
You can now connect Zira to Claude and simply ask about your operation. Claude reads your live Zira
data to answer, and — when you allow it — does the work in Zira for you.

No more copying readings into a chat window or pasting answers back out.

## Ask in plain language

Once connected, ask the kind of question you would ask a supervisor:

- *"Why did the trim saw stall last night? Check its readings around 22:00."*
- *"What was yesterday's output on line 3?"*
- *"Show me the open tasks for the Rehovot plant."*

Claude finds the right data source by name, looks up the readings, and answers. You do not need to
know which metric or device to point it at.

## Let Claude do the work

Give a connection permission to act and Claude can open and update tasks, record readings, and post
an update to a channel — always asking you before it does.

Prefer to start carefully? Choose **Look only** when you connect, and Claude can answer questions
but cannot change anything.

## Connecting takes two clicks

Open your profile picture and choose **Connect to Claude**. Pick the site you want Claude to work
with, choose what it may do, and press **Connect**. Copy the single line Zira gives you, paste it
into Claude, and you are done.

Each connection covers one site, so connect each site you want Claude to reach.

![Connecting a site to Claude: pick the site, choose what Claude may do, press Connect.](/changelogs/connect-zira-to-claude/connect/01-connect-panel.png)

## Claude can read the guides too

There is a second, separate connection that gives Claude the Zira help center — the product guides,
the API reference, and these release notes. It is public and read-only, so it needs no setup beyond
the address. Teams that use both get answers grounded in how Zira actually works, not guesswork.

## Getting started

- [Connect Zira to Claude](/developers/how-to-guides/connect-zira-to-claude)
- [Connect the documentation](/developers/how-to-guides/connect-the-documentation-mcp-server)


Pick a site, press Connect, paste one line into Claude. No keys to manage by hand.

Connect in two clicks

"Why did the trim saw stall last night?" — Claude looks it up in your live data.

Ask about your plant

Open a task, post readings, or share an update to a channel — Claude asks you first, every time.

Let Claude do the work

Choose a read-only connection and Claude can answer questions but change nothing.

Look-only when you prefer

A second connection lets Claude search Zira's guides and API reference while it helps.

Claude knows the product too

Connect Zira to Claude and ask about your operation in plain language — Claude reads your live production data, and can open tasks and post updates for you.

Connect Zira to Claude


Until now, a camera that spotted a problem could tell you about it. In this release it can also do
something about it — a routing rule can switch an andon light or trip a PLC contact the moment it
matches. Alongside that: a trim saw calibrates itself while you watch, models push to a named slot
and tell you they got there, and teaching a camera something new no longer asks you to fill in a
form full of machine-learning vocabulary.

## Ask Claude about your plant

**In beta.** You can now connect a site to **Claude** and ask about your operation the way you would
ask a supervisor:

- *"Why did the trim saw stall last night? Check its readings around 22:00."*
- *"What was yesterday's output on line 3?"*
- *"Show me the open tasks for the Rehovot plant."*

Claude finds the right data source by name and looks the readings up in your live Zira data. No more
copying readings into a chat window or pasting answers back out.

Open your **profile picture** and choose **Connect to Claude**, pick the site, choose what Claude may
do, and paste one line into Claude. That is the whole setup.

Choose **Look only** and Claude can answer questions but change nothing. Choose **Look and act** and
it can open and update tasks, record readings and post to a channel — asking you before each one.

We are still refining this one, and we would like to hear how it goes.

![Connecting a site to Claude: pick the site, choose what Claude may do, press Connect.](/changelogs/vision-hub-training-and-datasets/connect-to-claude/01-connect-panel.png)

Read more: [Connect Zira to Claude](/docs/ai-assistance/connect-to-claude) ·
[the full release note](/whats-new/connect-zira-to-claude)

## The AI Assistant, from any page

Until now, the AI Assistant came with a trade: to use it, it had to become your home page. Plenty of
people would rather start the day in the feed or on a dashboard — so the assistant now has a door of
its own.

