Bulk ScanCopy Anchor Link

A bulk scan lets you apply the same prompt and field connection to many documents at once. You can include up to 999,999 documents in a single bulk task, on every plan. See Plans and billing for token capacity by tier. Instead of scanning documents one at a time, you select a set of documents in Nuix Discover's browse list and let Claira work through all of them automatically. This is how you move from prompt testing to production-scale review.

Before you run a bulk scanCopy Anchor Link

You need three things in place before starting:

1. A connected field. In the Claira Settings area, connect the Nuix Discover field where results should be written. If you have not done this yet, see the Fields guide.
2. A saved prompt. Write and save your prompt in the Prompt area. We strongly recommend testing it first with Single Review on a sample of documents. Single review is free on every plan and every media type: bulk scans are the only thing that consume tokens.
3. Selected documents. In Nuix Discover's browse list, select the documents you want to scan. The current selection determines which documents Claira will process. The Bulk Scanning header reads back what you have picked: 3 documents selected once there is a selection, and Select one or more documents to get started while there is none, so an empty list tells you the next step instead of counting nothing. On a narrow pane the pill shortens to the number alone; hover it to read the whole sentence.

The field Claira starts you onCopy Anchor Link

Claira remembers the field you are working in on this case and offers it as the starting point in the other modes. Prompt Lab and Bulk Scanning share one destination field: change it in either one, or in the bulk scan confirmation, and the other shows the same field straight away. Start Bulk Scan on # Documents in Prompt Lab therefore always writes to the field Prompt Lab shows. The same field seeds a new Multi-Code row and the From side of Field Migration.

Three things are worth knowing about it:

• It is yours alone. The field Claira remembers is personal to you, per case. Your colleagues each keep their own, and picking a field never changes what anyone else sees.
• It is only a starting point. Every picker stays fully editable, and changing it has no effect on a scan that is running, a scan that has already run, or a task already queued. A running scan keeps writing to the field it started with, and resuming a task writes to that task's field without changing your pickers.
• A disconnected field leaves the picker empty. If the field Claira was holding has since been disconnected from the case, the picker simply opens empty and waits for you. Claira never quietly substitutes a different field, because a scan written into a field you did not choose is far more work to undo than one more click.

Choosing a field does not require anything in the prompt box. You can open a case, pick your destination field, and write the prompt afterwards: the choice is saved on its own.

Each row in the picker also carries a small marker. A circle with a check means you have used that field before in this case; an empty circle means you have not used it yet; a clock means the field is still waiting on access from your case admin. The first two are about your own work, so a field a colleague has scanned into still shows as one you have not used. Hover any marker to read what it means.

The field you have chosen carries a check at the left of its row, as in any dropdown. In the Prompt Lab and Bulk Scanning pickers, hover that check to be reminded that this is also the field Claira will offer you for your next scan of that kind.

How to run a bulk scanCopy Anchor Link

1. In Nuix Discover, select the documents you want to scan from the browse list.
2. Open the Claira pane and choose one of these entry points:
   • Go to Bulk Scanning mode.
   • Stay in Prompt Lab mode and use the bulk-start button in the Prompt section.
3. Confirm your prompt and connected field are correct.
4. Review the confirmation details. Claira shows you:
   • The estimated token usage for this run next to your current token balance, at the top of the dialog, with a confirmation of whether the run fits within your balance or may incur additional fees
   • The number of documents in your selection
   • Your current scan input mode
   • The estimated duration for the task
   • The destination field where results will be written. For a Multi-Code run, this row instead shows a Multi-code scan summary with the number of fields that will be written to.
   • When your case has a Prompt Log field, a Write the prompt to each document's Prompt Log checkbox, with the name of that field underneath. Tick it to add this scan's prompt to the Prompt Log of every document the scan codes, so anyone reviewing a document later can see which prompt produced its value; earlier Prompt Log entries are kept. Leave it unticked to leave the Prompt Log unchanged. In cases you were already using, the box starts unticked; a case you open for the first time starts on your latest choice from your other cases. After that, Claira remembers your last choice for the case. Scans the Agent starts for you follow that remembered choice too. Hover the information icon next to it for a reminder of what it does. When the prompt is too long to be written to every document (see Very long prompts), the checkbox is unavailable and a note under it says so: the scan runs without the Prompt Log, and the prompt is still kept in Prompt History and in the task's details.
   • On cases where Background Processing is set up (background processing is not available in Claira Private), a Run as background processing task checkbox, offered for every scan type (Text, Image, Audio, Video and Auto), on single-field and Multi-Code runs alike. For an Image, Audio, Video or Auto scan, the dialog adds that Claira uploads each document's file first. If you have selected a model that background processing cannot run, the background scan uses Claira's default model instead, and the dialog says so. On a case with no API token yet, when Claira holds one you can use, the Execution section offers to connect it with one click instead (see Connecting a token from a scan or Field Migration).
5. Start the task:
   • In Prompt Lab mode, click Start Bulk Scan on # Documents (shown when more than one document is selected).
   • In Bulk Scanning mode, click Scan List.

