Roboflow + Slack
Post a Slack message, with the annotated image attached, whenever a Roboflow Workflow finds something, using the Slack Notification block.
How to connect Slack to Roboflow
5 stepsCreate a Slack app
At api.slack.com/apps, create an app from scratch and add the chat:write bot scope, plus files:write to send images.
Install the app and copy the token
Install the app to your workspace and copy the bot token that starts with xoxb-.
Add the app to your channel
Add the app from the channel's integrations, then copy the channel ID from the channel details.
Add the Slack Notification block
In your Workflow, add the block and enter the token and channel ID. Store the token as a secret input.
Write the message and set when it sends
Write the message with placeholders such as {{ $parameters.count }}, map them to your results, and add a Continue If block before it to set the condition.
What teams build with Slack
Alert the line when a defect appears
Post the defect class and an annotated image to the quality channel.
Flag low stock on a shelf
Send a message when a count drops below your threshold.
Share counts with the team
Post the number of items detected in each run so the team sees it without opening a dashboard.
Questions
Yes. Add visualization blocks to draw the boxes and labels, then attach that output to the message. The token needs files:write.
Set a cooldown in seconds between messages, 5 by default, and add a Continue If block so messages go out only when your condition is met.
Yes. Set Fire and Forget to False while testing, so the Workflow waits and shows whether the message sent.
Why are companies choosing Roboflow?
The end-to-end platform for vision AI: create datasets, train models and deploy to production.
Flexible deployment modes
Move from a scalable cloud API to edge hardware like NVIDIA Jetson without managing complex dependencies.
Integrated workflow builder
Combine multiple AI models, custom business logic and third-party integrations into one production-ready pipeline in a low-code editor.
Model monitoring and alerts
Dashboards track confidence, inference time and request volume for your deployed models, and email alerts tell your team when confidence suddenly drops.