- Look for the **AI Assistant** icon — the sparkles — in the left menu, just above **Chats**. It
  opens the same assistant, with the same answers, previews and builders, and your Work mode stays
  exactly as it is.
- **Your saved chats come with you.** A conversation started from the icon is under **Saved chats**
  wherever you open the assistant.
- **On a phone,** open the menu and tap the same icon.
- **Heading back is one click:** open the menu and click the Zira logo to return to your home page.

If the AI Assistant is already your Work mode, nothing changes — it is still the first thing you see,
so the icon stays out of your way.

Read more: [Home AI Assistant](/docs/ai-assistance/home-ai-assistant) ·
[Choose Your Work Mode](/docs/getting-started/profile-preferences/home-page)

## Let a rule switch something on the floor

Routing decides which lane a pallet goes down. Now a rule can also **do something** the moment it
matches — so a decision on the screen becomes an action on the floor.

**Actuators** drive the camera's relay outputs. A relay is a dry contact, so anything that takes a
contact closure can be driven from a rule:

- **Andon lights** — put the red lamp on when a severe defect is routed, and clear it when the line
  recovers.
- **A machine PLC** — stop or start the line, or fire an eject, by closing the contact the PLC is
  already watching.
- Horns, diverters, gates — anything on a relay.

Pick the actuator and relay, then choose **on**, **off**, or **pulse**. A pulse takes a duration,
which is what an eject or a momentary stop signal wants. Actuators that publish named functions of
their own offer those too, with whatever fields the function asks for.

Only actuators the camera currently reports as **online** can be chosen. If a rule points at one
that has gone away, it stays on the rule as a warning rather than being quietly reassigned — so you
find out before it drives the wrong thing.

**Webhooks** are the other half: send an HTTP request when a rule matches, to tell an MES, a
scheduler, or anything else that should know. A rule can call several.

Rules in the **Default** stage can now be set to always match, so pallets nothing else caught can
still trigger an action — not just fall through to a lane.

### And you can tell whether the camera took it

Saving routing sends it to the camera, but a save is not proof it was applied. The toolbar now shows
**Awaiting sync**, **Syncing**, or **Up to date** per camera, with its name when more than one is
paired. Cameras that were offline pick the change up when they reconnect.

## Calibrate a trim saw from your desk

Measuring what a trim saw actually cuts — the length of a board going in and the length coming out —
used to mean commissioning the camera at the machine. It is now a run you start from the console and
watch on the live view.

Open **Trim saw stops** beside the live view, press **Collect**, and let the saw run. The camera
watches boards go past and captures a line for each stop it finds. Stop when you have enough, tell
it which cut size each line is, and apply. That is the calibration.

- **You only declare the sizes.** The positions are the camera's own measurement, so there is
  nothing to tape-measure and nothing to type in from the floor. Declare the sizes up front if you
  know them, or label each line after collecting if you would rather see what turns up.
- **A camera set up against a measured reference needs only one cut size** instead of two. When that
  applies, the window says so and shows the reference it was given.
- **Add to a calibration, or start over — and it asks which.** A saw that has drifted can be
  re-measured while keeping its existing sizes. Clearing them is now a single confirmation naming
  how many stops will go, rather than a question buried under settings for the run afterwards.
- **A run that nobody finished shows up on the data source**, so a collection left open does not
  quietly block the next one.
- Stops are set up by **the side of the board they sit on** — left, right, top or bottom — rather
  than by which end of the travel they are nearer.

This needs the current camera app on the device.

## Send a model to a camera, and know it landed

Cameras can now hold **several models at once**, so pushing one asks which **slot** it goes into.
The slot list comes from the camera itself, so a camera with four of them needs nothing configured
here.

