Introducing Agentic Object Detection! Given a text prompt like “unripe strawberries” or “Kellogg’s branded cereal” and an image, we use an agentic workflow to reason at length and detect the specified objects. No need to label any training data. Watch the video for details.

You can also play with the demo here:

Looking to automate reporting? Use AI agents to turn spreadsheets to reports in minutes without any coding.

Agentic workflows for computer vision makes so much sense

Agentic Object Detection sounds fascinating. The ability to reason without labeled data is a game changer. Imagine applying this to educational tools to enhance learning experiences, making AI-powered learning more intuitive. Keep pushing the boundaries of innovation.

Have you tested this against more complex scenarios like partially occluded objects or under varied lighting conditions? Really curious about edge cases and performance degradation patterns.

Super cool! This has lots of applications!

i asked it to detect rectangle in batsman picture and it cant find it.

and also, what's #23 wearing? isnt it a hat?

That's fascinating! Using agentic workflows to detect objects without labeled data could revolutionize how we approach image recognition tasks. How do you think this technology could be adapted for real-time applications like autonomous vehicles?

Its amazing

Thanks!