Getting started with AI Tools
- Updated: 2024/10/15
Getting started with AI Tools
Leverage AI Agents built on our Automation 360 platform, which harness the potential of generative AI models to make decisions, learn from data, and interact through natural language. These agents enable fully autonomous automations by executing a variety of tasks across different enterprise systems within a comprehensive business process.
Utilize the capability of AI Agent Studio to experiment with foundational models and prompts, creating reusable AI Skills tailored to your needs. Share these skills to facilitate easy integration for developers within the Automation 360 Control Room. Our AI-powered agents are ready to support you and take you beyond by connecting you to agentic-processes, orchestrated across enterprise systems.
Let us look at a use case to understand the concept and benefit of AI Tools.
There is a business requirement for routing incoming customer emails from a central message Inbox folder to the relevant customer support group for further action. Based on the tone of the email, the email needs to be sorted into a category such as happy, unhappy, dissatisfied, upset, or others. Once categorized, these should be forwarded to the relevant support group for further action. This feature lets you automate the process of analyzing the email sentiment using a predefined AI Skill. You can then route the email based on the sentiment-analysis to the relevant support group to respond back to the customers or take necessary action.
This outcome can be delivered by creating an AI Skill with the prompt-input tuned for text sentiment analysis supported by a foundational model, which will read the body of the email and produce a sentiment score. Based on the score, the automation can route the support email to the relevant group for further action. This AI Skill can be used to automate and complete this entire task quickly and efficiently without human intervention across different automation solutions.
Here's an overview of the process and the role each persona plays for implementing the scenario.
Automation Admin (Jake)
- Connects to a curated list of foundational models from hyperscaler vendors such as Amazon Bedrock, Google Vertex AI, Azure OpenAI, OpenAI and others.
- Creates Standard, Fine tuned, or Grounded Model connections with RAG capability from Amazon Bedrock or Google Vertex AI.
- Tests the model connections for viability.
- Makes these connections available to the Pro Developers to create AI Skills via custom role.
Pro Developer (Marcus)
- Creates an AI Skill for sentiment analysis using available Model connections.
- Defines the AI Skill to address the business need of sorting the emails received from customers into categories and forward them to the relevant departments for further action.
- Tests the prompt by using available Model connections, and fine-tuning the prompt parameters to optimize results for the requirement.
- Publishes the AI Skill so the other Pro Developers and Citizen Developers can use it to create automations quickly.
Citizen Developer (Sue)
- Creates a new automation or updates an existing one using the Bot editor. See: AI Skills package. in the
- Chooses the AI Skill made available to her.
- Defines the AI Skill values in the automation.
- Runs and tests the automation to ensure all actions in the automation are running as expected.
Set up roles and permissions for all personae. See Roles and permissions for AI Tools.