> ## Content Index > Fetch the complete content index at: https://blog.unitlab.ai/llms.txt > Use this file to discover other available public pages before exploring further. # Unitlab AI Automation Workflow with a Demo Project - URL: https://blog.unitlab.ai/unitlab-ai-automation-workflow/ - Published: 2025-04-08T10:31:12.000Z - Updated: 2026-08-18T22:15:43.000Z - Description: Feature Release: Unitlab Automation Workflow with a demo project. - Author: Hojiakbar Barotov - Tags: News, Data Annotation, ML, AI, Data Annotation Tools ## Current Unitlab platform This article preserves its original educational or historical topic. Unitlab AI is now an enterprise multimodal data platform for curating, annotating, managing, versioning, reviewing, and preparing image, video, audio, text, document, medical, pathology, and geospatial training data. Interface screenshots below may reflect the product version available when the article was published. ![Current Unitlab AI multimodal data annotation platform](https://storage.ghost.io/c/48/f4/48f4b614-5c29-430d-9cb3-e0b3f34395f3/content/images/2026/08/unitlab-current-multimodal-platform.webp) Current Unitlab AI multimodal annotation workspace. [Explore the current multimodal platform](https://unitlab.ai/en/multimodal-annotation?ref=blog.unitlab.ai) or follow the [end-to-end quickstart](https://docs.unitlab.ai/documentation/get-started/end-to-end-quickstart?ref=blog.unitlab.ai). *Note: This is a simplified, quick version of our project creation docs. For full information, refer to this page*: [Automation Workflow | DocumentationRun automated workflows within Unitlab AI![](https://storage.ghost.io/c/48/f4/48f4b614-5c29-430d-9cb3-e0b3f34395f3/content/images/icon/image-5)Documentation![](https://storage.ghost.io/c/48/f4/48f4b614-5c29-430d-9cb3-e0b3f34395f3/content/images/thumbnail/image-5)](https://docs.unitlab.ai/automation-workflow/automation-workflow?ref=blog.unitlab.ai) Automation Workflow | Unitlab AI At Unitlab AI, we strongly emphasize the intersection of human expertise and machine intelligence in data annotation. [We believe](https://blog.unitlab.ai/how-unitlab-ai-aims-to-transform-data-annotation/) AI should empower people, not replace them. Therefore, we've developed an AI-powered data annotation platform enabling human annotators to be 10x more productive through advanced auto-annotation tools. This commitment is why Unitlab AI provides built-in foundational AI models and supports [AI model integration](https://docs.unitlab.ai/ai-models/model-integration?ref=blog.unitlab.ai). Coupled with human oversight, these automated annotation tools produce datasets that are more accurate, faster, and better quality than manual or AI-only methods. ![Unitlab AI strikes a golden balance between man and machine](https://storage.ghost.io/c/48/f4/48f4b614-5c29-430d-9cb3-e0b3f34395f3/content/images/2026/01/unitlab-4.png) Unitlab AI strikes a golden balance between man and machine Previously, each project on our platform was limited to using just one AI model. While this approach is straightforward, it's often insufficient for complex real-world annotation tasks. For instance, labeling images from a fashion show might require separate auto-annotation models: F*ashion Segmentation* for clothing, *Person Detection* for identifying individuals, and *Image OCR* to recognize brand text. Clearly, a single-model limitation doesn't fit such scenarios. To address this, we are introducing our latest feature: **Unitlab Workflows**. ## Unitlab Workflows This new feature enables you to integrate multiple AI models within a single project. For complex annotation tasks requiring different labeling types (such as *instance segmentation*, *bounding boxes*, and *image OCR)* you can now use multiple AI models simultaneously. When running automated annotation tasks like *Crop Auto-annotation* or *Batch Auto-annotation*, the system applies **all** the models specified in your workflow automatically. Watch this demo video to see workflows in auction: 0:00 /1:14 1× Unitlab AI Automation Workflow Unitlab AI also lets you [incorporate your own custom AI](https://blog.unitlab.ai/yolov8-human-segmentation/) models into these automation workflows, offering extensive