Conflict Analysis (BETA)

Overview

The Policy Conflict Analysis tool allows Knowledge Managers (KM Admins) to proactively "health check" their knowledge base. It automates the detection of contradictory information across your published policy documents.

Instead of manually cross-referencing hundreds of files, this tool scans selected folders, identifies conflicting statements (for example, one document stating a "30-day return policy" while another states "15 days"), and provides a streamlined workflow to resolve them.

Conflicts are detected at the section level, not the document level. A single sentence deep inside a 60-page handbook can be flagged against a single sentence in a different document, and the result will point at exactly those two blocks.

Every conflict is rated by severity — Critical, High, Medium or Low — so you can fix the conflicts most likely to cause wrong answers first.

---

Before you begin

Understanding what gets scanned prevents most surprises later. When you run an analysis, Leena AI resolves your folder selection into a concrete article list by applying the following filters:

Two limits apply to the resulting list:

• A conflict group can contain a maximum of 1,000 published articles.
• Only one analysis can be active at a time per instance. If a colleague's run is pending or in progress, you cannot create or rerun a group until theirs finishes or is stopped.

---

Accessing the tool

You can access the module via the main Knowledge Management sidebar:

1. Navigate to the Knowledge Management dashboard.
2. Click on Conflict analysis.

---

Workflow 1: Initiating a conflict scan

To begin checking for inconsistencies, you must create a Conflict Group — a user-defined collection of folders you wish to analyze together.

1. Create a new analysis

From the main Conflict Analysis dashboard, click + Create conflict group.

2. Select content

A selection interface will appear displaying your folder hierarchy.

• Name of the conflict group: Give the group a unique name. Names must be unique within the environment — if the name is already in use you will be prompted to choose another.
• Browse & Select: Navigate through folders and sub-folders to check the boxes of the content you wish to scan. Selection is available at the folder level only — you cannot include or exclude individual articles.
• Search: Use the search bar to locate specific folders quickly.
• Capacity check: Pay attention to the running counter. It shows the number of published articles resolved from your selection, including everything in sub-folders. The limit is 1,000 articles per conflict group.

3. Run the analysis

1. Click Create.
2. Click Create and run on the confirmation modal to execute your conflict analysis.

Run statuses

Monitoring progress during a run

You do not need to wait for the full run to complete. Open the group while it is In progress to follow it:

• Progress bar: A progress bar at the top of the group shows how much of the analysis is complete, as a percentage. Until the first conflict is found it reads "No conflicts found yet. Analysis is still running..."; after that, "Analyzing articles for conflicts...".
• Live results: Conflicts are added to the page as they are detected, and the page refreshes automatically about every 30 seconds. The severity summary, the article list and the conflict count update with each refresh, so you can start reviewing early findings while the remaining articles are still being analysed.
• You can leave the page: The run continues in the background, and results are shown as they are found when you come back.

When the progress bar reaches 100%, the status changes to Successful and the final count is locked in. If you are on the page at that moment, an Analysis completed message appears briefly.

Stopping a run

Stop a run when you no longer need it — for example, if you selected the wrong folders or the scope is larger than intended.

1. Click Stop, either:
   • next to the progress bar inside the group, or
   • on the group's row in the Conflict Analysis list (while a run is in progress, Stop replaces Rerun).
2. The run ends and its status changes to Stopped. If you stopped it from inside the group, you are taken back to the Conflict Analysis list.

Once a run is stopped:

• The environment is free for another analysis — you or a colleague can start or rerun a group.
• A stopped run cannot be opened. To get results for the group, click Rerun when you are ready.

---

Workflow 2: Analyzing results

Once the status of your Conflict Group changes to Successful, you can review the findings. You can also open a group while its run is In progress to review conflicts found so far.

The conflict dashboard

Clicking on a group opens the summary view:

• Severity summary: A panel at the top shows the Total number of conflicts in the run and how many are Critical, High, Medium and Low. Hover over the info icon next to each severity for its definition. These counts always cover the whole run, whatever filters you apply.
• Articles with conflict: The number of articles carrying at least one conflict that matches your current filters is shown above the article list.
• Filters and search: Narrow the results by Severity and Conflict type, or search by article name. See Filtering results below.
• Conflict clustering: Results are grouped by document. If Document A conflicts with Document B, entries will appear for both.
• Prioritization: The list is sorted automatically to show documents with the highest number of unique conflicts at the top.
• New issues: Visual indicators highlight new conflicts that have appeared since the last time this group was run.
• Export: Download every conflict in the run, with its severity, for offline review or sharing with stakeholders. See Exporting conflicts below.

Understanding conflict severity

Every conflict is given one of four severity levels. Each conflict shows its severity as an icon at the top right of the conflict; hover over the icon to see the severity name.

Severity tells you how urgent a conflict is; the conflict type (T1–T5, below) tells you what kind of fix it needs.

