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

# Overview

> The TruLayer data model in one page.

TruLayer models an AI application as a hierarchy of **traces** (end-to-end units of work) made up of **spans** (individual steps), grouped optionally into **sessions** (user conversations). Everything else — evals, feedback, metrics — attaches to those traces.

## The hierarchy

```text theme={null}
Session
 ├── Trace (one user request, one cron run, one agent step)
 │    ├── Span (LLM call)
 │    ├── Span (vector search)
 │    ├── Span (tool call)
 │    └── Span (another LLM call)
 └── Trace (the next request in the same conversation)

Attachments on any trace:
 ├── Event       (discrete log within a trace)
 ├── Feedback    (human label — thumbs up/down, score, comment)
 └── Eval result (automated score — correctness, hallucination, etc.)
```

## Concepts

<CardGroup cols={2}>
  <Card title="Trace" icon="route" href="/concepts/traces-and-spans">
    One end-to-end unit of work — typically one user request or one agent turn.
  </Card>

  <Card title="Span" icon="bars-staggered" href="/concepts/traces-and-spans">
    A step within a trace — an LLM call, retrieval, tool call, or custom code block.
  </Card>

  <Card title="Session" icon="comments" href="/concepts/sessions">
    A series of traces that belong to the same user conversation or workflow.
  </Card>

  <Card title="Eval" icon="flask" href="/concepts/evals">
    An automated score for a trace — correctness, hallucination, safety, etc.
  </Card>

  <Card title="Feedback" icon="thumbs-up" href="/concepts/feedback">
    A human label attached to a trace — thumbs up/down, score, comment.
  </Card>

  <Card title="Metric" icon="chart-line" href="/concepts/metrics">
    An aggregated view across traces — error rate, p95 latency, cost.
  </Card>
</CardGroup>

## How it all fits together

You instrument your app with an SDK. Every LLM call, retrieval, or tool call becomes a **span** inside a **trace**. Traces are batched and shipped to the TruLayer ingest API. In the background:

* **Evals** run against traces and produce scores (stored as eval results).
* **Feedback** is attached to traces directly from your app or through the dashboard.
* **Metrics** are computed on a rolling window and surfaced in the dashboard and via the API.
* **Failures** are clustered and routed to alerting channels you configure.

From the developer's side: all you need to do is instrument. The rest happens automatically.