Knowing what a camera is *actually* running used to be guesswork. The Models tab now lists each
model the camera reports, matched against what is stored in Zira, and says how confident that match
is — an exact fingerprint match, or only a likely one based on name and size. Where it is unsure,
you can ask it to **verify**, and it checks the file byte for byte.

Adding a model is easier too: `.pt` files upload directly, and a new dialog collects the type,
classes and where it came from at the point you add it.

## Training that explains itself

There is a **new [Training guide](/docs/ai-vision/training)** in the help centre, covering the whole
path from a labelled dataset to a model running on a camera.

The training form is now called **Train a model**, and it opens by telling you what a run does: it
learns from a dataset, it runs in the cloud, you can close the page, and it takes minutes to hours.

- Settings are grouped into **what you are making** and **how it trains**, so it is obvious which
  handful of fields matter.
- Every field has a plain-language explanation beneath it — *"How many times it reads every image.
  100 is a good start."*
- The expert controls have not gone anywhere; they are collected under **Advanced**, clearly marked
  as things a normal run never needs.
- Only one field is required: the name.

### Fewer ways to waste a run

Cameras need a converted copy of a trained model, and some of the newer conversion formats cannot
run on the camera app yet. If you pick one, the form now says so clearly before you start — instead
of leaving you to discover it when the file will not go to the device.

## Understand how a run went

- Finished runs score **each class separately** on how often the model was right when it fired and
  how much of the real thing it found — so instead of one overall number you can see exactly which
  defect still needs more examples.
- You no longer have to wait for the end. The run's charts now plot **every class as it trains**, so
  you can watch one defect catch up — or fall behind — while there is still time to do something
  about it. Switch between the two scoring styles to tell "found it at all" from "placed it
  accurately".
- The run also lists the **image variations** it generated from your pictures, so you can see what
  the model was trained against. If you need different ones, you can now set them yourself under
  **Advanced**.
- If the run trained on a merged dataset, the job shows **which datasets went into it** and how they
  were split.
- The Training tab says what it is for, and when it is empty it tells you how to start your first run
  rather than showing a bare table.

## Group your datasets

Once a camera has been running for a while, its dataset list gets long. Now you can put datasets into
**groups** — by product line, by camera, by whatever suits you.

- Add a group from a dataset's menu, under **Groups**. A dataset can be in several.
- **The list opens in sections.** A data source with groups is organised, and opening on the
  unorganised version hid that. The plain list is still one click away on the group icon.
- **Rename a group from its heading** and every dataset in it follows. Rename it onto a group that
  already exists and the two merge — you are told before you confirm.
- Datasets that are not in any group collect under **Ungrouped**, after the real groups.
- Anything you put in **archived** drops to the bottom and stays closed, so finished work is out of
  the way without being deleted.

Dataset **tags** have been retired. They did the same job as groups without any of the behaviour, so
a dataset could end up labelled twice and sorted once — groups now do it in one place.

The Datasets table was tidied up while we were there: the toolbar is one consistent set of controls
instead of five different-looking ones, notes show their text in the list rather than an icon, and
the versions count is a link you can click.

## Merging datasets, without the wizard

Combining datasets used to be a three-step wizard ending on a page of counts, duplicate reports,
per-dataset split cards and half a dozen checkboxes. It is now a single short form that asks the four
things a merge actually varies: which datasets, what to call the result, how to split it, and which
classes to keep. Everything else is simply handled.

The detail has not gone — it is in a **Merge analysis** section you can open when a merge looks
wrong, showing per-dataset and per-class counts, repeated images and box quality.

Choosing which classes to keep also works properly now: the list reorders as you press the arrows,
and the number beside each class is the class number the model will learn.

## Follow work that outlives the page

Merges, training runs and camera-file builds take minutes and keep running after you close the
window that started them — or close Zira altogether. **Background work**, the history icon above the
Datasets table, is where you follow them.

It carries a badge with the count, turns into a spinner while something is still going, and opens a
list of what each piece of work is doing and how it ended. The snackbars that start these jobs now
point you straight at it.

