# Code agents observability

Code Agents Observability is a **standalone screen** in AI Center, separate from the Application Catalog and its monitoring views. It is purpose-built for external developer tools — Claude Code, Claude Cowork, Codex CLI, Gemini CLI — that emit telemetry natively over OTLP. No SDK instrumentation is required; you configure an OTLP endpoint directly in the tool, and the data flows automatically.

If you are building and monitoring your own AI applications — AI agents, chatbots, LLM-based applications — see [Getting started with AI observability](https://coralogix.com/docs/user-guides/ai/getting_started/index.md) and the [Application Catalog](https://coralogix.com/docs/user-guides/ai/app_catalog/index.md) instead.

______________________________________________________________________

AI coding agents like Claude Code generate a continuous stream of telemetry: tokens consumed, models invoked, tools called, code committed, and sessions started. Without visibility into this data, engineering teams operate blind — unable to attribute AI costs to teams or individuals, detect runaway usage, or understand whether agents are actually accelerating delivery.

Coralogix gives engineering leaders and platform teams a unified view of all coding agent activity — covering cost, usage, code impact, and user behavior across every agent, every developer, and every session.

## How it works

```
flowchart LR
    A[Your Agent] --> B[OTLP]
    B --> C[Coralogix Ingress]
    C --> D[Dashboards + Alerts]

    class A entry
    class D success
```

Each agent emits telemetry over OTLP. Configure the agent with your Coralogix endpoint and API key, and the data flows automatically. No wrappers, no custom SDKs, no custom instrumentation.

## What you need

- A Coralogix account with a **Send-Your-Data API key**. In Coralogix, navigate to **Settings**, then **API Keys**.
- One or more coding agents installed and connected to Coralogix.

## Connect an agent

Each agent has its own setup guide. Complete the setup before opening the dashboard.

| Agent Name        | Setup Guide                                                                                           |
| ----------------- | ----------------------------------------------------------------------------------------------------- |
| **Claude Code**   | [View documentation](https://coralogix.com/docs/integrations/ai-observability/claude-code/index.md)   |
| **Claude Cowork** | [View documentation](https://coralogix.com/docs/integrations/ai-observability/claude-cowork/index.md) |
| **Codex CLI**     | [View documentation](https://coralogix.com/docs/integrations/ai-observability/codex-cli/index.md)     |
| **Copilot CLI**   | [View documentation](https://coralogix.com/docs/integrations/ai-observability/copilot-cli/index.md)   |
| **Gemini CLI**    | [View documentation](https://coralogix.com/docs/integrations/ai-observability/gemini-cli/index.md)    |
| **Cursor**        | [View documentation](https://coralogix.com/docs/integrations/ai-observability/cursor/index.md)        |

## Access code agents observability

1. In Coralogix, navigate to **AI Center**, then **Code Agents Observability**. Select the **Code Agents** tab.
1. Use the time range picker to set the period you want to analyze.

The dashboard has four tabs: **Overview**, **Cost**, **Usage**, and **Users**.

## Overview

The Overview tab gives you the health snapshot you need before diving deeper—active models, total spend, and session volume for the selected period.

**Key Insights** surfaces the most critical metrics at a glance:

- **Models in use** — Primary models invoked across sessions.
- **Estimated total cost** — Spend calculated from token usage and model pricing.
- **Total sessions** — Number of Claude Code sessions in the selected period.

The **Cost summary** widget displays a trend line alongside the counter, so you can see direction at a glance without switching tabs.

## Cost

Gain a clear breakdown of where your AI spend is going—and who is driving it.

- **Model cost distribution** — A doughnut chart showing cost share by model. Use this to identify which models account for the majority of spend and whether that matches your intended usage.
- **High-spending users** — A ranked bar chart of users by estimated cost. Use this to detect outliers, verify that usage aligns with expectations, and prioritize conversations about responsible usage.
- **Activity** — Session and request volume over time, giving context to the cost figures.
- **Code impact** — Commits, pull requests, and AI suggestion acceptance rates correlated with cost. Use this to evaluate whether high-spend users are also driving proportional delivery output.
- **Productivity ratio** — The ratio of accepted AI suggestions to total suggestions generated. A higher ratio indicates that the output Claude generates closely aligns with developer intent.
- **Tool calls** — Breakdown of tools invoked by Claude during sessions (for example, file edits, shell commands, web searches), showing where Claude spends its execution budget.

## Usage

Understand how Claude Code runs and what tangible code output it produces.

- **Session activity** — Session count and request volume over the selected period.
- **Code impact** — Commits, pull requests, and lines of code attributed to Claude Code sessions. Use this to correlate AI usage with real development output.
- **Acceptance rate** — The percentage of AI-generated suggestions accepted by developers. A declining acceptance rate can indicate model drift or context quality issues.
- **Tool calls** — Which tools Claude invoked most across sessions, helping you understand the operational patterns Claude follows.

## Users

Identify your most active users and investigate individual session patterns.

- **Active users** — Ranked list of users by estimated cost in the selected period.
- Select any user to drill down into their session activity, token consumption, and code impact over time.

## Troubleshoot

**The Claude Code dashboard reports fewer tokens than a custom dashboard built on the same metric.** Cause: The Code Agents widgets use PromQL `increase()` over the visible time range. For short windows or sparse time series, individual data points can be excluded from the increase calculation, producing a smaller total than a raw counter sum. Fix: For an exact counter total, build a [Custom Dashboards](https://coralogix.com/docs/user-guides/custom-dashboards/introduction/index.md) widget with `sum by (cx_application_name) (claude_code_token_usage_tokens_total{})`. For longer time ranges, the Code Agents totals and the raw counter converge.

## Next steps

Discover every AI model and integration in your codebase with [AI Security Posture Management](https://coralogix.com/docs/user-guides/ai/spm/index.md).