Why you should use generative AI for writing Ansible Playbooks
Why you should use generative AI for writing Ansible Playbooks
Generative artificial intelligence (gen AI) can usher in a new era of developer productivity by disrupting how work is done. Coding assistants can help developers by generating content recommendations from natural language prompts.
As today’s hybrid cloud architectures expand in size and complexity, IT automation developers and operators can benefit from applying gen AI to their work. In a 2023 IBM survey of 3,000 CEOs worldwide, three out of four reported that their competitive advantage would depend on who had the most advanced gen AI.
To help businesses accelerate their IT automation initiatives with gen AI, IBM watsonx™ Code Assistant for Red Hat® Ansible® Lightspeed is introducing the first of several capabilities for model tuning and offering a no-cost, limited trial for Ansible Automation Platform users to begin using generative AI coding assistance.
The Red Hat Ansible Automation Platform empowers many IT operators and development teams to configure systems, deploy software, and orchestrate advanced IT workflows. Ansible Playbooks define critical automation tasks for resource creation, management and scaling across the enterprise, supporting successful digital transformation. Applying gen AI to create Ansible Playbooks accelerates IT automation initiatives, enhancing developer productivity and driving greater efficiency.
IBM watsonx Code Assistant for Red Hat Ansible Lightspeed is:
1. Domain-specific
Designed to help accelerate IT automation, IBM watsonx Code Assistant for Red Hat Ansible Lightspeed employs a large language model (LLM) that is specifically trained on Ansible Galaxy data sets to help developers create enterprise-ready content with AI-generated recommendations. Automation developers can provide single or multi-task prompts in plain language directly within Visual Studio Code (VS Code).
Key data from the technical preview:
- Approximately 4,000 developers actively participated in the technical preview.
- AI-generated content recommendations had an overall average acceptance rate of 85% (from 27 July to 23 October 2023, based on over 41,000 recommendations).
- Productivity improvements ranged from 20% to 45%.
2. Customizable
IBM watsonx Code Assistant for Red Hat Ansible Lightspeed empowers organizations to further tune its domain-specific LLM using their own organization’s unique Ansible data. The content parser tool enables users to easily convert existing playbook content into a single JSONL file, allowing users to customize the model to the specific needs of their business with ease.
IBM watsonx Code Assistant for Red Hat Ansible Lightspeed can discover unique modules used in your existing playbooks through prompt tuning. It learns about your team’s module preferences, helping to provide personalized code recommendations tailored to your enterprise.
Furthermore, as your business grows, your repository of Ansible Playbook content expands. With the capability for periodic tuning, watsonx Code Assistant for Red Hat Ansible Lightspeed can adapt its content recommendations to match the evolution of your business.
3. Trained AI
IBM watsonx Code Assistant for Red Hat Ansible Lightspeed is trained specifically on Ansible data sets and quality tested by Ansible experts who govern the acquisition and processing of data sets, including filtering out personally identifiable information and toxic or harmful content. IBM watsonx Code Assistant for Red Hat Ansible Lightspeed provides references to the possible source, author, and license information for its content recommendations.