## Models that say what they are

- The tab now has **two clearly named lists** — what the selected camera reports it is *Running on
  this camera*, and everything *Stored for this data source*. It used to be one word above both.
- Every model can carry a **type** — what it looks for — which the Models tab groups and filters by.
  You can set it while training, or correct it afterwards from the model's menu.
- **Version** and **Format** are their own columns instead of chips crowded into the name, so long
  model names stop wrapping onto two lines.
- **Opening a training run keeps your place.** It now opens in a panel over the list rather than
  navigating the whole page away from the models you were reading.
- The row menu says what each action is for in plain terms: **Build a file for the camera**,
  **Fine-tune from this model**, **Change what it looks for**.
- Models built in a format the camera app cannot run yet are marked, so you find out in the list
  rather than at the moment you try to send one.

## Quality you can watch live

- **QA snapshot widgets update the moment an image arrives** instead of polling on a timer, so a
  dashboard on the wall keeps pace with the line.
- **A marks report** gathers what reviewers marked across a site, so you can see what is being found
  without opening each session.
- **Auto-defects** flag known defect patterns as they come in.
- A **Validation hub** brings session review together in one tab, and the site list now shows at a
  glance which data sources are stable and current.
- Snapshot widgets take dashboard date filters, so one dashboard can be pointed at any shift.

### Judge a snapshot without leaving the dashboard

Opening a snapshot from a QA Snapshots widget used to load the whole review page inside the
dashboard. It now opens a reviewer built for the job:

- **A magnifier shows the frame at the camera's own resolution** — which is what makes a nail head
  or a hairline crack readable at all. On a pallet camera the reviewer can also draw the board and
  stringer crossings and let you pick the ones a defect is in, and the mark records exactly which
  crops you meant, so the next person looks at the same ones.
- **Your filter comes with you.** The arrows step through the snapshots the widget is already
  showing, so a defect filter carries into the reviewer and keeps going past the end of a capture
  session.
- **Marks already on the image are shown**, so a frame does not get judged twice.
- **Back returns to the dashboard** instead of leaving it, with every other widget still as you
  left it.
- **Or mark without opening anything.** Put the review categories on the card with **Show mark
  buttons**, and on a single-image widget you can draw the crossings there too — tap the ones a
  defect is in, press a category, done. Five steps become two. Opening the snapshot is still the
  better call when the judgement is close, because there the image is full resolution.
- **On a tablet, pinch to zoom** — the magnifier starts off there, since a panel that size costs
  more screen than it gives back. Tap a crossing to select it, and if you do turn the magnifier on,
  press and hold to move it.

## Dashboards and agents

- **Correction fields for Data Research widgets.** Apply a calculation to every reading *before* it
  is grouped, then group, measure or filter by the result — the one place a correction can change
  what a chart's categories actually say.
- **Alerts that get out of the way.** A popup condition alert can now fade itself out after a set
  delay instead of covering the widget until the next reading arrives.
- **AI agents can work across several dashboards** at once, take a time range, and be told what
  answer style you want.
- Charts default to sensible sizes and font scales, gauges to a sensible colour, and a data table
  can be printed.

## More ways to get images in

- **Take a photo straight from your phone** when filling a form or adding images, with the camera
  opening reliably on mobile.
- **Copy into a dataset keeps your choices** — split and annotation settings persist between copies.
- **Shuffle & split** gained real options and a preview of the result before you commit, and both
  copies and merges now honour a **target resolution**.
- Dataset images show **tiny box** and **edge box** chips so weak annotations are easy to spot, and
  label visibility, class colours and thumbnails stay in step.

## On the cameras themselves

Plenty changed on the cameras too. There are no new screens to learn — it is mostly things being
more accurate, and less being lost.

