked Data

EXTERNAL: Use caution when clicking on links or opening attachments.


Hi Leonard,

The sentence was cut in the context of a larger paragraph.

Knut-Olav’s statement was about the trust to the Agent. And my reaction is that “…agents can only do what they have the right to…”.

The reference around authenticity is a property of a (certain type of) object.

For example: an API call on a predefined endpoint (“access to my google calendar”) is not the intended use for C2PA?

Further, is the API the content or the entries in the calendar? Why wouldn’t I trust my calendar (to which I have to authenticate anyway)?

Regards,
___________________________________
Joshua Cornejo
marketdata<https://www.marketdata.md/>
smart authorisation management for the AI-era

From: Leonard Rosenthol <lrosenth@adobe.com>
Date: Monday 13 January 2025 at 13:28
To: Josh Cornejo <josh@marketdata.md>, Knut-Olav Hoven <knutolav@gmail.com>
Cc: "frederick@graphmetrix.com" <frederick@graphmetrix.com>, Melvin Carvalho <melvincarvalho@gmail.com>, Jesse Wright <jesse.wright@jesus.ox.ac.uk>, public-solid <public-solid@w3.org>
Subject: Re: Re: Agentic Linked Data
Resent-From: <public-solid@w3.org>
Resent-Date: Mon, 13 Jan 2025 13:27:57 +0000

Rights declarations (such as with ODRL or RightsML) simply express what the rights holders wishes to allow other to do (or not do) with the resource being described.  It doesn’t – nor should it – express anything related to trust.

Instead, this is where the work of C2PA (https://c2pa.org<https://c2pa.org/>) comes into play – enabling someone to establish a series of “trust signals” about a given asset/resource that downstream consumers can evaluate to determine their “trust” of the asset/resource.

Leonard

From: Josh Cornejo <josh@marketdata.md>
Date: Sunday, January 12, 2025 at 4:56 PM
To: Knut-Olav Hoven <knutolav@gmail.com>
Cc: frederick@graphmetrix.com <frederick@graphmetrix.com>, Melvin Carvalho <melvincarvalho@gmail.com>, Jesse Wright <jesse.wright@jesus.ox.ac.uk>, public-solid <public-solid@w3.org>
Subject: Re: Agentic Linked Data

EXTERNAL: Use caution when clicking on links or opening attachments.


“I would then use some vocabulary to express my trust in the statements/documents it creates”

You mean: rights management/authorisation.


___________________________________

Joshua Cornejo

marketdata<https://www.marketdata.md/>

smart authorisation management for the AI-era

________________________________
From: Knut-Olav Hoven <knutolav@gmail.com>
Sent: Sunday, January 12, 2025 9:23 pm
To: Joshua Cornejo <josh@marketdata.md>
Cc: frederick@graphmetrix.com <frederick@graphmetrix.com>; Melvin Carvalho <melvincarvalho@gmail.com>; Jesse Wright <jesse.wright@jesus.ox.ac.uk>; public-solid <public-solid@w3.org>
Subject: Re: Agentic Linked Data


How about this:

_:mybot a foaf:Agent .
_:me foaf:made _:mybot .

It doesn't say I created the technology behind "mybot", but I made this resource/thing/configuration and thus inherently control it. Doesn't mean I have to trust everything this agent does...

And I wouldn't let it write directly into my documents.

I would then use some vocabulary to express my trust in the statements/documents it creates. And probably copy selected statements into my own documents.

--
Knut-Olav Hoven

søn. 12. jan. 2025, 20:28 skrev Joshua Cornejo <josh@marketdata.md<mailto:josh@marketdata.md>>:
IMHO, ontologists would argue that the definitions for linked data should use the FOAF ontology for the definition of most “general” classes and stick to corresponding definitions …

http://xmlns.com/foaf/spec/#term_Agent

http://xmlns.com/foaf/spec/#term_Person


The Person<http://xmlns.com/foaf/spec/#term_Person> class is a sub-class of the Agent<http://xmlns.com/foaf/spec/#term_Agent> class, since all people are considered 'agents' in FOAF.

FOAF also defines Organisation as a type of agent. Other ontologies extend into Automatons/etc.

Others like DCAT<https://www.w3.org/TR/vocab-dcat-3/> bind Dublin Core and FOAF:

dcat:resource<https://www.w3.org/TR/vocab-dcat-3/#Property:resource_creator> has a property dcmi:creator<https://www.dublincore.org/specifications/dublin-core/dcmi-terms/#creator> with a range of foaf:Agent<http://xmlns.com/foaf/spec/#term_Agent>.

___________ ________________________
Joshua Cornejo
marketdata<https://www.marketdata.md/>
smart authorisation management for the AI-era

From: Frederick Gibson <frederick@graphmetrix.com<mailto:frederick@graphmetrix.com>>
Reply-To: <frederick@graphmetrix.com<mailto:frederick@graphmetrix.com>>
Date: Sunday 12 January 2025 at 18:27
To: Josh Cornejo <josh@marketdata.md<mailto:josh@marketdata.md>>
Cc: Melvin Carvalho <melvincarvalho@gmail.com<mailto:melvincarvalho@gmail.com>>, Jesse Wright <jesse.wright@jesus.ox.ac.uk<mailto:jesse.wright@jesus.ox.ac.uk>>, public-solid <public-solid@w3.org<mailto:public-solid@w3.org>>
Subject: Re: Agentic Linked Data

“Though Tim noted he’d be wary of something calling itself both a Person and an Agent!”