Monitoring progressCopy Anchor Link

Once the scan starts, you can watch progress in real time within the Claira pane. The progress indicator shows how many documents have been processed out of the total.

A live results panel streams each completed document as it finishes, newest first, so you can watch results land in real time. To read one in full, hover your cursor over it: the entry expands, and the feed pauses while your cursor is on the list, so the entry you're reading stays in place instead of being pushed down as new results arrive. Move your cursor off the list and the feed resumes, adding everything that arrived while you were reading. For a Multi-Code run, each entry shows the extracted values as Field: value lines, one per destination field, the same way the single-document Multi-Code response is presented.

While the scan runs, the counters above the live results track each outcome separately: processed counts the documents that produced a result (the same ones listed in the live results panel), while skipped counts documents with nothing the scan could read (no readable text or media, text over the size limit, a file over 23 MB in an Image, Audio or Video run, or a file the AI model could not read), and failed counts documents that errored. Only documents that produced a result appear in the live results panel; skipped and failed documents are reflected in the counters only. Not sure why documents fail? Hover over the failed count for a plain-language explanation of the common causes, and confirmation that failed documents are not charged.

When the scan finishesCopy Anchor Link

Past the halfway mark, a short note under the progress bar says Halfway there., and Nearly done. from 90%.

When a scan running in your browser finishes, a summary card takes the place of the progress panel. It leads with the result, for example 2,908 documents coded, shows the same colored result bar with the number of documents coded, failed and skipped, and offers the next step: a suggested Insight for the task when there is one, and View details to open the full task. Close the card with the X in its corner; starting another scan also replaces it. The notification with the same counts still appears at the top of the pane.

When every document was coded, the card adds a small check, a friendly line and, when the run passes one, a milestone such as This case just passed 10,000 documents coded. When some documents failed, the card leads with the failures instead. You can switch these touches off in Settings: see Celebrations.

Adjusting the scan speedCopy Anchor Link

Live bulk scans (the runs that stay in your browser tab) include a Scan speed slider in the progress area, with five positions from Slowest to Fastest. It controls how many documents Claira works on at the same time:

• Slower positions ease the load on the AI service. Use them when you see documents failing with resource-availability errors: at the slowest settings these errors all but disappear.
• Faster positions finish the task sooner, but are more likely to run into resource-availability errors, especially during busy hours. Documents that fail this way are refunded automatically and can be scanned again from the Bulk Tasks list.
• Balanced, the default, deliberately runs well below Fastest: results arrive in the live results panel at a pace you can follow, and resource errors stay rare. Every new scan starts at Balanced.

You can move the slider at any time while the scan runs. The change takes effect right away for the next documents (documents already being scanned simply finish at their own pace), and the estimated duration updates to match the new speed. The slider applies to live runs only; background processing tasks are paced on the server.

There is no need to interact with the interface while the scan runs: adjusting the speed is entirely optional. Just keep the browser window open and let Claira work through the list.

Moving a live scan to the backgroundCopy Anchor Link

Started a scan in your browser and then need to close your laptop? You don't have to cancel it and start over. While a live scan is running, a Send to background button sits next to Cancel Scanning. It hands the rest of the run to Claira's servers and keeps everything already done.