**Sharper pictures, steadier counting.** Exposure, ISO and zoom can be set by hand, the preview can
be rotated and stays that way, and a camera can now sample at high resolution without slowing down
the detection it is running at the same time. A frame-rate default that had been quietly holding
cameras at 15 frames a second is fixed. Occupancy areas can be any shape rather than a rectangle,
counting triggers can be limited to a single label, and pallet cameras are better at nails, lead
boards and keeping detections inside the pallet — with calibration that stays correct when the
camera is mounted at an angle. Stations running several cameras together coordinate more reliably.

**Less gets lost.** Shift counts now survive restarts, recoveries and shift changes instead of being
dropped, and a reading the server rejects is held rather than discarded. Recordings keep their raw
and validation clips together, pick up stalled uploads again, and recover from encoding errors
rather than ending up half sent. Cameras also show their CPU and battery temperature, so a unit
working too hard is visible before it starts dropping frames.

## Around the rest of the app

- **Image review** — a new **Pallet mark** filter narrows a session to one product or batch. It shows
  up only when the session actually contains marked pallets.
- **Pie charts** can now show a **legend**, for when the slice labels are too tight to read.
- **Indicator widgets** read **True** or **False** on a yes/no field instead of a raw value.
- **Chart tooltips** hold still, so the **view entries** button stops sliding away as you reach for
  it — and sorted Data Research charts now draw their axis correctly, embedded ones included.
- **The tasks board** scrolls to the bottom, loads more reliably, and opens the card you clicked.
- **Schedules** can be added at site level, and straight from an AI widget.
- The app **remembers more between visits**, so returning to a page you were just on is quicker.

## Read more

- [Connect Zira to Claude](/docs/ai-assistance/connect-to-claude) — new guide
- [Home AI Assistant](/docs/ai-assistance/home-ai-assistant) — opening it from the left menu
- [Routing](/docs/ai-vision/routing) — actuators, webhooks and device sync
- [Trim Saw Stops](/docs/ai-vision/trim-saw-stops) — calibrating a trim saw
- [Models](/docs/ai-vision/models) — rewritten
- [Training](/docs/ai-vision/training) — new guide
- [Datasets](/docs/ai-vision/datasets) — groups, merging and background work
- [QA Snapshots](/docs/dashboards/qa-snapshots-widget) — live updates, marks and reviewing from the dashboard
- [Image Review](/docs/data-sources/image-review) — pallet mark filter


Connect a site to Claude and ask about your operation in plain language. Claude reads your live data, and acts only when you let it.

Keep the feed or a dashboard as your home page, and open the assistant any time from the sparkles icon in the left menu.

The AI Assistant, from any page

Routing rules can now drive a relay — an andon light, or a PLC contact to stop, start or eject — and call a webhook.

Let a rule switch something on the floor

Measure cut lengths by watching boards go past on the live view. No tape measure, no standing at the machine.

Calibrate a trim saw from your desk

Push to a named slot on cameras that hold several, and see exactly which model each one is really running.

Send a model to a camera, and know it landed

Every setting says what it does in plain words, and each class is scored as the run goes — so you know which defect needs more images.

Training that explains itself

QA snapshots update the moment an image arrives, and a marks report gathers what reviewers found across a site.

Quality you can watch live

Routing rules can now switch an andon light or drive a machine PLC, a trim saw calibrates itself while you watch from your desk, models push to a named slot and prove they landed, and training explains every setting in plain language. You can also connect a site to Claude and ask about your operation out loud, and open the AI Assistant from any page without making it your home page.

Act on What the Camera Sees


This release opens Zira's documentation to the world. Guides, the developer reference, and release
news now live on their own public site — no sign-in, readable by anyone you send a link to, and
indexed by search engines. Alongside it, the API reference is finally complete: every endpoint shows
what to send, what comes back, and what to do when something fails. Inside the product, device
settings now come from the device itself, each data source gets its own Training tab, and routing
rules can call a webhook.

