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

# Agent Observability overview

> Kubit Agent Observability labels every agent span with Polaris and groups every run by execution path in Flows.

Kubit Agent Observability is Agent Observability with Behavior Analytics. It reads the OpenTelemetry traces your agents already produce, labels every span with Polaris and groups every agent run by its execution path, so you can see which runs went wrong and how often each path happens.

## What Agent Observability does with your traces

Agent Observability adds three things on top of raw spans.

| Feature | What it does | Example question it answers |
| - | - | - |
| **Polaris** | Kubit's in-house small language model labels every span with what it did and whether it worked. Each span gets labels in under a second, with no sampling. | Which tool calls returned 200 but picked the wrong parameter? |
| **Flows** | Groups every agent run by execution path (which tools ran, in what order) and draws all paths in one Sankey. | What share of refund conversations loop on `search_orders` three or more times? |
| **Triggers** | Compares a metric across model versions or user segments and tells you when it changes. | Did the Misstep rate on `book_appointment` go up after the model upgrade? |

Polaris annotations come in four types: **Action**, **Exception**, **Misstep** and **Warning**. [Concepts](https://learn.kubit.ai/agent-observability/concepts.md#polaris-annotations) defines each one.

## How traces get into Kubit

Kubit reads agent traces from one of three places.

| Where your traces are | What you do | Start here |
| - | - | - |
| In your app, not stored anywhere yet | Install the Kubit OpenTelemetry SDK (`kubit-otel` for Python, `@kubit-ai/otel` for Node) and send spans with an API key. | [Quickstart](https://learn.kubit.ai/agent-observability/get-started/quickstart.md) |
| Already in Langfuse or Braintrust | Add `KubitSpanProcessor` next to your existing processor. Your current tool keeps working. | [Set up with your coding agent](https://learn.kubit.ai/agent-observability/get-started/coding-agent.md) |
| Already in your warehouse | Connect Databricks, Snowflake, BigQuery or ClickHouse. Kubit queries the trace tables where they are. | [Bring your own warehouse](https://learn.kubit.ai/warehouses/overview.md) |

No data silo to secure. Traces retained in your control.

## Who uses Agent Observability

| Reader | Typical use |
| - | - |
| **AI product engineer** | Instruments the agent, finds the execution paths that fail and checks a fix against the next week of runs. |
| **Product manager or analyst** | Reads Flows to see which agent behavior leads to a completed task, a support ticket or a cancellation. |
| **Coding agent** | Wires Kubit into a repo with `/kubit-integrate`, then queries traces through the Kubit MCP server. |

## Related

> [card] [Quickstart](https://learn.kubit.ai/agent-observability/get-started/quickstart.md)
>
> First traces from a Python agent in about 10 minutes.

> [card] [Concepts](https://learn.kubit.ai/agent-observability/concepts.md)
>
> Users, sessions, traces, spans, execution paths and Polaris annotations.

> [card] [Set up with your coding agent](https://learn.kubit.ai/agent-observability/get-started/coding-agent.md)
>
> Let Claude Code detect your tracing setup and wire Kubit in.

> [card] [Is my data flowing?](https://learn.kubit.ai/agent-observability/get-started/data-flowing.md)
>
> Check each step when traces don't show up.


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