Accelerating Ansible with Watson X
Key Points
- IBM Watson X Code Assistant for Red Hat Ansible LightSpeed uses generative AI to turn natural‑language prompts into Ansible playbooks, allowing users to install and configure services like Apache with a single command.
- Users can combine multiple tasks in one prompt by prefacing the prompt with a hash and separating instructions with ampersands, then accept or edit AI‑generated recommendations via a tab key.
- The platform exposes the training data sources (author, license, etc.) for transparency and lets organizations fine‑tune the underlying large language model with their own private Ansible data to produce more relevant, customized code suggestions.
- An Ansible Content Parser converts existing playbooks into a single JSON‑L file, which can be uploaded to the intuitive Watson X Tuning Studio where non‑experts can run tuning experiments, view metrics, and monitor training loss graphs as the model improves.
- After tuning, the customized model is deployed by copying its ID into the admin portal, making the enhanced suggestions available to authorized users through Red Hat’s Ansible VS Code extension.
Full Transcript
# Accelerating Ansible with Watson X **Source:** [https://www.youtube.com/watch?v=vG54TKeEwP4](https://www.youtube.com/watch?v=vG54TKeEwP4) **Duration:** 00:03:48 ## Summary - IBM Watson X Code Assistant for Red Hat Ansible LightSpeed uses generative AI to turn natural‑language prompts into Ansible playbooks, allowing users to install and configure services like Apache with a single command. - Users can combine multiple tasks in one prompt by prefacing the prompt with a hash and separating instructions with ampersands, then accept or edit AI‑generated recommendations via a tab key. - The platform exposes the training data sources (author, license, etc.) for transparency and lets organizations fine‑tune the underlying large language model with their own private Ansible data to produce more relevant, customized code suggestions. - An Ansible Content Parser converts existing playbooks into a single JSON‑L file, which can be uploaded to the intuitive Watson X Tuning Studio where non‑experts can run tuning experiments, view metrics, and monitor training loss graphs as the model improves. - After tuning, the customized model is deployed by copying its ID into the admin portal, making the enhanced suggestions available to authorized users through Red Hat’s Ansible VS Code extension. ## Sections - [00:00:00](https://www.youtube.com/watch?v=vG54TKeEwP4&t=0s) **Watson X Ansible Code Assistant** - IBM's Watson X Code Assistant for Red Hat Ansible LightSpeed uses generative AI to turn natural‑language prompts into playbooks (e.g., installing Apache), provides tab‑accepted content recommendations with visible provenance, supports multi‑task prompts, and can be customized with an organization’s private Ansible data for tailored outputs. ## Full Transcript
IBM Watson X code assistant for Red Hat
ansible light speed leverages generative
AI to accelerate the creation of anible
playbooks and helps organizations
implement it automation let's see how it
works by asking Watson X code assistant
to install and configure an Apache web
server to start simply input your
commands in natural language and press
enter you'll quickly be served in AI
generated content recommendation if you
want to combine multiple tasks within a
single prompt Begin The Prompt with a
hash
and add ampersands between the different
sets of instructions once again Watson X
code assistant provides an AI generated
content recommendation press tab to
accept the
recommendation or you can modify as
needed to help Foster trust and
transparency the training data that may
have informed the content recommendation
like author and license is easily
accessible since every organization is
different Waton X code assistant
empowers you to customize its underlying
large language model with your existing
an data that helps deliver content
recommendations that are crafted for
your specific preferences for example
say you're creating an open shift
cluster when you enter your prompt
Watson X code assistant suggests
standard content from anible built-in
module however when you customize the
model with your organization's private
anible data set the model generates
custom content more aligned to your
needs the anible content parser tool
empowers developers to transform
existing playbooks into a single Json L
file filled with tr training data with
the data all in one place you can easily
create and run a tuning experiment in
the Watson X code assistant tuning
Studio as you navigate the tuning Studio
the intuitive user interface provides
helpful guidance in other words you
don't need to be a data scientist to use
it simply enter an experiment name and
brief description you can upload your
Json L file or simply drag and drop it
once uploaded you can view your data's
metrics and compare them to the models
Baseline for instance here you see your
data samples modules and unique modules
and how they compare to the anible data
used to train the base model you can
drill into the module count to see the
overall distribution of your data by
module here the new modules are now part
of the training data to initialize model
tuning click start tuning you'll see the
tuning status tracked on screen after
the tuning is complete a training loss
graph reveals the accuracy of your
models predictions as compared to the
training data the graph updates as you
run multiple tuning Cycles training loss
tends to decrease over time okay now
that the customization is complete you
can deploy your tuned model and use it
in Watson X code assistant for Red Hat
anible light speed simply copy the model
ID into the admin portal when activated
your model is accessible to your
authorized users in the anible vs code
extension by Red Hat with the tuned
model Watson X code assistant will
recommend content using modules
functions and other details specific to
your private it environment now let's
head back to VSS code and run the same
task again to see how Watson X code
assistant returns new and improved
content recommendations this time the
module IBM container cluster is being
recommended instead of anbl built-in
module by providing AI based content
recommendations IBM Watson X code
assistant for Red Hat anable light speed
helps make content development easier
and more efficient for hybrid Cloud
developers to see how it can help begin
a trial or reach out to an IBM
representative and book a live
demo