
Use the **People** tab when you want to review the people connected to the current channel.

This tab helps you confirm who belongs here, add people when needed, and keep people-related work tied to the right channel.

## Navigation

Open a channel first, then click the **People** tab.

Use this tab when the channel matters more than a broader people search across the whole app.

## Open the People tab

1. Open a channel.
2. Click the **People** tab.
3. Review the people shown for that channel.

## What you can do here

Use this tab to:

- review people connected to the channel
- confirm whether the right members are visible
- add people or invite them when that option is available
- review invite status in channels that support invites

If you need to check whether the right people are connected to the work, this is the right place to start.

## Add or invite people

1. Open the channel.
2. Click the **People** tab.
3. Click the **Add/Invite People** button in the toolbar.
4. Choose the people you want to add.
5. Confirm the action:
   - On system channels, the **Add people** dialog adds existing site members to the channel.
   - On site and company channels, the **Invite people** dialog lets you choose existing people or invite people by email.

## Review followers and invites

The People tab opens on **Followers**.

On site and company channels, use the **Followers** and **Invites** toggle to switch between current people and outstanding invitations.

## Tips

- Start here when membership matters for the work you are doing in the channel.
- Use this tab instead of a broader people page when you only care about one channel.

## Read next

- [User Invites](/docs/people/user-invites) - Invite new people to the site and review invite status.


Use the People tab to review who belongs to the channel and manage people-related work in the right context.

People


Use **invites** when you want to bring a new person into a site or company and give them the right level of access.

You can invite people who already have a Zira account or invite someone new by email address. Each invite can be set to a different permission level, so you decide who can manage the site and who can only view it.

## Where to invite from

You can start an invite from a couple of places, depending on where you are working:

- From a channel, open the **People** tab, then switch to **Invites** and use the add button.
- From a site or company, open the **Invite people** action to add colleagues directly to that site or company.

Both paths open the same **Invite people** flow, where you add colleagues by email or choose existing people and then set their access.

## Add the people you want to invite

1. In **Search existing people**, type a name or email address.
2. Select a matching person from the list to add them to the invite.
3. To invite someone new, enter their full email address and click **Invite** next to it.
4. Repeat until everyone you want is in the list.

You can prepare several invites before sending them, and each person appears as a row in the invite list.

If the email already belongs to an existing person, Zira shows **Existing person found** — select them from the list instead of inviting the email again.

## Set the permission level

Each row in the invite list has a **Permissions** selector. Choose the level for that person:

- **Admin** — for people who should be able to manage settings, people, and content in the site or company.
- **Viewer** — for people who only need access to view content without admin-level control.

New invites start as **Viewer**, so raise anyone to **Admin** only when they need to manage the space. You can set a different permission for each person before sending.

## Use Auto-Confirm only when needed

Each invite row also has an **Auto-Confirm** option.

Turn this on only for people who do not have a valid email address. When Auto-Confirm is on:

- the person is added without sending an invitation email
- they will not be able to reset their password
- email notifications will not be sent to them

In almost every case, leave Auto-Confirm off and send a normal invite so the person receives an email and can manage their own account.

## Send the invites

When the list is ready, click **Invite** at the bottom of the dialog to send everyone together.

If any invite fails, that person stays in the list so you can review and try again. The people who were invited successfully are removed from the list.

## Follow up on invite status

From the **Invites** view you can review everyone you have invited and their current status:

- **Active** — the person accepted the invite and joined.
- **Pending** — the invite has been sent but not accepted yet.
- **Expired** — the invite is no longer valid.

For pending or expired invites, open the row menu to:

- **ReInvite** — send the invitation again.
- **Delete** — remove the invite.
- **Confirm** — confirm the person yourself when you manage the site and the invite is still pending.

## Tips

- Add everyone first, set each permission, then send the invites together.
- Double-check who is set to **Admin** before sending.
- Keep Auto-Confirm off unless a person truly has no email address.
- Use the **Invites** view to chase anyone still showing as Pending.

## Read next

- [Accept an Invite](/docs/getting-started/account-access/accept-an-invite) - What the people you invite need to do to join.
- [People](/docs/people/channel-people) - Review the people connected to a channel.
- [Follow a Channel](/docs/channels/follow-a-channel) - Help new members get notified about posts and tasks.