Click it and Claira shows you how many documents are already coded and how many will finish in the background. Confirm, and Claira:

• Stops sending new documents from your browser and finishes the ones already under way, which takes a few moments.
• Passes the remaining documents to the servers under the same Task ID, so your Log Field reference (for example SC067) still finds the whole run in Nuix Discover.
• Leaves every document already coded exactly as it is. Nothing is scanned twice, and you are not charged a second time: the tokens for the whole run were reserved when it started.
• Retries the documents that failed during the live part of the run.
• Keeps writing the prompt to the Prompt Log, if you ticked Write the prompt to each document's Prompt Log when you started the scan. Documents already coded keep the single entry they got during the live part of the run.

For an Image, Audio, Video or Auto scan, Claira first uploads the files of the remaining documents from your browser, with the same Uploading files for Task #NNN progress a new background scan shows (see Uploading files for image, audio, video and Auto scans). Keep Claira open until the upload finishes; the scan then continues in the background.

Once the hand-off is done you'll see the same green Task #NNN is running in the background confirmation a background run shows, and it is safe to close Claira or Nuix Discover. Claira emails you when the scan finishes.

The button appears while a live scan is running and is available whenever the run qualifies for Background Processing. If it is greyed out, hover over it and Claira tells you why, most often because Background Processing is not set up for this case, or because the scan is running on a model that background processing cannot use. When the case has no API token yet but Claira holds one you can use, the button stays available: Claira asks Connect an API token and send to background?, and Connect and send connects the token and moves the scan in one step. On a Claira Private case the button is not shown: background processing is not available in Claira Private.

Monitoring background tasksCopy Anchor Link

When you start a background run, the live results panel is not shown: a background task processes everything server-side and streams nothing into your browser. In its place, Claira first shows an Assigning your Task ID… notice: keep Claira open for those few moments while the scan is handed to the servers. As soon as the Task ID is assigned, the notice is replaced by a green confirmation, Task #NNN is running in the background, which means it is now safe to close Claira or Nuix Discover. From that point on, you can follow the run in the Ongoing background tasks list. An Image, Audio, Video or Auto scan uploads its files between these two steps: see Uploading files for image, audio, video and Auto scans.

If assigning the Task ID takes longer than usual, for example on a slow connection, Claira tells you so and keeps checking whether the task started for up to five minutes: keep Claira open while it does. If it finds the task, the run carries on as normal. If it cannot confirm it, it asks you to check your bulk tasks before you start the scan again, because the task may already be running and a second start would scan the same documents twice.

When a bulk scan runs as a background processing task, a color legend sits at the top of the Ongoing background tasks list, and each task card shows a color-coded progress bar that fills from left to right as documents move through the run: green (Complete) for results already written back to Nuix Discover, blue (Scanning) for documents being processed by the AI, including those whose AI processing has finished and are waiting to be written back, amber for documents that are prepared and queued for AI submission, and pink (Skipped) for documents that will not be scanned. The amber label follows what the run reads: Text extracted on a Text scan, and File extracted on an Image, Audio, Video or Auto scan, where what was gathered is the document's own file. Pink covers every document set aside, whichever step set it aside: no readable text or text over the size limit on a Text scan, and no file the scan can read or a file too large to scan on the other modes, including the ones found while Claira was uploading the files. Skipped documents turn pink live, while the run is still going: they are not held in a pending color until the end. Not sure what a color means? Hover over its entry in the legend for a short, plain-language description of that step. Each segment shows its document count inside the bar; when a segment is too narrow to fit its number, hover over it to see the count in a tooltip. The numbers update whenever you refresh the Bulk Tasks view. There is nothing to configure, and you can close Nuix Discover at any time; the run continues server-side and Claira emails you when it finishes.

Background runs are built to ride out interruptions on their own: brief service hiccups, restarts, and long waits are absorbed silently and the task simply keeps going. Very long-running scans are continued automatically behind the scenes as well: the task just keeps going and the bar keeps advancing; you never need to restart anything. If you receive a failure email, it means the run genuinely stopped making progress and needs attention. Open Bulk Tasks and use Resume to continue it from exactly where it left off.