flexibility and customization while remaining user-friendly. Workflows truly enhance the hybrid approach of combining human labeling with AI automation. Let's set up a demo project to see this in action. ## Demo Project If you do not already have a Unitlab account, [create a free account](https://app.unitlab.ai/?ref=blog.unitlab.ai) in under 5 minutes to follow along the tutorial: [Create Account](https://app.unitlab.ai/login?ref=blog.unitlab.ai) ### Project Setup In our demo project, we'll create a project to *detect* *people* and *segment clothing*, requiring two distinct AI-powered auto-annotation models. Download sample images from [this Google Drive folder.](https://drive.google.com/drive/folders/1qPBP8JrRc7QA%5F8J-yNttLgZhbN2y8Q-L?ref=blog.unitlab.ai) First, create a project called ***Automata Workflow*** and select ***Image Segmentation*** as your base class. Unitlab AI currently supports image, [text](https://blog.unitlab.ai/unitlab-ai-text-data-annotation/), [audio](https://blog.unitlab.ai/audio-data-annotation-with-unitlab-ai/), and [DICOM](https://blog.unitlab.ai/guide-to-medical-image-annotation/) annotation, with support for video labeling coming soon: ![Project Creation | Unitlab AI](https://storage.ghost.io/c/48/f4/48f4b614-5c29-430d-9cb3-e0b3f34395f3/content/images/2026/01/i0-8.png) Upload your own images or the provided [sample images](https://drive.google.com/drive/folders/1qPBP8JrRc7QA%5F8J-yNttLgZhbN2y8Q-L?ref=blog.unitlab.ai) to this project, then assign yourself as a data annotator to this data sample. You can assign tags to data samples every time you upload data to your project. In our case, I assigned `Initial` : ![Data Upload | Unitlab AI](https://storage.ghost.io/c/48/f4/48f4b614-5c29-430d-9cb3-e0b3f34395f3/content/images/2026/01/i1-9.png) Data Upload | Unitlab AI ### Automation Setup With the project ready, go to the *Automation* menu on the sidebar and click *\+ New Automation.* The elegance of this feature is that you can use the same workflow for different projects, by connecting an existing one. For this project, we will create a new automation workflow from the ground up: ![Automation Workflow | Unitlab AI](https://storage.ghost.io/c/48/f4/48f4b614-5c29-430d-9cb3-e0b3f34395f3/content/images/2026/01/i2-9.png) Automation Workflow | Unitlab AI We want to detect people using [bounding boxes](https://blog.unitlab.ai/bounding-box-essentials/) and annotate clothing with [pixel-level segmentation](https://blog.unitlab.ai/pixel-perfect-image-labeling/), so we'll add two models to our workflow and name it **Automata Fashionium** (sometimes a name is just a name)*.* We can also manage annotators and reviewers: ![Automation Dashboard | Unitlab AI](https://storage.ghost.io/c/48/f4/48f4b614-5c29-430d-9cb3-e0b3f34395f3/content/images/2026/01/i3-11.png) Automation Dashboard | Unitlab AI You can adjust settings for each model by clicking one each auto-labeling model. In the settings panel, you can configure these parameters: - **Model Attributes**: You can change or remove model's class names and colors. - **Confidence:** Minimum confidence for valid predictions. For example, 0.7 (70%) means only detections above this confidence threshold will be shown; lower-confidence results will be excluded. - [**Iou Threshold**](https://blog.unitlab.ai/intersection-over-union-iou/)**:** Intersection-over-Union threshold used by Non-Maximum Suppression (NMS). A threshold of 0.25 means overlapping bounding boxes (more than 25% overlap) are either merged or filtered, keeping the box with the highest confidence. - **Max Detections:** Maximum number of detections allowed per image. A limit of 300 means the system retains only the top 300 detections ranked by confidence. ![Automation Settings | Unitlab AI](https://storage.ghost.io/c/48/f4/48f4b614-5c29-430d-9cb3-e0b3f34395f3/content/images/2026/01/i4-7.png) Automation Settings | Unitlab AI Now, your automation workflow is set. Let's annotate images automatically. ### Auto-image annotation Unitlab workflows support two annotation methods: [Batch Auto-annotation](https://docs.unitlab.ai/auto-labeling/batch-auto-annotation?ref=blog.unitlab.ai) and [Crop Auto-annotation](https://docs.unitlab.ai/auto-labeling/crop-auto-annotation?ref=blog.unitlab.ai). Batch