The VAST Platform AI Assistant: Integrating LLMs into a Live Smalltalk Environment - 25 March 2026

UK Smalltalk <[email protected]> Wed, 18 Mar 2026 23:29:51 +0000
Newsgroups gmane.comp.lang.self,gmane.comp.lang.smalltalk.gnu.general
Message-ID <CAPZPNh3idxiC26F4Ek+NF1UPVoPD6nPH-aO0YmA+GE-dMtzMmQ@mail.gmail.com>
--===============2637075072526561071==
Content-Type: multipart/alternative; boundary="000000000000cf4888064d54d4fe"

--000000000000cf4888064d54d4fe
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

Smalltalk environments have long been pioneers in developer productivity.
With the VAST Platform AI Assistant, Instantiations is extending that
tradition by integrating Large Language Models (LLMs) directly into the
VAST platform. This new tool is designed to bring AI capabilities directly
into your daily workflow.

In this session, Johan, Kris, and Mariano will share a user experience
report and a live demonstration of the assistant=E2=80=99s current capabili=
ties,
powered by Google=E2=80=99s Gemini.

You=E2=80=99ll see how it goes beyond simple chat by directly interacting w=
ith the
live VAST image through the LLM=E2=80=99s =E2=80=9Ctools=E2=80=9D capabilit=
ies. This allows
investigating source code as it responds to your questions.

These examples will demonstrate how the VAST Platform AI Assistant
leverages the live nature of Smalltalk to act as a true pair programmer.

We=E2=80=99ll also look ahead at our enterprise-focused roadmap, including =
support
for local models to ensure privacy and security, integration with
additional LLM providers, and our vision for deeper IDE-level capabilities
and Runtime Intelligence.

Join us to explore how we are shaping the future of AI-assisted development
in VAST to better empower software developers. See it in action, try it
out, and join the conversation on GitHub (
https://github.com/instantiations/VAST-Platform-AI-Assistant ).

Johan Brichau ( https://be.linkedin.com/in/johanbrichau ) is a seasoned
software engineer with over 25 years of experience across a wide range of
Smalltalk environments. He joined the VAST Platform development team at
Instantiations in January 2025. Prior to that, he spent nearly 15 years as
co-founder and CTO of Yesplan, a world-leading online venue management
platform. Johan holds a PhD in computer science from the Vrije Universiteit
Brussel (2005) and has actively contributed to several open source projects=
.

Kris Gybels recently joined Instantiations to work on the VAST Platform=E2=
=80=99s
AI-based tool support. He previously spent a number of years in academia
researching Declarative Meta Programming and its application to
Aspect-Oriented Programming, and over a decade co-developing the Yesplan
venue management system, during which he made a number of contributions to
Pharo, most notably Pharo 12=E2=80=99s improved Mac =E2=80=98Retina display=
=E2=80=99 support, as
well as to Seaside and its Parasol web testing framework.

Mariano Martinez Peck ( https://ar.linkedin.com/in/mariano-martinez-peck )
is a systems engineer specializing in dynamic programming language
software. In 2018, he joined Instantiations to further develop the VAST
Platform through the addition of new frameworks, libraries and tools, as
well as improving the existing code base of VAST. He is active in the
Smalltalk development community, and has used his expertise to co-author
numerous open source projects. Mariano has a PhD in Computer Science, and
his academic research has been published across various international
journals. In addition to his development duties, he currently leads the
VAST Platform engineering team at Instantiations. In his personal time,
Mariano enjoys traveling as well as outdoor activities like camping and
fishing.

This will be an online meeting.

If you'd like to join us, please sign up in advance on the meeting's Meetup
page ( https://www.meetup.com/ukstug/events/313492185/ ) to receive the
meeting details.