When a background task finishes. You don't need to keep Bulk Tasks open to find out. If a background task you started finishes while Claira is closed, a While you were away card appears at the top of Claira the next time you open it in that case, listing each finished task with its result and status. Choose View in Bulk Tasks to open the list, or close the card with its X. If the task finishes while Claira is open, in any mode, a notification tells you instead, for example Task #014 finished: 2,908 coded., with a View button. Each finish is announced once. Tasks you cancelled, and tasks other people started on the case, are not announced; you'll find them in Bulk scan task history.

Background runs support every scan type (Text, Image, Audio, Video and Auto), and single-field and Multi-Code scans alike. A Multi-Code background task codes every one of your configured fields for each document, exactly as the foreground run would; if some fields could not be written for a document, the task's document log says which ones. When you tick Write the prompt to each document's Prompt Log, a background task adds the same Prompt Log entry a live scan would to every document it codes.

Uploading files for image, audio, video and Auto scansCopy Anchor Link

A background Image, Audio, Video or Auto scan needs each document's own file, so Claira first uploads those files from your browser, both for a new scan and for Send to background.

• Keep Claira open while the files upload. Once the Task ID is assigned, the bulk scan card shows Uploading files for Task #NNN, with a count such as "120 of 500 files uploaded" and a Pause upload button. When the upload finishes, the scan runs in the background and the green Task #NNN is running in the background confirmation appears: from then on it is safe to close Claira or Nuix Discover, and the completion email arrives as usual.
• An interrupted upload waits for you. If Claira is closed or the upload is paused, the task waits under Ongoing background tasks with the status Uploading and a line such as "Waiting for files: 120 of 500 uploaded". Anyone working in the case can choose Finish uploading on that row, in Bulk scan task history or in the task details to upload the rest from their own browser. Files already uploaded are kept, and documents that person cannot open in Nuix Discover are skipped and not charged.
• After 24 hours, the scan starts with what it has. If nobody finishes the upload within 24 hours, Claira starts the scan with the files already uploaded; the remaining documents are not scanned and not charged. If no file was uploaded at all, the task is cancelled and fully refunded.
• Cancelling an Uploading task discards it. The background scan has not started yet, so there are no results to keep.
• A file that cannot be used is not charged. A background scan reads files up to 50 MB (a scan in your browser reads files up to 23 MB), and TIFF and JPEG 2000 images are converted automatically. A document whose file could not be downloaded, was larger than 50 MB, was not a readable format for the scan type, or was never uploaded gets an E-FETCH note in the destination field and is not charged.

A background media scan costs the same tokens as the same scan in your browser, and an Auto scan charges each document at the type it resolved to. Scans the Agent starts in Agent Mode with Image, Audio, Video or Auto always run in your browser; only text scans started by the Agent can run in the background.

Task namesCopy Anchor Link

Claira names each bulk task automatically from your prompt shortly after the run starts. You can change the name at any time:

• Rename it: click the task name in the Bulk Tasks list or at the top of the task details, type the new name, and press Enter (or click away) to save. Press Escape to cancel.
• Ask the AI for a new name: in the task details, click the small refresh icon next to the name (its tooltip reads Regenerate title with AI). Claira rereads your prompt and proposes a fresh name, useful when automatic naming didn't complete or the name doesn't capture what the run was about.

If a scan stops earlyCopy Anchor Link

A bulk scan runs in your browser tab. If the run is interrupted before every document has an outcome (for example the tab was closed, the connection dropped, or a burst of AI-service errors stopped the workers), the task is marked Incomplete instead of Completed, so unscanned documents are never silently presented as done.

An Incomplete task is easy to finish later:

• Open the Bulk Tasks tab and look for the amber Incomplete badge. The task details show exactly how many documents still need scanning.
• Click Resume Task to scan the remaining documents. Documents that already have results are not re-scanned and are not charged again. A Multi-Code task resumes with the fields and prompts it started with, whatever the Multi-Code card holds now.
• If you prefer not to finish the run, click Cancel task in the task details. The tokens reserved for the unscanned documents are released back to your balance.

A single-field task resumes with the prompt and Scan as setting it started with, even if you have since changed the prompt in Prompt Lab or the Scan as dropdown. If Claira cannot read the prompt the task started with, it does not resume the task and nothing is scanned. Try again in a moment, or start a new bulk scan for the documents that are left.

