Conversation Logs give you a complete view of every interaction between users — and service integrations — and the AI assistant. Browse conversations, filter by channel, caller type, or confidence, review audit details for individual messages, and flag guardrail triggers as false positives. The page is reachable from the Log item in the main navigation.
The Conversation Logs page displays conversations as cards with user info, confidence scores, and response times.
Browsing Conversations
Each conversation card displays:
| Element | Description |
|---|---|
| User avatar and name | The user or credential that started the conversation |
| Channel badge | The interface or messaging channel (Web Chat, Teams, API, MCP, and more) |
| Message count | Number of messages in the conversation thread |
| Timestamp | When the conversation occurred |
| Question text | The user's query |
| Confidence score | AI confidence as a percentage with a color-coded progress bar |
| Response time | Processing time in milliseconds |
Click any card to open the details drawer on the right side of the page. The selected card is highlighted with a colored left border.
Filtering and Search
Search
Use the search bar at the top to find conversations by user name, question text, answer text, or session ID. Search is debounced — results update 300 ms after you stop typing.
Advanced Filters
Click Filters to open the advanced filters popover. The popover groups every available filter in a single panel so you can combine them without leaving the page.
The Advanced Filters popover groups every filter control behind a single button.
| Filter | Options | Purpose |
|---|---|---|
| Channel | Web Chat, Mobile App, Teams, WhatsApp, SMS, Phone, Email, API, CLI, MCP, or All | Restrict conversations to a single messaging or integration channel |
| Caller Type | Human, Application, Agent, or All | Restrict to conversations produced by a specific caller class |
| Response Time | 0–10 seconds (slider) | Cap the maximum response time shown |
| Confidence Level | 0–100% (slider) | Cap the maximum confidence score shown |
| False Positives Only | Toggle | Show only conversations with at least one flagged guardrail result |
Active filters appear as chips below the search bar. Click the X on any chip to remove that filter, or click Clear All in the popover footer to reset everything in one step. Click Apply to commit your selections.
The Caller Type filter is most useful when combined with the Channel filter. For example, selecting MCP channel and Agent caller type isolates traffic from AI agents connected through the MCP server — a common first step when investigating an automation issue.
Channel Reference
The Channel filter includes every interface that can produce a conversation, not just the traditional human-facing channels. This makes it possible to investigate programmable traffic directly from the log view:
| Channel | Origin |
|---|---|
| Web Chat | AskRAI web widget |
| Mobile App | Embedded chat SDK in a native mobile app |
| Teams | Microsoft Teams bot |
| WhatsApp Business integration | |
| SMS | SMS gateway |
| Phone | Voice channel |
| Email-to-ticket integration | |
| API | Direct calls to the public API with a credential |
| CLI | Requests issued through the askrai command-line client |
| MCP | Calls from an AI agent through the MCP server |
Caller Type Reference
Caller Type describes who produced the request, regardless of which channel they used:
| Caller Type | Description |
|---|---|
| Human | An interactive end user — always reported for web, mobile, Teams, WhatsApp, SMS, and phone traffic |
| Application | A back-office service or automation that calls the API with a service credential |
| Agent | An AI agent that consumes AskRAI through the MCP server or the API with an agent credential |
Filters are persisted in the URL as query parameters. Share the URL with a teammate to give them the same filtered view.
Sorting
Conversations can be sorted by user name, channel, date/time, confidence score, or response time. The default sort is by date/time descending (newest first).
Conversation Details
Click a conversation card to open the details drawer with two tabs: Overview and Audit.
The details drawer shows thread information, user details, and conversation statistics.
Overview Tab
The Overview tab displays:
- Thread info — thread ID (copyable), message count, first and last message timestamps
- User info — display name, user ID (copyable), role, and channel — or credential name and caller type for programmable traffic
- Conversation stats — average confidence, average response time, total processing time, and AI sources used
Audit Tab
Select a message in the conversation thread (listed below the tabs) to view its audit record. The Audit tab shows:
AI Confidence — the confidence score as a percentage with a color-coded progress bar. If the response also has a vector confidence score (from knowledge base search), it is displayed separately.
Nearest Knowledge Base Match — when the confidence score is below the medium threshold, this section shows the closest matching question and answer from the knowledge base.
Governance — compliance status (Compliant, Not Compliant, or Not Checked), checked timestamp, reasoning, and per-guardrail results. Each guardrail result shows its compliance status, guardrail ID, and reasoning.
Escalation — the confidence band (High, Medium, or Low), whether the conversation was escalated, the ticket ID (if applicable, clickable to navigate to the ticket), and the escalation reason.
Click any message in the conversation thread to switch the Audit tab to that message's audit record. By default, the tab shows the most recent message.
False Positive Marking
When a guardrail evaluation produces an incorrect result — for example, flagging safe content as non-compliant — you can mark it as a false positive so it no longer counts against the block rate or triggers escalation.
Open the Conversation Details
Click a conversation card to open the details drawer, then switch to the Audit tab.
Find the Guardrail Result
In the Governance section, locate the guardrail result you want to flag. Each guardrail row shows its compliance status and a flag icon.
Flag as False Positive
Click the flag icon next to the guardrail result. A confirmation dialog appears where you can optionally enter a reason for the flag.
Confirm
Click Flag as False Positive to save. A red "False Positive" chip appears next to the guardrail result to indicate it has been flagged.
To remove a false positive flag, click the red flag icon on a flagged guardrail and confirm the removal.
False positive flags are per-guardrail, per-message. Flagging one guardrail result does not affect other guardrails in the same conversation or other conversations.
Field Reference
Conversation Card Fields
| Field | Description |
|---|---|
| Display Name | The user or credential that issued the request |
| Channel | Interface or messaging channel (Web Chat, Teams, API, MCP, …) |
| Messages | Count of messages in the conversation thread |
| Timestamp | Date and time of the conversation (format: MMM D, YYYY h:mm A) |
| Question | The user's query text |
| Confidence | AI confidence score as a percentage (0–100%) |
| Response Time | Total processing time in milliseconds |
Audit Record Fields
| Field | Description |
|---|---|
| Audit ID | Unique identifier for the audit record (copyable) |
| AI Confidence | Confidence score from the AI model (0–100%) |
| Vector Confidence | Confidence score from knowledge base vector search (when available) |
| Compliance Status | Whether the response passed all guardrail checks |
| Escalated | Whether the conversation triggered an escalation rule |
| Ticket ID | Link to the created ticket (if escalated) |
| Processing Time | Time taken to generate the response (milliseconds) |
| Caller Type | Human, Application, or Agent |
Related Pages
- Dashboard — view aggregated confidence, caller type, and interface metrics
- Tickets — manage tickets created by escalation rules
- Guardrails — configure the guardrails evaluated in audit records
- Programmable Access — manage the service credentials that appear as API, CLI, and MCP conversations
- Confidence Thresholds — adjust the bands that drive the confidence filter