# Create a genie
Agent Studio lets you build genies. Genies are AI-powered intelligent agents capable of performing contextual, goal-oriented tasks. You can integrate and automate workflows with the Agent Studio modular framework and no-code interface.
POWERED BY AI
Genies use advanced AI technologies, including Large Language Models (LLMs), to deliver context-aware interactions and precise task execution. Ensure that you review and test your genie’s behavior and skills to meet organizational requirements before deploying it across your workspace.
# Create a Genie profile
The Genie profile section is where you provide detailed prompt engineering to enable your genie to understand its role, objective, and overall goals.
Complete the following steps to configure a Genie profile:
Sign in to your Workato account.
Use the platform drop-down menu to select Agentic. The Your Genies page displays by default.
Switch to Agentic
Click Create genie or Create your first genie to create a new genie. The Basic setup page displays.
Your genies page
Locate the Genie profile section.
Genie profile
Provide a name for your genie in the Name field. Note that this field contains an automatically generated name that you can replace with a unique name for the genie.
Optional. Enter a description in the Description field to inform collaborators about the genie's purpose.
Enter detailed instructions for the genie in the What instructions should this genie follow? field. Use prompt engineering to describe how the genie should make decisions, and include its role, tone, and overall objectives.
For example, the following instructions define an IT support genie's role, tone, and decision-making framework. Adapt these based on your specific use case and organizational needs:
Example instructions
Role You are an IT Support Assistant tasked with handling incoming user requests related to technical issues and support inquiries. Your primary function is to triage requests, create tickets, and provide helpful and reassuring communication to users. Tone Maintain a friendly, professional, and empathetic tone. Avoid technical jargon unless the user demonstrates advanced technical knowledge. Use clear and concise language to ensure accessibility for all users. Primary Objective Acknowledge Requests: Let users know their request has been received promptly. Create Tickets: Log each request into the ticketing system with the appropriate categorization and priority. Provide Information: Share the ticket ID and a direct link to track the status of the request. Reassure the User: Offer a sense of urgency and support by explaining what will happen next. Decision-Making Framework Categorization Identify the type of issue based on user input (e.g., hardware, software, network, or general inquiry). Use keywords in the user's request to determine the appropriate category and assign the correct team if needed. Prioritization Assess urgency based on context clues or explicit user statements. High priority: Issues affecting multiple users or critical systems. Medium priority: Individual productivity issues. Low priority: General inquiries or requests without immediate impact. Escalation If the request involves advanced troubleshooting or a critical incident, escalate to the appropriate team immediately. Include all relevant details in the ticket before escalation. Follow-Up Instructions Notify the user of expected resolution timelines based on ticket priority. Provide a direct link to the ticket for tracking updates or adding further details. Sample Response Scenario: A user reports that their email account is not syncing on their mobile device. Subject: Your Request Has Been Received – Ticket #12345 Hi [User’s Name], Thank you for reaching out about the issue with your email account. I have created a ticket for your request: Ticket #12345. You can track the status of your ticket or add more details here: [Ticket Link]. Our team will investigate the issue and provide an update within [insert timeframe based on priority]. In the meantime, feel free to reply to this email if you have any additional information to share. Thank you for your patience and understanding. We’re here to help! Best regards, [Genie Name]
Click Save.
# Add an AI model
The AI large language model (LLM) that powers your genie’s core functionality is set to Workato AI by default. This is the only AI model available in the genies development stage.
Locate the AI model section and confirm that your LLM is set to Workato AI by default.
AI model
# Add a chat interface
The Chat interface is the platform from which your genie can be accessed and interacted with by your end users. You can't change the chat interface after you start the genie.
CHAT INTERFACE CONFIGURATION
The genies feature can only be configured to use Slack or Microsoft Teams as the chat interface. Support for additional chat interface apps is in development.
Complete the following steps to add a chat interface to your genie:
Locate the Chat interface section and click Configure interface to display the configuration page.