Auto-annotation quickly annotates many images simultaneously, while Crop Auto-annotation allows precise annotation of a manually selected area. Batch mode is ideal for large-scale annotation, while Crop mode is better for focused labeling. We'll run our workflow in batch mode first: 0:00 /0:12 1× Batch Auto-annotation with Automation for Fashion Segmentation | Unitlab AI Then, we'll use Crop Auto-annotation to precisely label a selected region using our *Automata Fashionium* workflow: 0:00 /0:06 1× Crop Fashion Auto-annotation | Unitlab AI ### Dataset Release Having completed image labeling, you can now release your first dataset version (0.1). As you add more images, subsequent dataset versions can be released, allowing iterative dataset management with [built-in version control](https://blog.unitlab.ai/dataset-version-control/). You can release datasets directly within the project interface by going to `Release datasets` on the left-side panel: ![Dataset Release | Unitlab AI](https://storage.ghost.io/c/48/f4/48f4b614-5c29-430d-9cb3-e0b3f34395f3/content/images/2026/01/i5-8.png) Dataset Release | Unitlab AI Under the [Free plan](https://unitlab.ai/en/pricing?ref=blog.unitlab.ai), your datasets are public by default and available to everyone on Unitlab AI. To create private datasets and access advanced features, [upgrade to a paid plan](https://unitlab.ai/en/pricing?ref=blog.unitlab.ai). For this tutorial, we've released a public dataset, which you can [explore here.](https://app.unitlab.ai/dataset/1c94bd5d-aea2-49ca-a247-d7377715c657/description?path=public-dataset&ref=blog.unitlab.ai) ![Dataset Release | Unitlab AI](https://storage.ghost.io/c/48/f4/48f4b614-5c29-430d-9cb3-e0b3f34395f3/content/images/2026/01/i6-7.png) Dataset Release | Unitlab AI See this additional post for more information on datasets and version control. [Dataset Management at Unitlab | Complete Platform GuideA comprehensive guide to manage and release AI/ML datasets with Unitlab AI. Updated for 2026.![](https://storage.ghost.io/c/48/f4/48f4b614-5c29-430d-9cb3-e0b3f34395f3/content/images/icon/652fe0711ca7a678ec836f1b_FavIcon-203.png)Unitlab BlogsHojiakbar Barotov![](https://storage.ghost.io/c/48/f4/48f4b614-5c29-430d-9cb3-e0b3f34395f3/content/images/thumbnail/Dataset-Management.png)](https://blog.unitlab.ai/unitlab-ai-dataset-management/) Dataset Management | Unitlab AI ## Conclusion Our new Unitlab Workflows feature enables the combination of multiple AI models into a single automated annotation process, allowing complex labeling tasks to be performed effortlessly. Additionally, custom AI model integration ensures maximum flexibility and adaptability to your annotation needs. Unitlab AI offers the ultimate annotation platform for efficiently creating high-quality datasets for your AI and ML models. Give it a try today. [Start Today](https://app.unitlab.ai/login?ref=blog.unitlab.ai) ## Explore More Check out these additional resources for deeper insights into automation and AI model management in Unitlab: - [Data Annotation with Segment Anything Model (SAM)](https://blog.unitlab.ai/data-annotation-with-segment-anything-model/) - [5 Best Practices for Auto Annotation in 2026](https://blog.unitlab.ai/best-practices-for-auto-annotation/) - [How Unitlab AI Aims to Transform Data Annotation](https://blog.unitlab.ai/how-unitlab-ai-aims-to-transform-data-annotation/) --- **Explore related Unitlab capabilities:** [AI training-data annotation](https://unitlab.ai/en/data-annotation?ref=blog.unitlab.ai). [](https://unitlab.ai/en?ref=blog.unitlab.ai) Enterprise multimodal data platform ## Turn raw data into production-ready datasets. Curate, annotate, manage, and version every modality in one secure workspace. [Try Now](https://app.unitlab.ai/?ref=blog.unitlab.ai)[Book a Demo](https://unitlab.ai/en/request-demo?ref=blog.unitlab.ai)[](https://unitlab.ai/en?ref=blog.unitlab.ai) Enterprise multimodal data platform ## Turn raw data into production-ready datasets. Curate, annotate, manage, and version every modality in one secure workspace. [Try Now](https://app.unitlab.ai/?ref=blog.unitlab.ai)[Book a Demo](https://unitlab.ai/en/request-demo?ref=blog.unitlab.ai)