While a task is Incomplete, the tokens reserved for its remaining documents stay on hold so that resuming can never charge you twice. They are settled automatically when the task finishes or when you cancel it.

Cancelling a background task works differently. Clicking Cancel task on a background run first opens a dialog: if documents have already finished AI processing, it tells you roughly how many, "Roughly N documents have finished processing" (or generic wording when the count is not yet known), and offers three choices:

• Write back results & cancel: Claira saves the completed results to the destination field before stopping the task. You are charged only for the documents actually written; the tokens reserved for everything else are returned to your balance.
• Discard & cancel: the task stops without writing anything further. This is permanent (the completed-but-unwritten results cannot be recovered), and the tokens reserved for the unwritten documents are returned to your balance.
• Keep running: closes the dialog and lets the task continue as if nothing happened.

No email is sent for a cancelled task.

A cancelled background task is final, so it has no Resume Task button: the tokens reserved for its unfinished documents have already been returned to your balance. To scan the documents it did not finish, start a new bulk scan.

Background runs also protect completed work when something goes wrong while nobody is watching: if a scan hits a failure it cannot recover from, Claira automatically writes back everything that had already completed before marking the task failed, and the notification email reports honest counts of what was written and what was not. Documents that could not be completed get an explanatory ERROR_LOG note in the destination field, just like other per-document errors.

Where results goCopy Anchor Link

Results populate directly into the connected Nuix Discover field while the task is still running. You do not need to export or transfer anything -- the data flows straight into your existing review workflow. Foreground scans write each document's result as it completes, and background scans -- including very large ones -- write results back progressively in batches throughout the run rather than all at once at the end.

You can begin reviewing results in Nuix Discover as soon as documents start completing, even while the rest of the task is still running. Results that have already been written are kept even when a task does not run to completion: if you cancel a background task and choose to write back the completed results, or a run fails partway through, everything that finished stays in the field.

Finding a past taskCopy Anchor Link

The Bulk task history list holds every bulk scan run on the case, by anyone on the team, and it comes with two ways to narrow it:

• Search by task name, by the person who ran it, or by the task number. Both spellings of the number work, so 014 and 14 find the same task.
• Filter with the funnel icon beside the search box. It opens a panel listing Everyone, then you, then each of your colleagues; tick the names whose tasks you want to see. A small number on the icon says how many filters are on, and Clear filters at the bottom of the panel puts the list back to everything. Filters are not remembered: reopening Claira starts you on the full list.

Runs still going in the background are not in this list. They live in Ongoing background tasks just above it until they finish, so no run is ever shown twice.

Both the history list and the ongoing list use the same card layout, and the title of each card carries a Background tag when the run is server-side and an amber Cancelling tag while a cancellation is being drained. Hover either tag to read what it means.

Each finished task's card shows its result in one line: how many documents succeeded and how many failed, for example 1,372 succeeded · 66 failed. A cancelled task's line starts with Cancelled. A task still running, or one that stopped early, shows where it is instead.

To see why documents failed or were skipped, open the task. Under the counts, Why documents failed and Why documents were skipped list each reason once with the number of documents it covers, largest first, for example The AI model did not return an answer or No text to scan. The reasons are:

Failed and skipped documents are not charged. On a single-field task each failed document also carries a note in its destination field naming the error; see Error codes.

Which prompt version a task ranCopy Anchor Link

Open a task to see its details. Above the prompt, Prompt version names the version of the prompt the task ran, numbered the way Prompt History numbers it ("Version 4 of 5"), with the green Final badge when it is the version your team marked final. Below it:

• An amber note says This scan did not run the final version when another version of the same prompt is marked final, and names that version. This is the quickest way to spot a scan that ran a draft or outdated wording.
• When nothing is marked final, a note says whether newer versions of the prompt exist.
• Open in Prompt History opens that version's details, where you can compare it with the versions before and after it and see every other bulk scan that ran it.

