Create Your First AI Coworker
1. Log in to Wexa Studio#
Open the platform at https://app.wexa.ai and navigate to the main dashboard. After logging in, you can use the SDK to programmatically interact with your coworkers.In Wexa Studio, look for a dropdown menu or sidebar in the top-left corner of the interface (e.g., near your profile name or labeled "Manage Your Coworkers").3. Select Create New Coworker#
Click on "Create New Coworker" for adding a new team member.Using the SDK to Create a Coworker:4. Fill in Coworker Details#
Name: Enter the coworker's full name (e.g., Mike)
Role: Select or type their role (e.g., DevOps Coworker)
Description: Provide a brief overview of their responsibilities
5. Create Your First Process Flow#
Once done, visit the Process Flows section to create your first process flow.Process Flows are workflows designed to accomplish specific tasks within a coworker. These flows are step-by-step sequences where multiple AI agents work together seamlessly to get a job done. At Wexa, Process Flows are modular, reusable, and optimized for collaboration between humans and AI.Using the SDK to Create Process Flows:Process flows are created as part of AgentFlow configuration. You can add agents to your coworker to build process flows:Process Flow Configuration:Process Flow Name: Give your process flow a unique, descriptive name (e.g., "Interview Scheduler", "Resume Ranker")
Role: Describe what the flow does in your team context (e.g., "Interview Assistant", "Candidate Tracker")
Description: Write a short summary explaining what the process flow will do and how it helps the team (max 500 characters)
Creating Your First Agent#
Agents are the core components of your coworker in Wexa. Each agent performs a specific task to streamline your workflow. Here's how to create agents using the SDK:Step-by-Step Guide to Creating an Agent#
1. Agent Type#
Skilled Agent: Performs specialized actions based on assigned skills (e.g., sending emails, fetching data)
Decision Agent: Makes branching choices based on outcomes or input values
Title: Name your agent (e.g., "Data Validator", "Meeting Scheduler")
Role: Explain what the agent does (e.g., "Processes raw lead data into qualified contacts")
Description: Expand on how the agent fits into the workflow and what it handles
2. Task#
Tasks are clear, detailed instructions that guide your agent step-by-step. Each Task should specify:What the agent needs to do
{{variable_name}} to reference or create variables dynamically within a task.3. Actions#
In Wexa Studio, Actions empower AI agents to perform tasks by defining how they interact with applications and data. Actions consist of two key components: Skills and Tables.Skills enable AI agents to perform specific operations by connecting with your existing business applications—without the need for custom development.Automate routine tasks like sending emails, creating tickets, updating records
Leverage the Connectors Marketplace to quickly integrate with popular tools
Request custom integrations for specialized connections
Store and manage data such as customer records, order details, product inventory
Enable agents to filter, extract, or update entries based on defined logic
Make decisions grounded in data
4. Triggers#
Triggers are events that will initiate the agent's workflow. You can add multiple triggers to your coworker for varied responses to different situations. Triggers automate the next steps. When a task is finished, they automatically start the following task, creating a seamless workflow.Configuring Triggers with SDK:Triggers are configured when creating tables or updating AgentFlows:1.
Define a Trigger: Name your trigger (e.g., "Trigger 1") to distinguish it within your automation setup
2.
Select a Process Flow: Choose from the list of available process flows
3.
Execution: Once the trigger condition is met, the selected process flow kicks off immediately—without manual intervention
5. Knowledge Base#
The Knowledge Base in Wexa Studio stores critical information and supports a variety of files such as PDFs, PPTs, Docs, and more. AI agents can refer to these documents while performing tasks such as answering queries, providing customer support, or making decisions.Uploading Files to Knowledge Base with SDK:6. Advanced Settings#
6.1 LLM Model ConfigurationSelect an LLM (e.g., GPT-4, Claude, Gemini) aligned with your task (creativity, accuracy, speed). Balance model size, cost, and latency.Configuring LLM with SDK:Set token limits to control response length, balancing conciseness and depth (e.g., 200-500 tokens). Higher limits suit detailed tasks but risk inefficiency; lower limits enforce brevity.Wexa integrates human oversight seamlessly into automated workflows for compliance, risk management, or strategic decisions.Auto Approve: Agent runs tasks automatically
Ask for Approval: User must approve each action—useful for sensitive tasks
7. Creating Multi-Step Workflows#
You can create multiple agents within a single coworker, essentially building a multi-step workflow. Each agent acts as a step in the process, leveraging its assigned skills (connector permissions) to perform specific tasks. By linking these agents together with triggers, you can design complex automation sequences.Building Multi-Step Workflow with SDK:8. Completing Your Coworker#
Once you've finished defining and configuring all the necessary agents within your coworker, submit the form to finalize its creation.Finalizing Coworker with SDK:With your coworker built and deployed, you're now equipped to automate specific tasks or processes within your workflow. Remember, coworkers can be designed for various functions, and the specific configuration steps might vary depending on the desired functionality.Modified at 2026-01-02 09:44:55
