---
title: "Send data"
description: "Send OpenTelemetry GenAI traces with content capture on, from any instrumentation that follows the GenAI semantic conventions or from a Mastra app."
---

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

# Send data

AI Center reads ordinary traces. Any span that follows the
[OpenTelemetry GenAI semantic conventions](https://opentelemetry.io/docs/specs/semconv/gen-ai/),
version 1.37 or later, shows up there once it's stored: send traces as for any service (see
[Traces](/observability/traces#send-traces)), with an ingest key that has `obs.traces.ingest`.
There's nothing to turn on in Observability.

Only the OpenTelemetry GenAI conventions are read. Other formats, such as OpenInference (`llm.*`)
or indexed prompt attributes (`gen_ai.prompt.0.content`), are stored as ordinary span attributes
and don't appear in AI Center. Content in the layout of conventions before 1.37, one event per
message (such as `gen_ai.user.message`), isn't read either.

## Turn on content capture

Instrumentations leave prompts and completions out of spans unless you turn content capture on.
Without content, a run still has its steps, timing, tokens and errors, and counts in the overview,
but its transcript has no text and search doesn't find it.

AI Center reads content from **span attributes**: `gen_ai.input.messages`,
`gen_ai.output.messages`, `gen_ai.system_instructions` and the others in the
[data reference](/observability/ai-center/data-reference#content), on the span or on its
`gen_ai.client.inference.operation.details` span event. Where an instrumentation can put content
on spans or in log records, choose spans. Content sent as log records is stored as ordinary logs
and isn't shown in AI Center.

For example, OpenTelemetry's Python GenAI instrumentations take:

```sh
OTEL_SEMCONV_STABILITY_OPT_IN=gen_ai_latest_experimental
OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT=SPAN_ONLY
```

For other instrumentations, see their documentation for content capture and the conventions
version they follow.

To keep some content out of storage, redact it at ingest with
[transform rules](/observability/transforms): they see GenAI spans with their content, before it's
stored.

## Mastra

A [Mastra](https://mastra.ai) app that sends its traces with `@ezghcloud/mastra-integration`
sends GenAI spans with their content, so its agents' runs appear in AI Center with nothing else to
set up. See [Deploy a Mastra app](/deploy/mastra).

## Check it

Open **Observability**, then **AI Center**, **Runs**, and choose the environment your agents send
to. The page is empty until a GenAI span arrives in the time range, and runs are searchable within
seconds of their spans arriving (in a dataset with [trace sampling](/observability/sampling#decision-wait-and-incomplete-traces),
after its decision wait). A run whose transcript has steps but no text was sent without
content.

Source: https://docs.ezghcloud.com/observability/ai-center/sending-data/index.mdx