Invite new people to a site or company, set their permission level, and follow up on invite status.

Invite People to a Site


A **model** is what lets a camera recognise something — a defect, a part, a label. The **Models**
tab lists every model belonging to this data source and is where you send one to a camera.

![Models tab](/docs/data-sources/models-01.png)

Open a data source, then click **Models**.

## How a model gets here

1. Create and label a dataset — see [Datasets](/docs/ai-vision/datasets).
2. Save the dataset as a version.
3. Run training on that version — see [Training](/docs/ai-vision/training).
4. The finished model appears in this list.
5. Use **Push to Device** to send it to the camera.

You can also use **Add model** (the **+** button) to upload a model you already have, or copy one
from another data source.

## What you see in the list

| Column | What it tells you |
| --- | --- |
| Name | The model's name. |
| Version | Which version of that model this is — 2 means the second one training produced. |
| Format | `PyTorch` is the trained model, `TFLite` and `LiteRT` are the converted copies a camera runs. |
| Looks for | What the model detects. Use the filter icon above the table to narrow the list. |
| Training run | The run that produced it. Click it to open that run in a panel over this tab, so you keep your place in the list. |
| Size | How big the file is. |
| Created | When it was made. |

A dash under **Looks for** just means nobody has set a type yet. You can set one from the row menu.

### Two kinds of file

- A **`.pt`** file is the trained model itself. It is what you fine-tune from, and what a camera
  file is built from — but a camera cannot run it directly.
- A **`.tflite`** file is the converted copy a camera runs. This is what **Push to Device** sends.

Training normally produces both at once.

## Running on this camera

If a camera is selected in the device picker, a short list above the table shows what is actually
installed on it right now — one line per slot, with a green tick when the model is there and matches
a model you have in Zira.

Click a model's name to see the full detail: the file on the camera, where it came from, and when it
was installed.

This is reported by the camera itself, so it is the truth about that device rather than a record of
what somebody meant to send.

## What you can do with a model

Open the **⋮** menu at the end of a row.

| Action | What it does |
| --- | --- |
| Download | Saves the file to your computer. Available to administrators. |
| View training analysis | Opens the run that produced this model. |
| Push to Device | Sends the model to the selected camera, into a slot you choose. `.tflite` only. |
| Fine-tune from this model | Starts a new training run that carries on from this model instead of starting fresh. `.pt` only. |
| Build a file for the camera | Converts a `.pt` into the smaller file a camera can run. |
| Change what it looks for | Sets the model's type, which is how this list groups and filters it. Safe to correct at any time — it does not change the model. |
| Delete | Removes the model from this data source. |

## Push to Device

Use this when you want a camera to start using a model.

1. Select the camera in the device picker at the top of the page.
2. Open the **⋮** menu on the model and choose **Push to Device**.
3. Choose the slot it should go into.
4. Send it, and watch the progress in the dialog.

If the camera is asleep or briefly offline the model still reaches it — the instruction waits for up
to five minutes. The dialog confirms the install from the camera's own record, so a success here
means the camera really has the file.

If nothing is selected in the device picker, Push to Device is unavailable: there is no camera to
send to.

## Build a file for the camera

Cameras cannot run a trained `.pt` model directly, so it has to be converted first. Training usually
does this for you; use this action when you need to redo it, or want a different size-and-accuracy
trade-off.

- **Size and accuracy** — smaller files run faster on the camera; larger ones are slightly more
  accurate.
- **Calibration** — the smaller options measure themselves against a sample of your real images so
  that shrinking the model costs as little accuracy as possible. The defaults are fine.

If a warning tells you the format does not run on the camera app yet, the file will still be built
and stored — you just will not be able to push it to a device until the app supports it.

## Read next

- [Training](/docs/ai-vision/training)
- [Datasets](/docs/ai-vision/datasets)
- [Validation](/docs/ai-vision/validation)


See every model for this data source, send one to a camera, build a camera file, and fine-tune a better version.

Browse Guides

People

Navigation

Open the People tab

What you can do here

Add or invite people

Review followers and invites

Tips

Read next