AI Copilot

Using the AI Copilot

The AI Copilot is a chat-based interface located in the right sidebar of your Flow Editor. It helps you build and maintain flows, and once you enter a prompt, it provides rich answers in formats such as text, flow snippets, code snippets, tables, images, and diagrams.

The AI Copilot is designed to assist you with the following actions:

• Creating Flows
  Describe what you need, and the AI Copilot will generate a new flow by selecting the best nodes, writing code for function nodes, and integrating community and qibb nodes to jump-start your project. Import your optimized flow to the Flow App with a single click.

• Editing Flows
  Easily update your existing flows using conversational commands. the AI Copilot helps you refine your flows, making them more organized, resilient, and secure. Changes can be applied to the flow directly from buttons integrated into the AI Copilot conversation.

• Troubleshooting & Debugging
  The AI Copilot delivers suggestions which are informed by the contextual data available in the logs and run history.

• Explaining Flows in Text and Diagrams
  Receive clear, detailed descriptions and step-by-step breakdowns of your flows to boost understanding and speed up onboarding.

• Answering Questions & Helping with Best Practices
  the AI Copilot provides step-by-step flow solutions and instructions based on qibb’s product documentation, helping users enhance flows and deepen their understanding of qibb.

FAQ

When will the AI Copilot become available?

qibb’s AI Copilot is now live in the demo environment and will be gradually rolled out to all existing customers. The rollout will commence in our SaaS environments and subsequently extend to our dedicated PaaS environments in June and July. Please note that the availability of this feature may vary based on individual account configurations and technical considerations.

Which Subscription Tier includes this feature?

This feature is available for all subscription tiers at no extra cost, although usage limits will vary depending on your subscription level.

How reliable are the suggestions provided by the AI Copilot?

Our AI Copilot leverages advanced large language models to generate suggestions designed to help you build and optimize your workflows.

However, there are limitations and it's important to review each response carefully before implementation. Some key points to consider:

• Context Matters: The quality of suggestions depends heavily on the clarity and context of your input.

• Manual Adjustments: the AI Copilot provides a strong starting point, however additional manual configuration of nodes may be required.

• Occasional Inaccuracies: Like any AI system, the AI Copilot may sometimes produce outputs that do not fully match your intent—these are often referred to as "hallucinations."

• Verification Recommended: We advise verifying critical details and treating the outputs as a helpful guide rather than definitive answers.

• Feature Limitations: Note that certain features and actions may have limitations. Please refer to the comprehensive list of current feature limitations.

We are always working to make the AI Copilot better and more accurate, and we'll keep updating it regularly.

How can I improve the accuracy of the AI Copilot's responses?

To enhance the precision and relevance of the AI Copilot’s output, consider the following tips:

• Be Specific: Provide clear, detailed, and specific instructions in your prompt. Incorporate relevant context or examples to help the AI Copilot better understand your requirements.

• Iterative Refinement: Request minor changes or flow segments step by step, following an iterative approach.

• Focus the Scope: Toggle different data sources to help the AI Copilot focus on the most relevant information.

Tip: Use Comment Nodes for Copilot Guidance

Insert comment nodes in your flow to add extra documentation for the AI Copilot. For instance, you can include extra system instructions or set a style guide for the AI Copilot on each flow tab. This information will be utilized as long as you share the deployed flow for context.

Can I bring my own AI Provider Account?

Currently, this feature does not support the use of a custom or third-party AI provider account.

Which AI model is used?

We currently utilize multiple large language models (LLMs), including those provided by OpenAI, to power the AI Copilot.

Is my data safe when using the AI Copilot?

the AI Copilot only accesses data that you have explicitly allowed, and sensitive information is never stored or used for training. You remain in full control of your data at all times.

What data sources is the AI Copilot accessing?

The AI Copilot can access a variety of data sources on-demand, as well as the qibb Knowledge Base. Users have full control over which of their data are available during a session.

Data sources include:

• qibb Knowledge Base

  • Nodes from qibb’s Catalog

  • Flow Templates from qibb’s Catalog

  • qibb’s Public Documentation

• Flow Resources

  • Flows: Auto share mode provides the flow selection or current flow tab. Users also have the option to share all flow tabs.

  • Context Data: When you share context data keys, the AI Copilot can integrate your defined flow and global context variables in a generated flow. Only the variable names are accessed – values remain confidential. Include a Secret Manager node in your flow to fully optimize this feature.

• Platform Monitoring Data

  • Logs & Run History: Logs and run history related to the flow from the last 30 minutes.

What diagram formats can be generated?

In addition to a Flow Diagram in qibb’s familiar flow app format, the AI Copilot can generate visualizations in several formats based on your prompts. This includes diagrams for flow logic and other specific data needs.

Supported formats include (but are not limited to):

• Sequence Diagram

• Flowchart Diagram

• Class Diagram

• State Diagram

• Pie Chart Diagram

Can I restrict access to the AI Copilot for my users?

Yes, you can control access using a feature toggle available at the app level during deployment or upgrade procedures initiated from the Portal. If the feature is enabled, users with the Edit or View app roles will have access to the AI Copilot in the Flow Editor.

Current Limitations

Some features and actions in the AI Copilot have known limitations. We're working to improve the product and value your feedback. Please review the current limitations below:

General AI Limitations

• The accuracy and quality of outputs depend on various factors, and results may vary.

• Always review generated flows and code before implementing them. For additional tips on improving outcomes, please refer to the AI Copilot FAQ on this page.

No Web Search

• The AI Copilot currently does not access any external web resources or offer web search functionality. Please include all necessary information directly in the chat.

Chat History

• To protect your privacy, chat history is not saved and will be discarded if you clear the conversation, refresh your browser or restart the Flow App.

Manual Node Installation

• The AI Copilot does not automatically install missing nodes. You will need to install them manually. Please refer to our documentation for guidance:

  • Installing nodes from the qibb catalog

  • Installing nodes from the Node-RED community

Node Properties Configuration and Data Mapping

• Some node configurations may not always be considered or applied by the AI Copilot. This can be applicable for error handling, input/output mapping, security fields for API Nodes and Authentication Nodes.

• Occasionally, nodes generated from qibb’s catalog may have incorrect operation selections or parameter configurations that do not match the node schema; in such cases, invalid settings are either ignored or appear empty when you open the node properties.

• Occasionally, data mapping between nodes is not implemented correctly, causing generated nodes to reference default variable paths (such as msg.payload) even when an alternative variable path is desired. Review variables accordingly to match your desired mapping.

Working with Flows

• the AI Copilot may not generate or interpret subflows correctly. We recommend creating flows at a flat level with the AI Copilot and then manually wrapping the logic into subflows afterward.

Working with JSONata Expressions

• JSONata expressions generated by the AI Copilot may occasionally contain syntax errors, especially within the body payloads or request parameters of API nodes from qibb’s Node Catalog.

Working with Function Nodes

• The “Import” syntax for external modules may not be correctly generated within a function node. Please refer to How to use external modules in a function node for guidance.

These limitations are part of our ongoing efforts to improve the product. For future updates, check the release notes of Flow Releases and Platform Releases.