Filtering results

Use the filters above the article list to focus on what matters most:

• Default view: The Severity filter starts on Critical and High. To see Medium and Low conflicts, add them to the filter, or clear it to show every severity.
• Filters apply everywhere on the page: both the article list and the conflicts shown in the detail view follow the selected filters.
• Filters are kept in the page URL: they survive a page refresh, and a copied link opens the group with the same filters applied.

Exporting conflicts

Once a run is Successful and has found at least one conflict, click Export conflicts at the top of the group to download an Excel workbook named after the conflict group (for example, Leave policies_Conflict_Report.xlsx).

• The export includes the severity of each conflict, color-coded, so stakeholders can prioritise offline.
• The export always contains every conflict in the run, regardless of the filters applied on screen.

Reviewing which articles were included

Each run records the exact set of articles it analysed. Open the article list from the run to confirm what was in scope — useful when a document you expected to see flagged does not appear, since it will show you immediately whether the article was included at all.

Detailed resolution view

Click on any document in the list to open the Detail View. This provides the context needed to fix the error.

Understanding conflict types

Every finding is classified into one of five categories. Knowing the type tells you what kind of fix is needed.

Fixing the issue

Start with Critical conflicts, then High, before moving on to Medium and Low. To resolve a conflict, click the Source Link provided in the detail view.

• For connector articles:
  • The link redirects to the KM article details page.
  • Action: Go to the source document (for example, the SharePoint or ServiceNow article) and make the change there. The information will update in KM during the next sync.
• For uploaded articles:
  • The link redirects to the KM article detail page.
  • Action: Make the required changes directly here, then save and publish.

Editing an article does not clear its findings. Results reflect the moment the run finished; only a rerun updates them.

Two alternatives to editing are often faster:

• Unpublish or archive a superseded document. It leaves scope immediately and stops conflicting with its replacement.
• State applicability explicitly ("This policy applies to employees in India only") where two documents differ legitimately.

---

Workflow 3: Verifying resolutions (reruns)

After you have edited your documents to resolve inconsistencies, verify the fix.

1. Return to the main Conflict Analysis dashboard.
2. Locate your original Conflict Group in the history list.
3. Click Rerun.

The new results are nested under the original group, creating a clear audit trail — you can show that a conflict count fell from one run to the next.

---

Knowledge Health cards

Two visualization cards within the Knowledge Health dashboard track these metrics. They are computed over different populations and will not reconcile arithmetically.

• Articles with conflicting information: The number of unique articles carrying one or more conflicts across your knowledge base.
• Active sectional conflicts: The total number of section-level conflicts, summed from the most recent completed run of each of your most recently created conflict groups (up to ten). Groups beyond that, and groups whose latest run is still in progress, do not contribute to this number.

Both cards link through to the Conflict Analysis module.

---

Troubleshooting

---

Frequently asked questions

Q: Which file types are supported?
A: The system supports all file types that are converted to PDF within the KM. CSV files are currently not supported for conflict detection. Detection also works on extracted text, so content that exists only inside images, screenshots, or charts is unlikely to be compared.

Q: What happens if I select more than 1,000 articles?
A: The system will prevent you from starting the run. You will need to deselect some folders or create narrower sub-groups.

Q: Does the system automatically fix the conflicts?
A: No. The system identifies and explains the conflict, but a human Admin must decide which policy is correct and manually update the source document. There is no precedence engine — the tool will not tell you which of two conflicting policies should win.

Q: Which conflicts should I fix first?
A: Start with Critical conflicts — direct contradictions that can lead to wrong answers or compliance risk — then High. Medium and Low conflicts are hidden by default; add them in the Severity filter when you are ready to review them.

Q: Can I stop a run that was started by mistake?
A: Yes. Click Stop next to the progress bar inside the group, or on the group's row in the list. The run is marked Stopped and the environment is free for another analysis. Rerun the group when you need results.

Q: Does the export follow the filters I have applied?
A: No. The export always includes every conflict in the run, together with its severity.

Q: Can I check a draft policy for conflicts before publishing it?
A: No. Only published articles are analysed.

Q: Does the analysis account for audience targeting?
A: Yes. The analysis considers audience assignments on each article. Two articles are compared only if their audiences overlap — that is, if at least some of the same users can see both. Articles targeted at entirely different groups (for example, one visible only to India employees and another only to US employees) are not flagged against each other, even if the content appears contradictory. This reduces false positives for organizations that use audience-based targeting to manage region- or entity-specific policies.

Q: Does the analysis account for effective dates?
A: No. A superseded policy that is still published will be flagged against its replacement. Unpublish or archive obsolete documents.

Q: Will two runs over identical content always give identical results?
A: Not necessarily. Detection is AI-based, so results can differ slightly at the margins between runs. Treat conflict counts as indicative rather than as an exact ledger.

Q: Does conflict analysis run automatically or on a schedule?
A: No. Every run is triggered manually. Results are a point-in-time snapshot and do not update as articles change.

Q: An article was renamed after the run — will the result still be correct?
A: Yes. Findings are stored against article identifiers, and names and folder paths are resolved when you open the results, so you always see current details.