> ## Documentation Index
> Fetch the complete documentation index at: https://docs.kaireonai.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Live Console

> Real-time monitoring console for decisioning operations — live metrics, customer diagnostics, and action analysis.

The Live Console is KaireonAI's real-time monitoring dashboard for day-to-day decisioning operations. It brings together live decision metrics, customer-level diagnostics, and action analysis (Why-Not) in a single interface.

<Info>
  Access the Live Console at **Dashboards > Live Console** or navigate directly to `/operations/live` in the platform.
</Info>

***

## Business Value

| Persona                | How the Live Console Helps                                                                  |
| ---------------------- | ------------------------------------------------------------------------------------------- |
| **Operations analyst** | Monitor decision throughput, error rates, and latency in real time                          |
| **Marketing manager**  | Investigate why specific campaigns are under-delivering against targets                     |
| **Support agent**      | Look up a customer and see exactly which offers were shown (or suppressed) and why          |
| **Data scientist**     | Validate that model scores are flowing through the pipeline and producing expected rankings |

***

## Key Capabilities

### Live Decision Metrics

The dashboard shows real-time aggregates for the current tenant:

| Metric                 | Description                                                   |
| ---------------------- | ------------------------------------------------------------- |
| **Decisions/min**      | Number of Recommend API calls processed per minute            |
| **Avg latency**        | Mean decision pipeline response time in milliseconds          |
| **Error rate**         | Percentage of decisions that returned a 5xx error             |
| **Suppression rate**   | Percentage of candidate offers suppressed by contact policies |
| **Budget utilization** | Current spend vs. allocated budget across active campaigns    |

### Customer Lookup

Enter a customer ID to view their complete decisioning context:

* **Unified Profile** — demographics, interaction history, CLV score, active suppressions
* **Recent Decisions** — the last 20 decision traces with timestamps and outcomes
* **Active Journeys** — journey enrollments and current step
* **Segment Memberships** — which segments the customer belongs to

### Action Analysis (Why-Not)

From the customer lookup, select any offer to run a [Why-Not analysis](/decisioning/why-not-analysis). The Live Console renders the results inline:

* Decisioning gate pass/fail breakdown with reasons
* Contact policy evaluation with usage counts vs. caps
* Customer attribute values used in each evaluation
* Interaction history summary (impressions, last contact)

<Note>
  Why-Not analysis runs in real time against current rules and data. If you changed a decisioning gate 5 minutes ago, the Why-Not result reflects the new configuration.
</Note>

### Cross-Channel View

The operations console shows decisions across all channels:

| View             | What It Shows                                                                       |
| ---------------- | ----------------------------------------------------------------------------------- |
| **By channel**   | Decision volume and conversion rate per delivery channel (email, push, SMS, in-app) |
| **By offer**     | Top offers by impression count and conversion rate                                  |
| **By flow**      | Decision flow execution counts and average latency                                  |
| **Suppressions** | Offers suppressed by policy type (frequency cap, cooldown, budget exhausted)        |

***

## How It Works

The Live Console pulls data from several platform subsystems:

<Steps>
  <Step title="Decision traces">
    The Recommend API records sampled traces (configurable sample rate per tenant) that capture the full pipeline execution, including which candidates entered, which were filtered, and the final ranking.
  </Step>

  <Step title="Interaction summaries">
    Aggregated interaction data (impressions, conversions, value) per customer-offer pair, updated by the Respond API.
  </Step>

  <Step title="Real-time metrics">
    Prometheus-compatible metrics exposed by the API instrumentation layer (`withMetrics` wrapper on every route handler).
  </Step>

  <Step title="Why-Not API">
    On-demand diagnostic endpoint that replays the decision pipeline for a specific customer-offer pair.
  </Step>
</Steps>

***

## Configuration

### Enable Decision Tracing

Decision tracing must be enabled for the Live Console to show pipeline details:

1. Go to **Settings > Tenant Settings**
2. Enable **Decision Trace**
3. Set the **Sample Rate** (e.g., `0.1` for 10% of decisions)

<Warning>
  Setting the sample rate to `1.0` (100%) captures every decision. This is useful for debugging but increases storage usage and may impact performance at high volumes. For production, 5-10% is recommended.
</Warning>

### Dashboard Refresh

The live dashboard auto-refreshes every 10 seconds. Metrics are computed from the most recent 5-minute window for decisions/min and latency, and from rolling 24-hour windows for utilization and suppression rates.

***

## Supported Workflows

### Investigating Under-Delivery

<Steps>
  <Step title="Check the offer">
    Look up the offer in the Live Console. Check its status (active/paused), budget remaining, and total impressions.
  </Step>

  <Step title="Run Why-Not for sample customers">
    Pick 3-5 customers from the target audience and run Why-Not analysis for each. Look for patterns in blocking rules.
  </Step>

  <Step title="Review decisioning gates">
    If a specific rule is blocking most customers, check whether the rule's condition is too restrictive or the customer data is missing.
  </Step>

  <Step title="Check contact policies">
    If frequency caps are the primary blocker, consider adjusting the cap or switching to a different channel.
  </Step>
</Steps>

### Real-Time Incident Response

When decision latency spikes or error rates increase:

1. Open the Live Console live dashboard
2. Check the **Error rate** and **Avg latency** tiles for anomalies
3. Navigate to **Decision Traces** to find failing requests
4. Examine the trace detail for the specific pipeline stage that failed
5. Check the [Dashboards](/operations-reporting/dashboards) for correlated infrastructure metrics

***

## Related APIs

The Live Console UI is backed by these APIs:

| API                                               | Purpose                                            |
| ------------------------------------------------- | -------------------------------------------------- |
| [Decision Traces](/api-reference/decision-traces) | Query and view pipeline execution traces           |
| [Why-Not](/api-reference/why-not)                 | On-demand action analysis for customer-offer pairs |
| [Unified Profile](/api-reference/unified-profile) | Customer lookup with all data sources merged       |
| [Metrics Summary](/api-reference/metrics-summary) | Aggregated operational metrics                     |
| [Dashboard Data](/api-reference/dashboard-data)   | Pre-computed dashboard tile data                   |

***

## Next Steps

<CardGroup cols={2}>
  <Card title="Why-Not Analysis" icon="magnifying-glass" href="/decisioning/why-not-analysis">
    Deep dive into action analysis diagnostics.
  </Card>

  <Card title="Dashboards" icon="chart-mixed" href="/operations-reporting/dashboards">
    Business and operational dashboards for reporting.
  </Card>

  <Card title="Decision Traces" icon="timeline" href="/api-reference/decision-traces">
    Query raw decision trace records.
  </Card>

  <Card title="Unified Profile" icon="id-card" href="/api-reference/unified-profile">
    Aggregated customer data from all sources.
  </Card>
</CardGroup>