--000000000000cf4888064d54d4fe
Content-Type: text/html; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr">Smalltalk environments have long been pioneers in develope=
r productivity. With the VAST Platform AI Assistant, Instantiations is exte=
nding that tradition by integrating Large Language Models (LLMs) directly i=
nto the VAST platform. This new tool is designed to bring AI capabilities d=
irectly into your daily workflow.<br><br>In this session, Johan, Kris, and =
Mariano will share a user experience report and a live demonstration of the=
 assistant=E2=80=99s current capabilities, powered by Google=E2=80=99s Gemi=
ni.<br><br>You=E2=80=99ll see how it goes beyond simple chat by directly in=
teracting with the live VAST image through the LLM=E2=80=99s =E2=80=9Ctools=
=E2=80=9D capabilities. This allows investigating source code as it respond=
s to your questions.<br><br>These examples will demonstrate how the VAST Pl=
atform AI Assistant leverages the live nature of Smalltalk to act as a true=
 pair programmer.<br><br>We=E2=80=99ll also look ahead at our enterprise-fo=
cused roadmap, including support for local models to ensure privacy and sec=
urity, integration with additional LLM providers, and our vision for deeper=
 IDE-level capabilities and Runtime Intelligence.<br><br>Join us to explore=
 how we are shaping the future of AI-assisted development in VAST to better=
 empower software developers. See it in action, try it out, and join the co=
nversation on GitHub ( <a href=3D"https://github.com/instantiations/VAST-Pl=
atform-AI-Assistant">https://github.com/instantiations/VAST-Platform-AI-Ass=
istant</a> ).<br><br>Johan Brichau ( <a href=3D"https://be.linkedin.com/in/=
johanbrichau">https://be.linkedin.com/in/johanbrichau</a> ) is a seasoned s=
oftware engineer with over 25 years of experience across a wide range of Sm=
alltalk environments. He joined the VAST Platform development team at Insta=
ntiations in January 2025. Prior to that, he spent nearly 15 years as co-fo=
under and CTO of Yesplan, a world-leading online venue management platform.=
 Johan holds a PhD in computer science from the Vrije Universiteit Brussel =
(2005) and has actively contributed to several open source projects.<br><br=
>Kris Gybels recently joined Instantiations to work on the VAST Platform=E2=
=80=99s AI-based tool support. He previously spent a number of years in aca=
demia researching Declarative Meta Programming and its application to Aspec=
t-Oriented Programming, and over a decade co-developing the Yesplan venue m=
anagement system, during which he made a number of contributions to Pharo, =
most notably Pharo 12=E2=80=99s improved Mac =E2=80=98Retina display=E2=80=
=99 support, as well as to Seaside and its Parasol web testing framework.<b=
r><br>Mariano Martinez Peck ( <a href=3D"https://ar.linkedin.com/in/mariano=
-martinez-peck">https://ar.linkedin.com/in/mariano-martinez-peck</a> ) is a=
 systems engineer specializing in dynamic programming language software. In=
 2018, he joined Instantiations to further develop the VAST Platform throug=
h the addition of new frameworks, libraries and tools, as well as improving=
 the existing code base of VAST. He is active in the Smalltalk development =
community, and has used his expertise to co-author numerous open source pro=
jects. Mariano has a PhD in Computer Science, and his academic research has=
 been published across various international journals. In addition to his d=
evelopment duties, he currently leads the VAST Platform engineering team at=
 Instantiations. In his personal time, Mariano enjoys traveling as well as =
outdoor activities like camping and fishing.<br><br>This will be an online =
meeting.<br><br>If you&#39;d like to join us, please sign up in advance on =
the meeting&#39;s Meetup page ( <a href=3D"https://www.meetup.com/ukstug/ev=
ents/313492185/">https://www.meetup.com/ukstug/events/313492185/</a> ) to r=
eceive the meeting details.</div>

--000000000000cf4888064d54d4fe--

--===============2637075072526561071==
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

_______________________________________________
Self-interest mailing list -- [email protected]
To unsubscribe send an email to [email protected]

--===============2637075072526561071==--