You can choose between two types:
- Web Co-Browsing AI Agent: Ideal for in-browser guidance across SaaS platforms or websites.
- Desktop Co-Browsing AI Agent: Tailored for desktop-based applications and automations, equivalent to Robotic Process Automation (RPA) with powerful show-and-tell features.
Step-by-step: Creating a Co-Browsing AI Agent
1. Navigate to AI Agent Creation
- From the Supervity dashboard, click on the “Create AI Agent” button on the left sidebar.
2. Choose Co-Browsing AI Agent
- You’ll see different AI agent templates.
- Select “Co-Browsing AI Agent” from the list.
3. Select Web or Desktop Agent
- Choose either:
- Web Co-Browsing AI Agent — for websites or web apps
- Create and share in-app walkthrough AI agents for your organizational web applications to digitally enable your employees, customers, and suppliers. AI Coach can also be connected with a collection of knowledge to answer user queries in natural language.
- Desktop Co-Browsing AI Agent — for desktop apps or RPA-style interactions
- Desktop Co-browsing AI Agent can enable teams to automate repetitive digital tasks on your desktop. Use simple no-code show and tell interface to create and share automations for self or the team. This is equalent to Robotic Process Automation with all powerful desktop automation features.
- Web Co-Browsing AI Agent — for websites or web apps
4. Enter Agent Details
- Fill in your Agent Name and Description.
- Click Next to proceed.
5. Build the Walkthrough
- You’ll be taken to the visual builder.
- Click the ➕ buttons to add steps in your flow.
- While building your walkthrough, each step can either:
- Add a Skill from your existing skill collections,
- Or Record your screen, where your actions are automatically captured and inserted as steps.
These recorded steps can later be reused as automations — making your co-browsing agent both instructional and functional.
6. Finalize and Publish
- Use the top options to Play, Save, Export, or Publish your co-browsing agent.
- Once published, the walkthrough can be triggered for users within your product.