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

# Observability

> Real-time tracing, analytics, drift detection, and threshold alerts for every LLM call, chain, and tool invocation.

Observability is what tells you what your agents are actually doing. Every run is captured as a chain of events with inputs, outputs, timings, token counts, and cost. From those events you get search, analytics, drift detection, and alerts — without writing any of the plumbing yourself.

## What's inside

> [card] [LLM Calls](https://docs.flowx.ai/6.x/observatory/observability/llm-calls.md)
>
> Table of every LLM invocation with filters, search, and a detail drawer.

> [card] [Traces](https://docs.flowx.ai/6.x/observatory/observability/traces.md)
>
> Full chain-of-calls per run — chains, tools, retries, and durations.

> [card] [Analytics](https://docs.flowx.ai/6.x/observatory/observability/analytics.md)
>
> Cost by model, p50/p95 latency, error rate, and model performance.

> [card] [Threads](https://docs.flowx.ai/6.x/observatory/observability/threads.md)
>
> Multi-turn conversations grouped from `chat` events.

> [card] [Drift Monitor](https://docs.flowx.ai/6.x/observatory/observability/drift-monitor.md)
>
> Distribution monitoring across five metrics with composite scoring.

> [card] [Alerts](https://docs.flowx.ai/6.x/observatory/observability/alerts.md)
>
> Threshold rules with cooldown, escalation, and SLA tracking.

***

## When to use what

| You want to... | Use |
| - | - |
| Find a specific run by user, agent, or input text | [LLM Calls](https://docs.flowx.ai/6.x/observatory/observability/llm-calls.md) |
| Debug why a particular run failed | [Traces](https://docs.flowx.ai/6.x/observatory/observability/traces.md) |
| Track cost and latency over time | [Analytics](https://docs.flowx.ai/6.x/observatory/observability/analytics.md) |
| Inspect a multi-turn conversation | [Threads](https://docs.flowx.ai/6.x/observatory/observability/threads.md) |
| Catch behavioural shifts before users do | [Drift Monitor](https://docs.flowx.ai/6.x/observatory/observability/drift-monitor.md) |
| Get paged when something breaks | [Alerts](https://docs.flowx.ai/6.x/observatory/observability/alerts.md) |

***

## The data behind the views

Every event the SDK emits lands as one of two records in the database:

* A **Run** — one execution of an agent, chain, or tool. Carries the aggregate cost, duration, status, and saved flag.
* An **Event** — a leaf record inside a run, such as `chain_start`, `tool_end`, `chat`, or `saved`.

The Observability views are all built on top of these two tables. The [SDK reference](https://docs.flowx.ai/6.x/observatory/sdk/overview.md) describes the event flow and how custom events plug in.

***

## Related resources

> [card] [SDK event reporting](https://docs.flowx.ai/6.x/observatory/sdk/event-reporting.md)
>
> How events are batched, sent, and persisted.

> [card] [Governance](https://docs.flowx.ai/6.x/observatory/governance/overview.md)
>
> Once you can see runs, the next step is shaping them.


## Related topics

- [Observability with OpenTelemetry](https://docs.flowx.ai/6.x/docs/platform-deep-dive/integrations/open-telemetry.md)
- [AI Platform setup](https://docs.flowx.ai/6.x/setup-guides/ai-platform-setup.md)
- [Document Converter setup](https://docs.flowx.ai/6.x/setup-guides/document-converter-setup.md)
- [Microservices setup guides](https://docs.flowx.ai/6.x/setup-guides/setup-guides-overview.md)
- [Speech to Text setup](https://docs.flowx.ai/6.x/setup-guides/speech-to-text-setup.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.