## 📚 A public help center at help.zira.us

Everything that used to sit behind a login now has a public home.

- **Guides, developer docs, and What's New** are all served from [help.zira.us](/docs), and every
  page works without an account. Send a colleague — or a prospective customer — a direct link and it
  simply opens.
- **Search engines and AI assistants can read it.** The old in-app help was invisible to both, so
  people looking for an answer never found ours. Now they will.
- **Existing links keep working.** Old `/docs`, `/developers` and `/whats-new` addresses forward to
  the new site automatically, so nothing you have shared or bookmarked breaks.
- **Support stays private.** Opening a support ticket still happens inside Zira, where we know who
  you are.

## 🔌 A complete API reference

If your team connects Zira to another system, the reference is now something you can build against
rather than guess at.

- **Every endpoint documents its response.** Each one shows the real body you get back, with a field
  table explaining what each value means and which values can be empty. Previously most endpoints
  described only what to send.
- **Request and response examples are copy-ready**, with a one-click copy button.
- **A familiar layout.** Each endpoint is laid out in tabs — description, parameters, authorization,
  headers, body, response — so it reads the way an API client does.
- **Errors are documented once, properly.** Every endpoint lists the statuses it can return and what
  each one actually means, so you can handle failures instead of discovering them.
- **Corrections throughout.** A number of endpoints listed fields that no longer exist, marked
  optional fields as required, or omitted parameters you cannot work without. Those are fixed.

## 🤖 Ask about the endpoint you are reading

An assistant now sits beside the reference behind a button that stays with you as you scroll. Ask how
to authenticate, what a parameter does, or for a snippet in your language, and it answers from the
documentation for the endpoint you are on — so the field names and addresses match what the system
really accepts.

## ⚙️ Device settings come from the device

Camera and vision device settings used to be described in two places: once on the device and once in
Zira. When a device gained a new option, Zira did not know about it.

Now the device publishes its own settings, and the dialog renders exactly that. You see the options
your device actually supports, read-only values are clearly shown as read-only, and a device can gain
a setting without waiting for a Zira release.

## 🎓 Training, per data source and across the account

Each data source now has its own **Training** tab showing the training runs it has been part of,
along with their results and metrics. Administrators also get a single page listing every training
job in the account, so a run that needs attention is easy to find.

## 🪝 Routing rules can call a webhook

A routing rule can now send its decision to another system as it happens, so downstream tools react
immediately instead of waiting for the next poll.

## 🗂️ Smaller things that add up

- **Sharper image review.** Filter a session by the classes actually present in it, and jump between
  sessions without losing your place.
- **Smarter agents.** Agents now run on the current generation of AI models only, with faster,
  leaner requests. What used to be labelled "GPT" is now simply "AI".
- **QA Snapshots.** Mark an image straight from its card, with clearer labels on the widget.
- **Dashboards.** More control over table columns and bar colours, and pie chart colours follow the
  palette you expect.

## 🐛 Fixes

- Hover states across the app no longer come out too dark in dark mode.
- Editing an agent's configuration no longer shows a stale copy of what you just saved.
- Deleting all of a label file's labels now removes the empty file instead of leaving it behind.


Guides, the API reference, and release news all live at help.zira.us — no sign-in, and shareable with anyone.

Help and developer docs, now public

Every endpoint now shows its parameters, headers, request body and a real response example you can copy.

A complete API reference

An assistant sits beside the reference and answers questions about the endpoint you are reading, with working code.

Ask about any endpoint

Camera and device settings dialogs now show exactly the options that device supports, so nothing is stale or missing.

Device settings from the device itself

A Training tab on each data source shows its training runs and results, with a single place to watch every job.

Training, per data source

Send a routing decision straight to another system as it happens, instead of polling for it.

Routing rules can call a webhook

This release opens Zira's documentation to the world. Guides, the developer reference, and release news now live on their own public site — no sign in, readable by anyone you send a link to, and indexed by search engines