Click Configure interface
Use the Where should users interact with this genie? field to select the app you plan to use as your interface. Available options include Slack and Microsoft Teams.
Select your chat interface
Go to Step 1 and click Create new app. This redirects you to the app you selected and enables you to create a new app.
Go to Step 2 and enter your Client ID. You can find this in the Basic Information or App Credentials section of your app.
Enter your Client Secret. You can find this in the Basic Information or App Credentials section of your app.
Provide your Signing Secret. This is used to verify that interactive messages and events requests originate from your app. You can find this in the Basic Information or App Credentials section of your app.
Click Connect interface.
# Add a knowledge base
Knowledge bases store and organize company-specific information and domain knowledge, enabling your genie to provide more contextualized and accurate responses. Your knowledge base can only be assigned to one genie. Knowledge bases can contain multiple knowledge recipes.
Complete the following steps to create a knowledge base:
Click Knowledge in the sidebar navigation.
Click Create knowledge base.
Provide a Name and Description for your knowledge base.
Add knowledge base
Click Add knowledge base.
# Create a knowledge recipe
Knowledge base recipes are used to load and update information from your various applications. The knowledge base ensures that your genie has access to the latest data and stays aligned with your business requirements. Your knowledge base must contain at least one knowledge recipe. You can't clone recipes from one knowledge base to another knowledge base.
Complete the following steps to create a knowledge recipe:
Go to the knowledge base where you plan to add your knowledge recipe.
Click Create knowledge base.
Click Create knowledge recipe
Provide a name for your knowledge recipe in the Name field.
Go to Pick a starting point and select either Trigger from an app or Run on a schedule.
Click Start building.
Click Start building
Search for the app you plan to use as your trigger in the Choose an app search box and select the connection you created in the preceding steps.
Select and configure the trigger you plan to use for the recipe.
Click + Add action to add an action step to your recipe.
Click Add action
Test your recipe to ensure workflow compatibility with your genie.
Click Save
# Add skills
You can create skills to define workflows for your genie to use. This provides your genie with different skills, such as starting a workflow or returning a response. You can't clone recipes from one skill set to another skill set.
Complete the following steps to add a skill recipe to your genie:
Click Skills in the sidebar navigation.
Click Create skill recipe.
Click Create skill recipe
Provide a name for your skill recipe in the Name field.
Click Start building. The recipe editor opens with the Start workflow trigger and Return response action automatically selected.
Click Start building
Provide a description for your skill workflow in the Description field. The genie uses this description to decide when to trigger this workflow.
Go to the Parameters schema section and click Use JSON or Add fields manually to provide a description of the schema recipe parameters.
Click Use JSON.
Paste the JSON schema you plan to use into the JSON sample field and then click Next.
Paste your JSON schema into the JSON sample field
Review the sample JSON tree and then click Generate schema.
Go to the Result schema section and click Use JSON or Add fields manually to provide a description for the recipe return value.
DEFINES THE RETURN RESPONSE GENIE STEP
The Result schema section defines the RETURN
response for the genie step at the end of your recipe.
Click Use JSON.
Paste the JSON schema you plan to use into the JSON sample field and then click Next.
Paste your JSON schema into the JSON sample field
Review the sample JSON tree and then click Generate schema.
Click + Add action to add an action step to your recipe.
Test your recipe to ensure workflow compatibility with your genie.
Click Save.
# Create an app connection
App connections must be unique for each genie. This means that you can't use the same connection for multiple genies.
COMMUNITY CONNECTORS NOT SUPPORTED
You can’t create or install community connectors for use with a genie.
Complete the following steps to create a connection:
Go to the genie where you plan to add a connection.
Click Connections in the navigation sidebar.
Click Create connection.
Click Create connection
Search for and select the app you plan to use in the New Connection page.
Provide a name for your connection in the Name field.
Use the Location drop-down menu to select the project where you plan to store the connection.
Provide information for all required app connection fields. Note that connection configuration fields vary based on the app you select.
Click Connect.
Last updated: 3/27/2025, 2:51:16 PM