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

# Dashboard Concepts

> Understand dashboard cards, time windows, top-k logic, and operational interpretation

## Dashboard Mental Model

Dashboard is designed for **detect → validate → act** workflows. It emphasizes quick trend detection first, then links to deeper module-level investigation.

```mermaid theme={null}
graph LR
    A[Detect changes in Dashboard] --> B[Validate in drill-down modules]
    B --> C[Act on scaling routing configuration]
    C --> D[Measure outcome in Dashboard]
```

## Core Concepts

### 1) Summary Cards vs. Analytical Charts

* **Summary cards** provide compact, high-signal status snapshots.
* **Charts** provide comparative context across projects or models.

### 2) Time Window and Delta Interpretation

Each chart uses fixed windows:

* Last 24 Hrs
* Last 7 Days
* Last 30 Days

Deltas compare the current window against a prior equivalent baseline so teams can quickly assess trend direction.

### 3) Top-K Ranking

Usage and quality panels focus on top-ranked entities (for example, top 5 models) to keep the view actionable and prevent visual overload.

### 4) Multi-Dimension Monitoring

Dashboard balances several dimensions simultaneously:

* **Demand** (requests, API calls)
* **Performance** (latency, throughput)
* **Quality** (benchmark accuracy)
* **Cost proxy** (token metrics)
* **Operational posture** (endpoints, clusters, projects)

## Common Interpretation Patterns

| Signal pattern               | Likely interpretation      | Typical next step                       |
| ---------------------------- | -------------------------- | --------------------------------------- |
| Requests up, throughput flat | Capacity pressure building | Check scaling and cluster health        |
| Latency up, API calls stable | Efficiency regression      | Inspect slow projects and model changes |
| Usage up, accuracy down      | Quality drift under load   | Re-route or re-evaluate model mix       |
| Output tokens rising sharply | Cost profile change        | Review prompts and response limits      |

## Data-to-Decision Flow

1. Identify deviation in one chart.
2. Cross-check with related charts.
3. Validate at project/model/deployment level.
4. Apply operational change.
5. Re-check dashboard after rollout.

## Best Practices

<Check>
  Use one consistent time window across charts during a single review.
</Check>

<Check>
  Compare at least one demand metric and one quality metric before action.
</Check>

<Check>
  Treat dashboard as triage; use Observability for root-cause evidence.
</Check>

<Check>
  Document weekly baselines for team-level incident readiness.
</Check>