The version is matched on the wording itself, so a scan is linked to its version whoever ran it, including bulk scans run before this link existed. A few tasks cannot be placed:

• Claira did not record which prompt version this scan ran appears for some Multi-Code scans run before this link existed, when Claira could not match the scan to its configuration with certainty.
• A task whose prompt is older than the entries Prompt History shows says so, rather than guessing a version.

Version numbers follow Prompt History's grouping, so they can change as your team adds versions: a scan that ran "Version 4 of 5" shows "Version 4 of 6" once a sixth version exists.

Comments on a taskCopy Anchor Link

Every bulk task has a comment thread, the same one prompts have in Prompt History. Use it to record what a run was for, so whoever opens the task later has the context: which sample it was, where its documents came from, what you were testing, or what you decided once you had reviewed the results.

• Open the task by clicking it in Bulk scan task history (or in Ongoing background tasks while it is still running). Comments is under the task's prompt.
• Type your comment and click Add Comment. It is saved with your name and the date, and everyone working in the case can read it.
• To remove a comment, click the bin icon beside it. You can delete only your own comments.

A task that has comments shows a speech-bubble icon and the number of comments on its card in the history list, so you can spot annotated runs without opening each one. Comments are also printed in the Bulk Task History Report, under each task's prompt.

Comments from the Agent. In Agent Mode you can ask Claira what the team noted on a task, or ask it to add a comment for you. When the Agent starts a bulk scan, it also leaves a note on the new task saying why it started it, what it is for and what the task does; the scan card shows that note before the scan starts. A comment the Agent writes carries your name and is marked Added by the Agent, and you can delete it like any of your own.

Deleted comments are recorded. Deleting a comment removes it from the task, but the deletion itself is kept for your organization's compliance records: who deleted which comment, whose it was and when. The text of the comment is not kept. Organization admins see these records in the Admin Portal's Activity feed.

Bulk Task History ReportCopy Anchor Link

For an audit-friendly record of every bulk task you've run on a case, click the download icon at the top of the Bulk Tasks tab. The PDF contains one card per task with:

• The task number, name, and media type badge (auto, text, image, audio, or video).
• Status, success rate, and the count of succeeded / failed / skipped documents.
• The full prompt text that was sent to the model.
• The customer-facing model name (e.g. "Claira Default (CA)") and the run configuration (temperature, language, destination field).
• Tokens used.
• The task's comments, each with who wrote it and when, and marked when the Agent wrote it.

The report opens on the most recent task and works backwards, so the run you are most likely looking for is on page one. A long task name wraps onto two lines on its card instead of being cut short, so two tasks named alike stay tellable apart. Every page of the report ends with a line naming Claira, the report, the case, and the date you exported it, with Page 3 of 11 opposite on the right, and from the second page onward a small running header repeats the report's title.

If the comments cannot be loaded while the report is being built, the report is still produced, and its summary says that comments could not be loaded, so a task printed without comments is not mistaken for one that has none.

This is the canonical record of what was run on the case, useful for QC reviews, defensibility, or sharing with a client.

Token usageCopy Anchor Link

Token usage depends on the Scan as dropdown selection. The per-document rate is charged only for documents the AI successfully scans: failed, skipped, and pending (cancelled) documents are refunded automatically when the task reaches a terminal state. If your plan renews before the task ends, the plan tokens it reserved and did not use are not returned. See What a bulk scan refunds.

• Auto mode (default): 1 to 20 tokens per successful document, set by the mode Claira picks for that document (text=1, image=5, audio=10, video=20). The task reserves the worst-case rate (20 / doc) up front and refunds the difference as each document resolves.
• Text mode: 1 token per successful document
• Image mode (single field): 5 tokens per successful document
• Audio mode (single field): 10 tokens per successful document
• Video mode (single field): 20 tokens per successful document

When Multi-Code is enabled, the per-document cost is the base media scan rate plus 1 flat token, the same regardless of how many active multi-code fields you configure (1 to 10 fields all cost the same):

• Text + Multi-Code: 2 tokens per document.

• Image + Multi-Code: 6 tokens per document.

• Audio + Multi-Code: 11 tokens per document.

• Video + Multi-Code: 21 tokens per document.

• Claira reserves the full task cost upfront and checks your token balance before starting; with overages off, a scan will not begin if it would exceed your available tokens.

