Tips & Best Practices

​

Keyboard Shortcuts

Master these shortcuts to build flows faster:

​

Flow Builder Tips

​

Validate Flows with Variables

Before publishing your flow, validate it using variables to ensure all paths work correctly:

1. Open the flow in preview mode
2. Test different conversation paths
3. Verify that variables are captured and used correctly
4. Check conditional logic with various inputs

​

Multi-Select Entities

Speed up your editing by selecting multiple entities at once:

• Hold Ctrl while clicking entities to select multiple
• Move, delete, or modify properties of multiple entities together
• Useful for reorganizing large sections of your flow

​

Working with Images in Entities

The entity editor isn’t just for text - you can create rich visual experiences:

• Add images to enhance visual appeal
• Combine text and images for better engagement
• Use images to illustrate complex financial concepts
• Leverage the image generation capabilities in chat settings

​

Chat Settings

The chat settings panel is crucial for customizing your assistant’s behavior. Access it to: Adjust AI Assistant Behavior

• Configure response style and tone
• Set knowledge boundaries
• Control verbosity and detail level

Configure Image Generation

• Enable/disable AI image generation
• Set image style preferences
• Control when images are generated

Other Important Settings

• Response formatting options
• Context window management
• Model selection (coming soon)

​

General Usage Tips

​

Managing AI Assistant Output

If the assistant creates too much content or goes into a loop:

• Ask it to limit the number of questions
• Specify exactly what you want (e.g., “create only 3 questions”)
• Use the enhance prompt feature (Ctrl + E) to add constraints

​

Request Custom Features

Need specific functionality for your business? Custom Entities and Components

• Request specialized components for your use case
• We can create custom entities tailored to your institution
• Examples: Live PDF signatures, specialized calculators, custom visualizations

Integration Support

• Connect to your internal systems
• Custom API integrations
• Specialized triggers and actions

Contact our team to discuss your requirements - we provide customization for tenant-specific needs.

​

Support

​

We’re Here to Help

Support Availability

• Contact our team for implementation questions
• Get help with complex flow design
• Request feature consultations

What We Provide

• Implementation support
• Custom component development
• Tenant-specific customization
• Integration assistance

---

​

Wizflow Assistant Training Lab

​

Assistant Feedbacks

​

What It Does

Collects user feedback on AI assistant responses to improve our wizflow assistant user experience. Key Benefits:

• Captures user satisfaction and detailed issues
• Creates training datasets for model improvement
• Provides insights into assistant performance
• Measure User Satisfaction

​

Feedback rating footer - how users give feedback

After generation completes, users see thumbs up/down buttons:

• 👍 Thumbs Up: Good response, no further action needed
• 👎 Thumbs Down: Opens detailed feedback form, allow user to specify what went wrong with generation.

​

Feedback browser and editor

Only users with elevated permissions can view the training lab.

View all collected feedbacks in training lab tables.

​

Feedback table

Shows all collected feedback with:

• User prompts and comments
• Rating (Satisfactory/Unsatisfactory)
• Issue tags
• Attachment count
• Review status
• Actions (View | Delete)

​

Feedback editor

Each feedback has three states accessible at feedback editor, which can easily accessed from feedback table action column

Feedback states

https://github.com/user-attachments/assets/e5c87799-9a86-457a-9a65-53e9010d4318

• Original: Template before AI changes
• Generated: AI-modified template
• Ideal: Corrected response (created by reviewers)

Overall collection and dataset generation process

1. Users submit feedback
2. Internal reviewers create “Ideal” responses
3. Export script generates training datasets
4. Data used for SFT and DPO training

​

Technical Overview

​

Data storage

All feedback stored in ChatflowAssistantFeedback table including:

• Complete template states
• User context and attachments
• Ratings and comments
• Issue categorization

​

Fine-tuning

• SFT (Supervised Fine-Tuning): Transform feedbacks collected into single use samples
• DPO (Direct Preference Optimization): Use rating to create dataaset consisting of preferred and non-preffered output for a user prompt. This is a different kind of optimisation that helps in improving model accuracy by comparison.

​

Key features

• Optional feedback submission
• Binary rating system
• Predefined issue tags (user-assigned)
• Role-based access control
• Automated export functionality via script

​

Security & Privacy

• Anonymous feedback collection
• Permission-based training lab access
• No personal user data captured
• Secure training data exports

---

​

Next Steps