View trace charts
Navigate to your project, then open the Overview tab. Adaline displays a dashboard of metric charts, each showing a time-series view of a specific performance dimension aggregated per trace:
View span charts
Navigate to your prompt, then open the Monitor tab. You will see all the spans logged for that prompt. In the top right, click the chart view toggle to switch from the span list to aggregated charts for that prompt’s spans.
Available metrics
The following metrics are automatically computed from your logged data, aggregated per trace:| Metric | What it measures |
|---|---|
| Logs | Total number of traces per unit of time. |
| Latency | End-to-end trace duration. |
| Input tokens | Input tokens across all Model spans in each trace. |
| Output tokens | Output tokens across all Model spans in each trace. |
| Cost | Cost (in USD) across all Model spans in each trace. |
| Eval score | Continuous evaluation score. Failed evaluations score 0, passed score 1. |
Percentile and average aggregations
The Logs chart shows total count. For all other metrics (latency, input tokens, output tokens, cost, and eval score), Adaline provides multiple aggregation modes so you can analyze both typical and tail-end behavior:
| Aggregation | What it shows |
|---|---|
| Avg | The mean value across all traces in the time bucket. Best for tracking overall trends. |
| P50 | The median — 50% of requests are at or below this value. Represents the typical user experience. |
| P95 | The 95th percentile — only 5% of requests exceed this value. Surfaces latency or cost issues affecting a meaningful minority of users. |
| P99 | The 99th percentile — only 1% of requests exceed this value. Catches the worst-case outliers that SLA commitments often target. |
Select a time window
Charts support multiple time granularities. Choose the window that matches your analysis needs — from last hour for real-time debugging to last month for trend analysis: Available windows include last hour, last day, last week, last month, or a custom date range. The chart automatically adjusts its data point density to match the selected window.
Inspect data points
Hover over any data point to see the precise value at that specific time:
What to look for
Use charts to identify operational patterns and anomalies. Here are common signals and how to act on them:| Pattern | What it means | Action |
|---|---|---|
| Latency spike | A sudden increase in response times. | Check for model rate limiting, increased prompt complexity, or provider outages. Drill into the affected traces to find the slowest spans. |
| Cost increase | Spending is growing beyond expected levels. | Review token usage charts — prompts may be getting longer, or a more expensive model was deployed. Filter spans by cost to find the most expensive requests. |
| Eval score drop | Quality is declining on live traffic. | Investigate recent prompt or model changes. Filter logs by evaluation results to find failing cases. |
| Traffic surge | Request volume increased significantly. | Verify capacity and rate limits. Check for unexpected bot traffic, viral usage, or a new feature launch driving volume. |
| Token usage growth | Average token consumption is trending up. | Review prompt length and context windows. Multi-turn chats accumulate tokens over time — consider summarization or context pruning strategies. |
| Flat eval score at 0 | All evaluated requests are failing. | Your evaluator configuration may be too strict, or a recent change broke the prompt. Review continuous evaluation settings and spot-check a few spans. |
Next steps
Analyze Log Traces
Drill down into individual request flows.
Analyze Log Spans
Inspect individual operations within traces.
Setup Continuous Evaluations
Add quality scores to your charts.
Filter and Search Logs
Find specific traces with filters and metadata search.