As
computational
thinking
(CT)
becomes
increasingly
acknowledged
as
an
important
skill
in
education,
self-directed
learning
(SDL)
emerges
a
key
strategy
for
developing
this
capability.The
advent
of
generative
AI
(GenAI)
conversational
agents
has
disrupted
the
landscape
SDL.However,
many
questions
still
arise
about
several
user
experience
aspects
these
agents.This
paper
focuses
on
two
questions:
personalization
and
long-term
support.As
such,
rst
part
study
explores
eectiveness
personalizing
GenAI
through
prompt-tuning
using
CT-based
prompt
solving
programming
challenges.The
second
identifying
strengths
weaknesses
model
semester-long
project.Our
ndings
indicate
that
while
could
hinder
ease
use
perceived
assistance,
it
might
lead
to
higher
outcomes.Results
from
thematic
analysis
also
is
useful
debugging,
but
presents
challenges
such
over-reliance
diminishing
utility
over
time.