If we look at the OED definition of agent:

"A person who or thing which acts upon someone or something; one who or that which exerts power; the doer of an action. Sometimes contrasted with the patient (instrument, etc.) undergoing the action."

"A person who acts as a substitute for another; one who undertakes negotiations or transactions on behalf of a superior, employer, or principal; a deputy, steward, representative; (in early use) an ambassador, emissary. Also figurative. Now chiefly in legal contexts."

By definition, a person can be both type person and type agent, just as a person can have countless types depending on the state of a person at a given time.  And given that "thing which..that which" is included in the first definition, it would be consistent that any system could be an agent acting on behalf of another system (whether artificial or organic), not just people as agents.

Fred Gibson
Founder & CEO
mobile: 415.335.8232

1255 Treat Blvd,<https://www.google.com/maps/search/1255+Treat+Blvd,+Suite+300?entry=gmail&source=g> Suite 300<https://www.google.com/maps/search/1255+Treat+Blvd,+Suite+300?entry=gmail&source=g>
PMB#4611
Walnut Creek, CA  94597
office: 925.940.0741
[cid:image001.png@01DB65C0.78F96CA0]





---- On Sun, 12 Jan 2025 09:25:59 -0800 Josh Cornejo <josh@marketdata.md<mailto:josh@marketdata.md>> wrote ---


“Though Tim noted he’d be wary of something calling itself both a Person and an Agent!”

 ODRL has a :isA operator to work around these type of validation/specialisation semantics. (Equivalent to typecasting in programming)




___________________________________

Joshua Cornejo

marketdata<https://www.marketdata.md/>

smart authorisation management for the AI-era

________________________________
From: Melvin Carvalho <melvincarvalho@gmail.com<mailto:melvincarvalho@gmail.com>>
Sent: Sunday, January 12, 2025 4:26 pm
To: Jesse Wright <jesse.wright@jesus.ox.ac.uk<mailto:jesse.wright@jesus.ox.ac.uk>>
Cc: public-solid <public-solid@w3.org<mailto:public-solid@w3.org>>
Subject: Re: Agentic Linked Data



so 28. 12. 2024 v 12:34 odesílatel Jesse Wright <jesse.wright@jesus.ox.ac.uk<mailto:jesse.wright@jesus.ox.ac.uk>> napsal:
Hi Melvin,

Have you come across the Web Agents CG https://www.w3.org/community/webagents/ - there are several people working in that direction there.


Hi Jesse,

Thanks for pointing out the Web Agents CG. Yes, I’ve been a member since its inception—an excellent group!

Quick note, as not all responses made it to the mailing list over the holidays. I used an LLM to summarize some key points:

Summary of the Discussion on Agentic Linked Data

Participants

  *   Melvin Carvalho: Initiated the discussion.
  *   Joshua Cornejo: Experienced in ODRL and authorization architecture.
  *   Eric Jahn: Interested in agent roles and permissions.
  *   Aad Versteden: Integrates AI and Linked Data in semantic.works.
  *   Sindhu Raju: Focuses on personal data management and consumer use cases.
  *   Matt Taylor: Consultant in ethical tech, cautious about broad agentic access.
  *   Ram Mukund Kripa: Developed privacy agents for consent management.
  *   Jesse Wright: Highlighted the Web Agents CG.
  *   Jacob Beauchamp: Exploring agentic learning and entity data.

There’s clear interest in moving this forward. I also mentioned Agentic Linked Data on the SolidOS call, where the idea (of agents) was well received. For context, TimBL’s “timblbot” illustrates prior work:
https://timblbot.inrupt.net/profile/card#me

Classes include:

  *   schema:Person, schema:SoftwareApplication, foaf:Agent, foaf:Person, prov:SoftwareAgent.

(Though Tim noted he’d be wary of something calling itself both a Person and an Agent!)

Next steps: We’re probably too small for a standalone Community Group. A practical option might be to work within the Solid CG for now, with a dedicated chat area for agentic topics. Initial work items could include adapting Agent entities to existing Solid tooling, libraries, pods, servers, and apps.

Looking forward to further discussion and collaboration!

Best,
Melvin


Best,
Jesse

Get Outlook for Android<https://aka.ms/AAb9ysg>
________________________________
From: Melvin Carvalho <melvincarvalho@gmail.com<mailto:melvincarvalho@gmail.com>>
Sent: Saturday, December 28, 2024 11:11:09 AM
To: public-solid <public-solid@w3.org<mailto:public-solid@w3.org>>
Subject: Agentic Linked Data


Hi All,

When I started this group, it was with the idea that Solid = Social Linked Data. Solid's foundation on WebID ties it to the concept of "Agent," based on FOAF's Agent class (parent of FOAF Person).

With "agentic AI" really taking off right now, I wonder—would anyone be interested in exploring "Agentic Linked Data"? It feels like a natural direction.

Best,

Melvin


___________________________________

Joshua Cornejo

marketdata<https://www.marketdata.md/>

smart authorisation management for the AI-era




___________________________________

Joshua Cornejo

marketdata<https://www.marketdata.md/>

smart authorisation management for the AI-era