Roboflow Docs
DashboardResourcesProducts
  • Product Documentation
  • Developer Reference
  • Changelog
  • Roboflow Documentation
  • Quickstart
  • Workspaces
    • Workspaces, Projects, and Models
    • Create a Workspace
    • Manage Team Members
    • Role-Based Access Control
    • Usage Based Pricing
      • View Plan Usage
      • Purchase Pre-Paid Credits
      • Flex Credit Billing
    • Rename a Workspace
    • Delete a Workspace
  • Workflows
    • What is Workflows?
    • Create a Workflow
    • Build a Workflow
    • Test a Workflow
    • Deploy a Workflow
    • Workflow Examples
      • Multimodal Model Workflow
    • Share a Workflow
    • Workflows AI Assistant
  • Dataset Management
    • Create a Project
    • Upload Images, Videos, and Annotations
      • Import Data from Cloud Providers
        • AWS S3 Bucket
        • Azure Blob Storage
        • Google Cloud Storage
      • Import from Roboflow Universe
    • Manage Datasets
      • Dataset Batches
      • Search a Dataset
      • Set Dataset Classes
      • Add Tags to Images
      • Create an Annotation Attribute
      • Download an Image
      • Delete an Image
    • Dataset Versions
      • Create a Dataset Version
      • Preprocess Images
      • Augment Images
      • Delete a Version
      • Export a Dataset Version
    • Dataset Analytics
    • Merge Projects
    • Rename a Project
    • Delete a Project
    • Project Folders
    • Make a Project Public
  • Annotate
    • Introduction to Roboflow Annotate
    • Annotate an Image
      • Keyboard Shortcuts
      • Comment on an Image
      • Annotation History
      • Similarity Search
    • AI Labeling
      • Label Assist
      • Enhanced Smart Polygon with SAM
        • Smart Polygon (Legacy)
      • Box Prompting
      • Auto Label
    • Set Keypoint Skeletons
    • Annotate Keypoints
    • Annotate Multimodal Data
    • Collaborate on Annotations
    • Annotation Insights
  • Managed Labeling
  • Train
    • Train a Model
      • Train from a Universe Checkpoint
      • Train from Azure Vision
      • Train from Google Cloud
    • Roboflow Instant
    • Cancel a Training Job
    • Stop Training Early
    • View Training Results
    • View Trained Models
    • Evaluate Trained Models
  • Download a Dataset Version
  • Deploy
    • Deploy a Model or Workflow
    • Managed Deployments
    • Serverless Hosted API V2
      • Use in a Workflow
      • Use with the REST API
      • Run an Instant Model
    • Serverless Hosted API
      • Object Detection
      • Classification
      • Instance Segmentation
        • Semantic Segmentation
      • Keypoint Detection
      • Foundation Models
        • CLIP
        • OCR
        • YOLO-World
      • Video Inference
        • Use a Fine-Tuned Model
        • Use CLIP
        • Use Gaze Detection
        • API Reference
        • Video Inference JSON Output Format
      • Pre-Trained Model APIs
        • Blur People API
        • OCR API
        • Logistics API
        • Image Tagging API
        • People Detection API
        • Fish Detection API
        • Bird Detection API
        • PPE Detection API
        • Barcode Detection API
        • License Plate Detection API
        • Ceramic Defect Detection API
        • Metal Defect Detection API
    • Dedicated Deployments
      • Create a Dedicated Deployment
      • Make Requests to a Dedicated Deployment
      • Manage Dedicated Deployments with an API
    • Batch Processing
    • SDKs
      • Python inference-sdk
      • Web Browser
        • inferencejs Reference
        • inferencejs Requirements
      • Lens Studio
        • Changelog - Lens Studio
      • Luxonis OAK
    • Upload Custom Model Weights
    • Download Model Weights
    • Enterprise Deployment
      • License Server
      • Offline Mode
      • Kubernetes
      • Docker Compose
    • Monitor Deployed Models
      • Alerting
  • Universe
    • What is Roboflow Universe?
    • Find a Dataset on Universe
    • Explore Images in a Universe Dataset
    • Fork a Universe Dataset
    • Find a Model on Universe
    • Download a Universe Dataset
  • Set a Project Description
  • View Project Analytics
  • Support
    • Share a Workspace with Support
    • Delete Your Roboflow Account
    • Apply for Academic Credits
Powered by GitBook
On this page

Was this helpful?

  1. Workflows

Workflows AI Assistant

Use the Workflows AI Assistant to help build and debug Workflows.

PreviousShare a WorkflowNextCreate a Project

Last updated 1 day ago

Was this helpful?

The Workflows AI Assistant lets you build, update, and debug Workflows from a chat interface.

The Workflows AI Assistant can answer questions about an existing Workflow, make changes based on the goal you have for your project, and fix errors in your Workflow if you encounter one.

To use the Workflows AI Assistant, click the sparkle icon on the left side of the Workflows editing window:

The AI Assistant will open as a sidebar in your Workflows editor:

You can then start to ask questions in the chat interface.

Editing Workflows

You can ask the Workflows AI Assistant to make changes to your Workflow.

For example, you could ask to:

  • Add object tracking to a Workflow.

  • Make your current Workflow run only if a classification model returns a certain result.

  • Change the confidence threshold of a model used in a Workflow.

When you do, the AI Assistant will make changes, then ask whether you want to save them to your Workflow or revert the changes.

Changes are not saved to your production Workflow until you save changes.

Here is an example of a Workflow where a CSV block was added after asking the Assistant to save records to a CSV file:

Of note, the block may not be configured when added. In this example, the CSV Formatter is created and connected to the relevant block — the one that returns tracked predictions — but does not save any results. You can click into any blocks created by the Workflows AI Assistant to make the necessary configurations according to your project needs.

Example showing the results for the question "How do I save predictions to a CSV?", with the Assistant creating a plan to save detections to a CSV file.