> For the complete documentation index, see [llms.txt](https://docs.biodock.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.biodock.ai/analysis-and-results/running-an-analysis.md).

# Running an analysis

*What you'll get: how to run a model on your images from the **New analysis** page, what each step asks for, who can see the results, and how to follow the run until it finishes.*

## Open the New analysis page

Go to **Analysis** in the sidebar and click **Start new analysis**. Or, on a model version, click **Use for analysis**: the page opens with that model already picked once you choose **Automated batch**.

The steps are numbered down the left. On the right, the **Job manifest** sums up the job and holds the **Submit** button. While something is missing, the manifest says what, in red (for example "Name this run before submitting.").

<figure><img src="https://3806122466-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fk3DfNQKoMy1JXdaDLvpG%2Fuploads%2Fgit-blob-cae5bcc441229d20ff9df97d74f6ca626cbfa6e2%2Fdocs-analysis-new-analysis-page.png?alt=media" alt="The New analysis page with Analysis type, Pipeline, Input files, Parameters and Results folder on the left, and the Job manifest with Job name, Cost and Submit on the right"><figcaption><p>The <strong>New analysis</strong> page and its <strong>Job manifest</strong>.</p></figcaption></figure>

## Run a model on many images (Automated batch)

<figure><img src="https://3806122466-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fk3DfNQKoMy1JXdaDLvpG%2Fuploads%2Fgit-blob-0097e0ec6086390ef6722b56fe144359efdc1e60%2Fdocs-analysis-run-batch.gif?alt=media" alt="Click Automated batch, click Select on Nuclei counter, click Add files, tick the Control and Treatment folders, click Confirm selection, type a Job name, click Submit, the job appears at the top of the Analysis list with a progress bar"><figcaption><p><strong>Automated batch</strong> → pick the model → <strong>Add files</strong> → <strong>Confirm selection</strong> → name the job → <strong>Submit</strong>.</p></figcaption></figure>

1. Under **Analysis type**, click **Automated batch**.
2. Under **Pipeline**, pick the model (see [Pipelines](#pipelines)).
3. Under **Input files**, click **Add files**, tick the images or folders, and click **Confirm selection**.
4. Check **Parameters**, and optionally choose a **Results folder**.
5. In the **Job manifest**, type a **Job name**, check the **Cost**, and click **Submit**.

## Analysis type

* **AI-assisted**: for small jobs. The images open in the labeler, and you outline the objects yourself with AI help. No trained model is needed. See [Path 1: AI-assisted analysis](https://docs.biodock.ai/start/path-1-ai-assisted-analysis.md).
* **Automated batch**: runs an active model on every image in the cloud, for any number of images.

For **AI-assisted**, there is no **Pipeline** step. Pick the input files, name the job, and click **Start labeling session**. The run opens on its **Label** tab. When you have labeled the objects, click **Quantify objects**, choose the measurements in **Choose analysis metrics**, and click **Run analysis**.

## Pipelines

A pipeline is the model that runs on your images. The **Pipeline** step lists:

* **Your models**: projects with an active model version, trained in this account or workspace. If a project has more than one active version, pick the version on its card.
* **Biodock models**: ready-made models available to your account, and [public models](https://docs.biodock.ai/projects-and-models/public-ai-models.md) you have added.

Click **Select** on a card to pick it. Once one is picked, the other cards are hidden; click **Change** to see them again.

A model you trained runs in the account where you trained it. To run it from another account or workspace, [publish it](https://docs.biodock.ai/projects-and-models/public-ai-models.md#publishing-your-model).

## Input files

1. Click **Add files**. The **Choose images** window opens.
2. Pick from **Filesystem**, or, for a model you trained, from **Project images**.
3. Tick images or folders. Ticking a folder includes every image in it. Click a folder's name to open it.
4. Click **Confirm selection**.

Each folder you pick becomes an image group in the results, so you can compare groups straight away. Before you run, put each condition in its own folder (for example `Control` and `Treatment`). The page shows how many images and groups you picked, and the groups your results will be arranged into. Click **Change selection** to change them.

## Parameters

What you set here depends on the model.

* For a model you trained, **Channel mapping** matches your images' channels to the channels the model was trained on. If your images are the same kind the model learned on, there is nothing to change. If a microscope saves the channels in a different order, open **Advanced settings** and pick the right channel for each row.
* Biodock models may ask for their own settings.

All images in one run must have the same number of channels. For very large images, Biodock may ask you to tick a warning before you can submit.

## Results folder and who can see it

If you have analysis folders, choose a **Results folder** to file the analysis in. It is optional: choose **No folder (top level)**, or file it later.

Above the **Submit** button, the manifest says who will see the results:

* In a workspace, a new analysis starts private: **Only you will see the results**. Nobody else sees it until you share it from the **Share** tab or from **Share…** in its row menu on the **Analysis** page.
* If you file it in a folder that other people can see, the line changes to **Others will see this analysis** and names them. A folder's access covers everything in it.

See [Sharing and visibility](https://docs.biodock.ai/workspaces/workspaces/sharing-and-visibility.md).

## Cost

The **Cost** box in the **Job manifest** shows what the run will use before you submit. AI-assisted runs show their cost when you click **Quantify objects**. If a run needs more than you have left, the manifest tells you and **Submit** stays disabled. For how credits work, see [Credits, storage and limits](https://docs.biodock.ai/account/credits-storage-and-limits.md).

## Follow the run

After you click **Submit**, the job appears at the top of your **Analysis** list with a progress bar. Click **Watch live** to follow it on the **Job details** tab.

* **Queued**: waiting for a machine.
* **Processing**: the images are being analysed. Job details shows how many have completed.
* **Finalizing**: the results are being put together. Progress can look stalled near the end while this runs.

When it finishes, Job details shows one of:

* **Succeeded**: every image worked. Click **View results**.
* **Partial success**: some images failed; the rest are ready. Click **View results**.
* **Failed** or **Cancelled**: run it again, or contact [Biodock support](https://docs.biodock.ai/about/contact-us.md).

How long a run takes depends on the number and size of your images; a small batch usually takes minutes. It is safe to close the tab and come back later.

## Next steps

* [Results dashboard overview](https://docs.biodock.ai/analysis-and-results/results-dashboard-overview.md): read the results.
* [Download results and reports](https://docs.biodock.ai/analysis-and-results/download-results-and-reports.md): take the numbers with you.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.biodock.ai/analysis-and-results/running-an-analysis.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
