Review readiness, audit, and exports

Beta

The ITRS Agentic SRE app is currently available as a beta release. Features, behavior, and documented procedures are subject to change without prior notice during ongoing development.

Use this page when you need to confirm that chat can run, review what the app recorded, or take a conversation record out of the Web Console.

When Usage is enabled, Admin > AI > Usage is marked Preview. That page counts AI usage against the license entitlement. Without a license to count against, the page is incomplete.

Review service readiness in Status Copied

Admin access

Status, Audit, and tenant-wide export require access to Admin > AI. Exporting your own conversation from the chat uses a separate permission and does not require that access. Available sections can vary by deployment. For day-to-day chat, see Use Agentic SRE for operations and support in ITRS Analytics.

If Status is enabled in your deployment, use Admin > AI > Status to review whether the services required by the Agentic SRE app are ready.

The Status page provides live information for:

• LLM Readiness — Shows the number of configured LLMs and whether chat is ready. You can test individual LLMs from this card. To add a model, see Configure language models.
• Documentation Index — Shows whether the index, documents, and embedding model are loaded
• Entity Index — Shows whether the entity index is available, its current build phase, the number of indexed entities, and the number of received entities. While the index is building, the card shows progress for the embedding pass

The overall status can be Operational, Degraded, or Unavailable. Review the individual cards when the app reports reduced capability or an unavailable component.

If the installation has features enabled beyond the default release, Status also shows Feature configuration. That card lists those features under Enabled beyond the production release. A default installation does not show this card.

The AI chat header also shows a status indicator. Administrators can select this indicator to open the Status page.

Review AI activity in Audit Copied

If Audit is enabled in your deployment, use it to review recorded AI conversations and related activity.

Use Audit and chat history for different purposes:

• Chat history is a way to reopen, rename, archive, and restore your own previous conversations from the chat. See Use chat history if it is enabled.
• Audit is an administrative view of recorded AI conversations and related activity.

Chat history contains your own AI chat conversations. Audit provides administrators with tenant-wide activity, including conversations from all users and activity that is not added to user chat history, such as Eval runs and LLM connection tests.

• use chat history when you want to continue your own earlier work

• use Audit when you want to review tenant-wide activity in more detail, inspect turns, or export records

  

1. Go to Admin > AI > Audit.
2. Review the list of recorded conversations. Each entry can show details such as Title, LLMs Used, Exchanges, Tokens, Created, and Status.
3. Use the available filters to narrow the list when you need to find a specific conversation or time range.
4. Use Refresh to reload the Audit list.
5. Open a conversation from the list to review the recorded exchange in more detail.
6. In the conversation detail view, review the summary information, including the LLMs used, exchange count, average latency, total tokens, user and team information, and conversation status.
7. Review the conversation replay to inspect the recorded prompts and responses.
8. If turn replay is available, select Inspect turn on a turn entry to open the turn inspection drawer.
9. In Turn inspection, review the event timeline for that turn. This view can help you examine the recorded sequence of events for the selected exchange in greater detail.
10. Review the feedback indicator for a turn to see whether the user approved or disapproved the response. Point to the indicator to review an optional feedback comment. Users submit that feedback from the chat. See Provide feedback on an AI response.
11. Export the conversation when you need to keep or share it. From the detail view or the list, you can Download as Markdown, Download as CSV, or Download full trail (JSON). The JSON trail is the full record described in Export a conversation. Downloading another user’s conversation requires permission to review tenant-wide audit activity.

Use conversation details as follows:

• Review LLMs Used to confirm which model or models were involved in the conversation.
• Review Exchanges to understand how many turns were recorded.
• Review Tokens to understand the scale of the interaction.
• Review Created and Status to confirm when the conversation occurred and whether it completed successfully.

If turn replay is available, each turn can also show:

• Turn status
• Duration
• Token count
• User prompt
• LLM used for the response
• Assistant response

Use Inspect turn when you need a more detailed view of a single exchange. In the turn inspection drawer, review the event timeline and use the available categories to focus on the part of the turn that you want to inspect, such as LLM activity, tools, retrieval, or routing.

For example, if you need to review a production support conversation, open the audit entry and confirm which LLM answered, how many exchanges occurred, how many tokens were used, and whether the conversation completed successfully. If a specific turn needs closer review, use Inspect turn to open the detailed event timeline for that exchange.

Export a conversation Copied

Export a conversation when you need the full record outside the Web Console, for example to attach to a support request. The JSON file contains each turn’s question and answer, the agent and routing decision, the entities in scope and where each one came from, every tool call with its arguments and result, views, entity tiles, model usage, and any error that was shown.

You can export in two places. The two permissions are separate. Permission to review Audit does not include permission to export your own conversations from the chat, and permission to export your own conversations does not include other users’ conversations.

• Your own conversation — In the chat header, select Export conversation. In chat history, open the conversation menu and select Export. The control is shown only when your role includes this permission and the conversation has a turn to export. By default, the user role includes it.
• Any conversation in the tenant — In Admin > AI > Audit, select Download full trail (JSON). This requires permission to review Audit. By default, the admin role includes it.

Each export is recorded on that conversation. Markdown and CSV downloads from Audit are transcripts of the conversation. The JSON trail is the full record.