Single ReviewCopy Anchor Link

Single review is the process of scanning one document at a time through Claira. It is the fastest way to test a prompt, spot-check results, or review an individual document that needs attention. Every scan you run this way gives you immediate feedback, making it the natural starting point before scaling to bulk operations.

When to use single reviewCopy Anchor Link

• Testing prompts. Before committing tokens to a bulk scan, run your prompt on a few individual documents to see how the AI responds: single scans are free on every plan.
• Spot-checking. After a bulk scan, revisit specific documents to verify that results look correct.
• Reviewing individual documents. When you need the AI's analysis of a particular document outside of a bulk workflow.
• Iterating on prompt wording. Adjust your prompt, scan the same document again, and compare outputs side by side.

How to run a single scanCopy Anchor Link

1. Open a document in your Document Viewer pane within Nuix Discover.
2. In the Claira pane, write a new prompt or select a saved prompt from the Prompt area.
3. Optional: choose what Claira sends to the model in the Scan as dropdown next to the scan button. Auto is selected by default: it sends the document's own file when that is a PDF, image, audio or video file the model can read, and its extracted text otherwise. Pick Text, Image, Audio or Video to decide yourself. See Media scans for the full list of accepted file types per mode.
4. Click Scan Document.
5. The AI's response appears in the Results area of the Claira pane within a few seconds.

That is all it takes. The result is shown immediately in the Claira panel, and if you have a field connected, it is also written to that Nuix Discover field.

Reviewing and editing resultsCopy Anchor Link

After a single scan, you can review the AI's output directly in the Claira pane before it is finalized. This gives you an opportunity to:

• Read the full response and confirm it meets your expectations
• Edit the result if needed before saving it to the connected field
• Decide whether your prompt needs refinement

In Multi-Code, prompt reuse is available directly in the panel: use View history or Quickstart to insert from history, templates, or the generator: Claira will ask you to pick the shared instruction, an existing field row, or a new row (up to 10), then append or replace if that spot already has text. The choice starts on the destination you picked last time.

Recording the prompt in the Prompt LogCopy Anchor Link

When your case has a Prompt Log field, a small Prompt Log section sits below the AI response in Prompt Lab and in Multi-Code. It is closed by default, and its header says On or Off. Open it to find the Also write the prompt to the Prompt Log checkbox, with the name of the field underneath. Tick it and each save (Apply in Prompt Lab, Save to fields in Multi-Code) also adds the prompt behind the value to the document's Prompt Log, so anyone reviewing the document later can see how it was produced; earlier entries are kept. Leave it unticked to save the value on its own. Without a Prompt Log field on the case, none of this appears.

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. Claira remembers your choice for the case as soon as you change it, and the same choice applies in Prompt Lab, in Multi-Code and when you save an Agent answer to a field. Bulk scans have their own checkbox, in the bulk scan confirmation dialog (see Bulk Scan). Hover the information icon beside the checkbox for a reminder of what it does.

A Prompt Log entry is limited to about 300,000 characters. When the prompt is longer than that (see Very long prompts), the save still stores the value, nothing is added to the document's Prompt Log, and the message after the save says so.

When the destination field already holds a valueCopy Anchor Link

Claira adds a value to the destination field and never replaces what is already there. This applies to every save of a single result: Apply in Prompt Lab, Save to fields in Multi-Code, and saving an Agent answer to a field.

• A field that can hold several values, such as a Memo field, keeps what it holds and gains the new value.
• A field that holds one value and already has a different one is left unchanged. Claira tells you so instead of reporting the save as done. To put the new answer there, clear the field in Nuix Discover first, then save again.
• Saving an answer the field already holds is not an error: the field has it, so Claira reports it as saved.
• In Multi-Code, the summary after Save to fields names the field rows left unchanged because their field holds a different value.

Using single review to prepare for bulk scansCopy Anchor Link

The most effective way to prepare for a bulk scan is to build your prompt through repeated single reviews:

1. Start with a draft prompt. Write your initial instructions and scan a document you already know the answer for.
2. Compare the AI's result to your expected output. Does it match? Is the format correct? Are the key details captured?
3. Refine and rescan. Adjust your prompt wording and scan the same document again. Small changes in phrasing often produce noticeably different results.
4. Test on diverse documents. Once the prompt works on one document, try it on documents that are clearly relevant, clearly not relevant, and a few edge cases.
5. Move to bulk. When you are confident across your sample, proceed to Bulk Scan.

Next stepsCopy Anchor Link

• Ready to scale? See the Bulk Scan guide.
• Need prompting help? Visit the Prompting Overview.
• Want to understand what the AI returns? See Understanding Results.

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