• When the task finishes, any documents that did not complete successfully are credited back to your balance as a refund entry on the billing ledger.

• To check your current balance, look at the token count displayed in the bulk scan confirmation dialog or in the Usage popover.

• If a finished scan leaves the case with less than 15% of its monthly tokens, or using overage, the message reporting the finished scan offers Buy tokens. See When a bulk scan leaves you low.

What counts as a successful documentCopy Anchor Link

A bulk task processes every document you selected. At the end of the task each document is in one of these states:

• Completed: the AI returned a response. Charged. This includes a document whose field already holds exactly that answer, for example when you scan the same documents again with the same prompt.
• Failed: the AI returned an error, its answer could not be used or written to the destination field, or retries were exhausted. Refunded.
• Skipped: the document has nothing the scan can read: no extracted text, a file type the selected mode does not read, text or a file over the size limit, or a file the AI model could not read. Refunded.
• Pending: the task ended (cancelled, abandoned, or terminated for another reason) before the document was scanned. Refunded.

If the task is Incomplete (the scan stopped early; see If a scan stops early), the not-yet-scanned documents stay Pending and their reserved tokens stay on hold until you resume the task or cancel it.

The success / failed / skipped counts are also visible per task in the Bulk Task History Report.

• Keep one saved configuration per workflow to reduce setup drift.
• Record model, template, and field mapping choices in your matter log for auditability.
• When results vary unexpectedly, rerun the same sample before changing multiple settings at once.

Scan-as dropdown (auto / text / image / audio / video)Copy Anchor Link

Bulk scan uses Auto by default: Claira picks the best mode for each document at scan time, so a mixed production gets the right treatment without you needing to sort it first. Auto, Text, Image, Audio, and Video are all available on every plan, including Starter.

• Auto (default): Claira inspects each document and picks Text / Image / Audio / Video on the fly. Bills at the resolved mode's rate per document (1 / 5 / 10 / 20 tokens). Up to 20 tokens / doc is held at task creation; the difference is refunded as each document resolves to a cheaper mode. See Media scans for the full hierarchy.
• Text: Claira sends Nuix extracted text. 1 token/doc (single-field), or 2 tokens/doc in Multi-Code.
• Image: Claira attaches the source image / PDF file. 5 tokens/doc (single-field), or 6 tokens/doc in Multi-Code.
• Audio: Claira attaches the source audio file. 10 tokens/doc (single-field), or 11 tokens/doc in Multi-Code.
• Video: Claira attaches the source video file. 20 tokens/doc (single-field), or 21 tokens/doc in Multi-Code.

What the model receives by modeCopy Anchor Link

• Text mode: Claira sends your prompt plus Nuix extracted text in the request body.
• Image mode: Claira sends your prompt and attaches the source document. Accepted formats: PDF, PNG, JPEG, WebP, GIF, BMP, HEIC, HEIF.
• Audio mode: Claira sends your prompt and attaches the source audio file. Accepted formats: MP3, WAV, AAC, OGG, FLAC, M4A, AIFF.
• Video mode: Claira sends your prompt and attaches the source video file. Accepted formats: MP4, MOV, WebM, AVI, MKV, MPEG, 3GP, FLV, WMV.

If a file section is unreadable or missing, Claira prompts the model to state that limitation and provide best-effort findings.

If a scan fails because of input modeCopy Anchor Link

When a document cannot be scanned in the selected mode, Claira shows an actionable error. Where possible, Claira inspects the document's source files and tells you which mode would work. For example, a Text scan on an audio-only document writes "this looks like audio content. Try Audio scan" into the field.

Common examples:

• Source file unavailable or unsupported MIME for the selected mode: switch the Scan as dropdown to a different mode and rerun.
• Extracted text is missing on a Text scan: switch to the suggested media mode (or Image if no suggestion is available).

Next stepsCopy Anchor Link

• New to prompting? Start with the Prompting Overview.
• Need media scan details (image / audio / video accepted formats)? See Media scans.
• Want to understand your results? See Understanding Results.
• Encountering errors? Check Error Codes or Troubleshooting.

Need help? Contact us at support@claira.to.