AI Agent Studio
Follow the role, mission, dataset, skills, and output steps to create a custom agent.
Start a new agent
Open More.. → Super Admin → AI Agent Studio, then select the AI Agent Studio creation card. The guided flow shows your choices in Your pipeline. Available options depend on your permissions and deployment.
Choose a role and mission
Role sets the agent’s intended expertise and working style. Examples include Researcher, Learning Coach, Customer Support, and L&D Designer. Choose the role closest to the task, then continue.
Mission tells the agent what to accomplish. Describe the audience, task, expected result, and how it should use the source material. You can write a mission or choose Saved prompts from the prompt library.
The optional Mentor with Memory role is available only in installations configured for it. Talvi works with your team to develop a Markdown journey document describing the process and guidance the agent should follow. Selecting this role reveals Mentor journey document in the Mission area: upload the agreed file or paste its Markdown, review the text, then finish the remaining setup and save the agent. A journey document is required for this role. See Mentor with Memory for examples, upload instructions, and later updates.
Select a dataset
Choose the knowledge collection in Dataset, then select Use dataset. Confirm its name in Your pipeline before continuing. If it is missing, first create or upload the dataset.
Add optional skills
When enabled, Skills lists active MCP servers the agent can use. Select View tools to inspect a server before adding it. The interface shows the selection count and limit; the current flow supports up to four servers.
Select Skip this step when no additional tools are needed. A skill’s usefulness depends on its connection and enabled tools; adding a server with no usable tools does not provide working actions. See MCP Tool Store.
Choose an output and save
Output determines where people will use the agent. Depending on your permissions, the choices can include Talvi AI Agent, Talvi Embeddable AI Bot, Slack app, and Microsoft Teams app.
Complete any output-specific details, review the pipeline, and select Save AI Agent. Use a clear name so administrators and users can identify it. After saving, open its detail page to check the mission, audience, and connection details.
Selecting an output alone does not complete the external Slack or Teams installation. Those connections require their corresponding app setup and credentials.
Configure a Talvi Embeddable AI Bot
When you choose Talvi Embeddable AI Bot as the output, complete the website configuration before saving the agent:
- Select Create embeddable bot credentials in the output details.
- Set Widget title, Widget subtitle, Theme (Light or Dark), and Welcome message. These introduce the assistant to website visitors.
- Enter Allowed origins, one website origin per line. Include the scheme and hostname, plus a port when required; do not include a page path. Add each intended site variant separately, such as your main site and its
wwwhostname. - Select Save in the configuration dialog to create the public embed credentials. The output details now provide an HTML snippet for the bot.
- Complete Save AI Agent. Choosing the output or creating credentials alone does not finish saving the agent.
The Studio requires embedded credentials before it can save this output type. The generated snippet uses the bot’s publishable key, which is intended for the website widget; do not substitute an MCP access key or a private integration credential.
After saving, open the agent’s View Config to adjust its logo, welcome message, allowed origins, and initial appearance. Closed starts with the chat icon; Open shows the text input. Select Save Config to apply those changes.
Follow Add your Talvi AI bot to your website to install the generated snippet and test it. For optional links and buttons, see Custom CTA Actions.
