The Risks tab lists every risk finding linked to the current document — both AI-detected results from automated checks and manual annotations added by your team. It is the central place to review, refine, and sign off on what Emma (and your colleagues) flagged in the file. In addition to these findings, Emma surfaces AI-identified “Additional Risks” that might represent potential issues not covered by the existing checks.

For creating new findings by drawing on the PDF, see PDF viewer — Creating a manual risk. For Matrix-level risk management, see Checks and Risks in the Matrix.

Why this matters for deal teams

A single view of all flagged risks (including those the standard check set might miss) helps ensure your diligence workstream captures potential deal-breakers. AI-surfaced additional risks can highlight non-standard exposures or missing clauses that may not be present in a standard checklist, supporting more complete disclosure and negotiation preparation.

Tab header and counts

The tab label shows Risks (n) where n is the number of relevant findings excluding "No risk" results. Findings marked No risk do not appear in the count or list.

If the document failed AI processing, an amber banner explains the limitation. You can still add manual findings, but automated check results may be incomplete.

Three main sections

The Risks tab is divided into three areas:

Document-level recommendations

At the top, Document-Level Recommendations holds deal recommendations tied to the whole file rather than a specific check — for example, "Request an updated version before closing" or "No action needed".

Each recommendation has:

To manage recommendations:

• Click Add recommendation to create a new entry
• Click the pencil icon to edit inline
• Click Delete to remove one
• Multiple recommendations can coexist — use the type field to categorise them for the Red Flag Report

Recommendations appear in the report editor and export alongside per-check findings.

Risk-level findings and recommendations

Below the document-level section, findings are grouped by risk level:

Each group is a collapsible panel showing the count of findings at that level. Expand a group to see individual findings.

Additional Risks (AI Scan)

Below the regular risk groups, Emma displays a separate Other potential risks found by AI section (collapsed by default, not shown if empty). These "Additional Risks" are:

• Flagged by AI scans specifically for potential High or Medium risks that are not covered by any of the checks already run on this file.
• Often represent missing clauses, unusual exposures, or non-standard issues that static checklists may not pick up.
• Clearly labelled as "Not yet in the report" with a blue sparkle icon, and separated from regular risks.

Each additional risk entry shows:

• A short summary (markdown supported)
• Risk level (High/Medium), colour-coded
• Navigation controls if bounding boxes (PDF highlights) are present; these work exactly like for standard risks

Click to expand a risk and read the full summary. If the finding points to missing content rather than a flagged paragraph, it will say so explicitly.

Navigating and promoting additional risks

• You can navigate between bounding boxes for Additional Risks using the same arrow controls as for standard risks.
• Clicking an additional risk row will scroll the PDF to the highlighted location (when available) and select it in the sidebar. Opening from a chat citation or deep link will auto-expand the section and focus the correct item.
• Promote to report: Click Add to report to promote an Additional Risk. This makes it a regular, reportable risk (creating a manual check/answer entry), moving it into the regular risk list. From there, manage as you would any other risk.
• Only Additional Risks that have not yet been promoted appear in this section.

This flow gives you a chance to audit Emma's suggestions for gaps and decide what is material enough to add for client or report purposes.

Understanding a finding row

Each regular finding corresponds to one check (a due-diligence question Emma runs). A row shows:

Click anywhere on a finding row to:

1. Select it in the sidebar (highlighted state)
2. Scroll the PDF to the linked bounding boxes
3. Show the highlights for that finding on the document

When arriving via a deep link (from Matrix, chat, or report), the app expands the correct group or section and focuses the selection automatically.

Viewing AI reasoning for a finding

Next to the paragraph-navigation controls, the AI reasoning button (brain icon) appears if further detail about the AI's decision is available.

• Click the button to open a window showing:
• Why this was flagged
• Why this risk level was assigned
• All content supports Markdown.

If no AI reasoning is available, the button is hidden.

AI vs manual findings summary

A summary line below the section header tells you the composition of findings in this document:

Small AI/Human icons reflect the same information visually.

Human review workflow:

1. Review each AI finding — read the summary and check the PDF evidence
2. Adjust the risk level if Emma over- or under-classified
3. Edit the summary to add context; saving marks the finding as human-classified
4. Delete false positives
5. Add manual findings for issues Emma missed (via the PDF viewer)
6. When satisfied, use Approve in the sidebar header and choose to mark AI risk levels as human-reviewed

Editing a finding

Inline summary edit — click the summary text to open the markdown editor. Saving updates the finding and marks it human-classified if it was AI-generated.

Full edit dialog — click the pencil icon to open the complete finding form where you can:

• Change topic and check assignment
• Adjust risk level
• Edit the summary
• Add or remove bounding boxes (the currently selected boxes on the PDF are included)
• Create a new check on the fly if none fits

Risk level change — use the dropdown on the finding row for a quick level change. PDF highlight colour updates immediately.

Delete — remove a finding entirely. This deletes the answer for this document/check combination and removes all linked bounding boxes from the PDF.

Show and hide highlights on the PDF

Each risk-level group header has an eye icon:

• Eye open — highlights for this level are visible on the PDF
• Eye crossed out — highlights are hidden on the PDF (findings remain in the sidebar)

Use this to focus on High risks first without removing Medium or Low findings from the record.

Per-finding recommendations

Expand a finding to see its recommendations subsection (when present). These are check-specific recommendations — distinct from document-level recommendations at the top of the tab. Types (Pre-closing, Closing action, etc.) flow into the Red Flag Report under that risk.

Collaboration and presence

When another team member is editing a finding's summary in the report editor or the viewer, Emma shows an Editing by [name] badge and locks the field to prevent overwrites.

Changes sync live:

• Risk level changed in the viewer updates Matrix and open report editor
• Risk edited in the report updates the viewer if open on the same document
• New manual finding appears in the Matrix column for that check

Empty state

When no relevant findings exist, the tab shows a green shield icon with "No risks detected". This means every check returned No risk or nothing relevant. Verify in the Matrix that checks are assigned to this document's type.

Bundled documents

When the open file is a bundle main document with PDF annexes, the Risks tab aggregates findings from all files in the bundle. Selecting a finding scrolls to the correct file's page within the merged PDF view.

Chat assistant integration for additional risks

When you ask the Emma chat assistant for risk summaries or specific findings, it now:

• Surfaces unconverted Additional Risks clearly: Badges and tooltips mark these as "Found by AI · Not yet in the report" both in the chat output and risk badge overlays.
• Explicitly calls out when a cited risk has not yet been added to the report, so you know if a finding is only present in AI findings, not in the signed-off due diligence risk list.
• Click-through navigates to the correct additional risk in the Risks tab, expands the section, and scrolls the PDF to the relevant spot (where available).

This helps reviewers trace the origin of a suggestion and check whether the new issue needs to be escalated for team discussion or placement in the live deal report.

Improved navigation and selection state

Emma now strictly enforces that only one risk — either a regular finding or an AI additional risk — is active at any time. When you select an additional risk, any previously selected standard risk is automatically deselected (and vice versa). This avoids clashing highlights and ensures auto-scroll and sidebar navigation always focus on your current review action, making risk review and hand-off in M&A workflows more reliable.

Related workflows

If you need additional help with the Risks tab or encounter any other problem, don't hesitate to reach out through the chat bubble in the bottom right or contact [email protected].

Updated on: 23/07/2026