Elastic Agent Builder traces overview dashboard
Elastic Agent Builder ships a prebuilt overview dashboard that turns your agent trace data into ready-made operational and usage metrics. Instead of building visualizations yourself, you install one managed dashboard and see how your agents behave, including how many tokens they use, how long conversations take, which agents run most often, and where tool calls fail.
Use the dashboard to:
- Track token usage and LLM request volume across models and providers.
- Spot slow conversations and long-running agent executions.
- Find tools that fail or run slowly.
The dashboard reads the traces that Elastic Agent Builder collects into your own Elasticsearch, so it reflects your real agent activity. You collect that trace data first, then install the dashboard in each Kibana space where you want it. The following sections walk through both.
The overview dashboard is a single prebuilt dashboard named [Elastic] Agent Builder Overview. It is a managed dashboard, so it is read-only. To change or extend it, duplicate it and edit the copy, as described in Customize the dashboard.
You install the dashboard separately in each Kibana space, and each copy shows only that space's trace data.
The dashboard groups its panels into four areas:
- Token usage and LLM requests: Input and output tokens by model, and LLM request counts by model and provider.
- Conversation volume and latency: How many conversation rounds ran and how long they took, including average, 95th percentile, and maximum duration.
- Agent execution: How often each agent ran and how long it took, broken down by agent.
- Tool calls and errors: How often tools were called, their success and error rates, average tool duration, and the most-used tools.
Before you install the dashboard:
- Make sure trace collection is on for the space and the setting is saved. It is on by default. The Install Dashboard button appears only after trace collection is enabled and saved. For details, refer to Collect agent traces.
- Make sure you can read the trace data streams, otherwise the panels have no data to show. For the required privileges, refer to Read trace data.
- Install the dashboard in each Kibana space where you want it. It is not shared across spaces.
The overview dashboard is not installed automatically. Install it once per Kibana space.
- Go to Management > Gen AI Settings.
- In the Agent Builder Traces section, confirm that Collect conversation traces is on and saved.
- Select Install Dashboard.
To open the dashboard, select View Dashboard, or open Dashboards and select [Elastic] Agent Builder Overview.
Repeat these steps in each space where you want the dashboard.
The dashboard is not restored automatically, including in a new space or after you remove it. If it is missing, open the Agent Builder Traces section and select Install Dashboard again.
To remove it, select the arrow next to View Dashboard, then select Uninstall dashboard.
The overview dashboard is managed, so you cannot edit it directly. To build your own version:
- Open the dashboard.
- Duplicate it.
- Edit and save the copy.
Because the original is managed, Elastic can ship improvements to it without overwriting your copy.
The dashboard panels are ES|QL queries over your trace data. To build your own visualizations in Dashboards, Lens, or Discover, query the trace data stream and filter by span type and attribute.
Traces are stored in the traces-agent_builder.otel-* data stream, where each document is a span. The dashboard identifies the kind of work a span represents from its span.name, and reads generative AI details from the span attributes.
Each document is a span. Filter on the span.name field to select a kind of agent activity. The dashboard matches span names by prefix.
| Agent activity | Filter |
|---|---|
| LLM requests, tokens, model, and provider | span.name LIKE "chat *" |
| Conversation rounds (volume and latency) | span.name LIKE "invoke_agent *" and attributes.elastic.inference.span.kind == "CHAIN" |
| Agent executions | span.name LIKE "invoke_agent *" and attributes.elastic.inference.span.kind == "AGENT" |
| Tool calls | span.name LIKE "execute_tool *". For failures only, add status.code == "Error" |
These fields carry the details the dashboard aggregates. Generative AI attributes use the attributes. prefix.
| Field | Description |
|---|---|
attributes.gen_ai.usage.input_tokens |
Input tokens sent to the model |
attributes.gen_ai.usage.output_tokens |
Output tokens generated by the model |
attributes.gen_ai.request.model |
Model name |
attributes.gen_ai.provider.name |
Model provider |
attributes.gen_ai.agent.id |
Agent identifier |
attributes.elastic.inference.span.kind |
On invoke_agent spans, separates conversation rounds (CHAIN) from agent executions (AGENT) |
name |
Tool name, on execute_tool spans (root field, no prefix) |
duration |
Span duration in nanoseconds (root field). Divide by 1,000,000,000 for seconds |
status.code |
Span status, for example Error (root field) |
@timestamp |
When the span started |
Use these as starting points, and test them on your own data. They query all spaces. To scope a query to one space, replace the wildcard with that space's data stream, for example traces-agent_builder.otel-default.
Total input and output tokens by model and provider:
FROM traces-agent_builder.otel-*
| WHERE span.name LIKE "chat *"
| STATS
input_tokens = SUM(TO_LONG(attributes.gen_ai.usage.input_tokens)),
output_tokens = SUM(TO_LONG(attributes.gen_ai.usage.output_tokens))
BY model = attributes.gen_ai.request.model,
provider = attributes.gen_ai.provider.name
| SORT input_tokens DESC
Tool calls and errors by tool:
FROM traces-agent_builder.otel-*
| WHERE span.name LIKE "execute_tool *"
| STATS
calls = COUNT(*),
errors = COUNT(*) WHERE status.code == "Error"
BY tool = name
| SORT calls DESC