How to create an app using Agent Crew

After selecting Agent Crew as your orchestration method on the App Details page, click the ‘Next’ button at the bottom right corner to proceed. This will direct you to the Configure Bot page, where you can seamlessly integrate your selected Agent Crew and fine-tune your bot’s settings.

Configure Bot

In this section, you can fine-tune and personalize your bot’s settings by integrating the chosen orchestration method and configuring essential parameters to meet your unique business needs. These adjustments ensure smooth bot operation within your workflow, offering a streamlined, personalized, and outcome-focused experience.

Steps to configure the bot:

Select the Agent Crew

How to add the Agent Crew:

• Click ‘Add’ to open the crew selection dialog.

• Choose an existing Agent Crew from the list to start building a ZBrain AI app.

• Upon selection, the Agent Crew will be added, providing clear visibility into the crew’s name and the last updated timestamp. Once selected, you can delete selected agent crews before finalizing app setup via an intuitive “DELETE” icon.

Add guardrails

Upon selecting a relevant Agent Crew, you can add guardrails.

Add guardrails to ensure your app behaves safely, accurately, and within defined boundaries. Guardrails are configurable safety mechanisms that monitor and control inputs, outputs, and behavior to prevent harmful, inappropriate, or off-policy responses.

How to add guardrails:

• Click ‘＋ Add Guardrails’.

• A right-hand side panel titled Add Guardrail Parameter appears.

Toggle on any options:

• Input Checking – screens every user prompt for policy violations (jailbreak detection, hate speech, self-harm, and disallowed content) and blocks or sanitizes the request/response.

  • You can enable Input Checking to activate content-moderation filters, sexual content, harassment, hate, and dangerous content. Each filter is adjustable with intuitive slider controls, giving users precise control over moderation thresholds.

    Each category can be tuned using a three-level slider:

    • Block None – No filtering applied. All content is allowed.

    • Block Few – Minimal filtering applied. Only severe or explicit cases are blocked.

    • Block Most – Strict filtering applied. Most flagged content is blocked.

Jailbreak Detection – looks for prompt-injection patterns that try to override your system instructions and blocks or sanitizes the request/response.

• You can find the following jailbreak categories for more granular control and security oversight. You can select each category for Jailbreak Detection filtering based on your requirements:

  • System Override

  • Code Injection

  • PII Access

• Output Checking - ensures that your AI application's responses are factual, safe, and aligned with your knowledge base. This feature is particularly useful in retrieval-augmented generation (RAG) setups, where validating both the factual fidelity and safety of LLM outputs is essential. Output Checking evaluates model responses for the following risks:

  • Misinformation

  • System Prompt Leakage

• Hallucination Detection -This feature automatically validates AI-generated outputs against the linked Knowledge Base to detect factual inconsistencies or unsupported claims. If hallucination is detected, the app returns a fallback message, ensuring that only accurate, trusted responses are delivered. The following risks are evaluated through Hallucination Detection:

  • Irrelevant Content

  • Extra Speculation

Once guardrails are enabled, they appear in the main panel with a lock icon, indicating that they are active. You can reopen the panel at any time to disable or re-enable them.

Note: The ‘＋ Add a guardrail parameter’ button remains available so you can attach future guardrail types as they become available in ZBrain.

Once guardrails are added, click 'Next' to proceed to the Appearance page, where you will customize the visual and user interface elements of your app.

• You can customize the visual and interactive aspects of your app by configuring the following:

  • Welcome message: Add a welcome message that users will see when they first access the app.

  • App name and description: Provide a name and a brief description of your app.

  • Sample questions: Add up to nine sample questions to guide users on how to interact with the bot. You can also generate these questions automatically.

  • Upload logo and app theme: Enhance your app’s branding by uploading a logo and selecting a theme.

  • Bot name and icons: Customize the bot's name and icons to match your app’s branding.

• After clicking ‘Done,’ your app will be created, and you'll be directed to an overview page to manage various aspects of your application. Alternatively, click ‘I will do later’ to set the appearance at a later time.