Re: Agentic Linked Data

Hello Melvin et al,

Agree with using "timblbot" as reference implementation, although we maybe
need Tim's authorization ;)
  * schema:Person
  * schema:SoftwareApplication
  * foaf:Agent
  * foaf:Person
  * prov:SoftwareAgent

This discussion always is going to end up with some technical vs legal
agency distinction. Don't know if any of you are lawyers but I'm not, so I
tend to scope away legal bits for delegation to pros in that space to
observe and report back. This leaves plenty to work on in technical
decisions on linked data vs trust frameworks and person vs agent
classification concerns.

Balance here is the key in my experience. We weigh standardization vs
flexibility. We weigh integration with existing tooling vs new. And of
course we weigh availability vs privacy and security implications.

If we create a more dedicated chat area for such agentic topics, I would
like to help focus towards practical integration across Solid tooling,
libraries, storage, servers and apps. We're still at a place in time where
all of it needs development together.

On that note I've noticed a divergence in philosophical approaches that
could slow our steps towards such applied technical progress.

Either (1) an inclusive/technical approach:
- Multiple classifications possible
- Focus on capabilities and functions
- Emphasis on technical implementation

Or a (2) restrictive/ethical Approach:
- Careful about dual person/agent classification
- Concern for implications and misuse
- Emphasis on responsibility and trust

I would propose we could merge the two successfully using Buber's
philosophical framework into a happier middle path:
- Technical agency allowed while preserving genuine relationship capacity
- Maintain boundary clarity and data integrity
- Enable evolution and growth through interaction

I wrote a bit more in depth here about how Buber helps guide agentic
development:
https://www.flyingpenguin.com/?p=64616

DaviBot


On Sat, Dec 28, 2024, 12:12 Melvin Carvalho <melvincarvalho@gmail.com>
wrote:

> 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
>

-- 
This e-mail, and any attachments thereto, is intended only for use by the 
addressee(s) named herein and may contain legally privileged, confidential 
and/or proprietary information. If you are not the intended recipient of 
this e-mail (or the person responsible for delivering this document to the 
intended recipient), please do not disseminate, distribute, print or copy 
this e-mail, or any attachment thereto. If you have received this e-mail in 
error, please respond to the individual sending the message, and 
permanently delete the email.