Insights

Insights turn the per-document AI results you already have into a single distilled output — a chronology paragraph, a relevance summary, a PII report, an investigation narrative. Instead of reading 200 rows in a field one at a time, you point Claira at the results and tell it what you want.

Every factual claim in an Insight is followed by a green-italic citation to the source document so you can verify what it's based on, and the whole output can be downloaded as a PDF that lists every source document on the trailing pages.

When to use Insights

Common patterns:

• Chronology rollup — run a bulk scan that extracts the date and one-line summary from each document, then ask Insights to turn those entries into a single timeline paragraph.
• Relevance review summary — after a relevance bulk scan, ask Insights to summarise what the relevant documents collectively show about the matter.
• PII or sensitivity report — run a scan that flags personally identifiable information, then ask Insights to produce a single report describing what was found and where.
• Investigation narrative — run an extraction scan for an issue (e.g. communications about a specific event), then ask Insights to weave the extractions into a coherent narrative.

What you need before running an Insight

Either:

• A completed bulk scan task in this case — Insights will read the per-document AI results that the task already wrote, or
• A document selection in Nuix Discover where the documents already have values in a field you choose.

You also need a prompt describing what you want and how it should be structured.

How to run an Insight

1. Open Claira and switch to Insights mode in the mode menu.
2. In the New insight card at the top:
   • Choose a source:
     • Current selection — the chip shows how many documents you've selected in Nuix, and you pick which field's values to use.
     • Bulk task — pick one of your completed bulk tasks in this case. Claira uses the AI results that task wrote per document.
   • Type your prompt. Describe what you want and how to structure it. For example: "Summarise these chronology entries as a single paragraph timeline, citing each event's document."
3. Click (or press Cmd/Ctrl + Enter).

A new row appears in the Past insights list below. While Claira is working, the row shows a Generating badge. When the row turns Completed, click it to open the full-window Insight viewer.

Reading and revising an Insight

The full-window viewer has three areas:

• Revisions sidebar (left) — every revision of this Insight, oldest at the top. The active revision is highlighted in green; click any other revision to switch the main view.
• Reading pane (right) — the generated text with green-italic citations inline. Hover a citation to see the document ID; click it and Claira will focus the document in Nuix when available.
• Revise this Insight (bottom) — type what you'd like changed (e.g. "Make it shorter," or "Add a paragraph about the May correspondence") and click . A new revision appears in the sidebar; the original revision is preserved so you can compare or roll back.

Click below the body to expand the list of documents that contributed to the Insight.

Downloading the PDF

Click in the Insight viewer to save the currently selected revision as a PDF. The PDF contains:

• A header with the title, source description, and the revision number.
• The Insight body, with citations rendered green-italic inline so they match the in-app appearance.
• A Source documents table on the trailing pages listing every document the Insight references, with its document ID and the value the AI read from the chosen field.

The filename follows the pattern Claira-Insight-<title>-rev<N>-<YYYYMMDD>.pdf.

What the model sees

For each source document, Claira passes the model: the document ID and the value of the chosen field (i.e. the per-document AI result from the bulk task, or the field value on the selected document). The model is instructed to cite every factual claim with a [doc:DOCUMENT_ID] token, which Claira renders as the green-italic pill you see in the body.

The model is always Gemini 2.5 Pro at the highest reasoning level — Insights do not expose a model picker.

Limits and known constraints

• Phase 1 is capped at 1000 source documents per Insight. Larger sets will be supported in a future update.
• The audit pass that double-checks every citation against the cited document's source text is planned for a future revision. Until then, treat citations as the model's claim about where the fact came from and verify any that matter via the source document table or by clicking the citation to open the document in Nuix.

Related

• Bulk Scan — how to produce the per-document results that feed an Insight.
• Understanding Results — interpreting the per-document AI outputs an Insight summarises.