Same agent Smaller bill. The tools and infrastructure to get more work from your AI. Fewer tokens. Less compute. Lower cost.
TypeScript agent-harnessagent-harness-engineeringai-engineeringai-observabilityamd-gpuclaude-codeclickhousecodexcoding-agentcoding-agentscursorgenaigpu-monitoringllm-observabilityllmopsnvidia-smiobservabilityopen-sourceopenaiopentelemetry
docs: surface content capture controls in the AI observability quickstart (#1652)
Dmitry Voropaev73ffa6e50597
diff --git a/docs/snippets/quickstart-observability.mdx b/docs/snippets/quickstart-observability.mdxindex 5ce02dde..ec3de4be 100644--- a/docs/snippets/quickstart-observability.mdx+++ b/docs/snippets/quickstart-observability.mdx@@ -57,6 +57,9 @@ flowchart TB;<Step title="Instrument your AI application"><Tabs><Tab title="Python">+ <Note>+ OpenLIT captures prompt and completion content on spans by default (`capture_message_content=True`). Pass `capture_message_content=False` to keep that content out of your traces, `max_content_length` to truncate it, or `guards=[openlit.PII(action="redact")]` to redact sensitive values before a prompt is sent and recorded — today that rewrite only reaches single-message prompts, so do not rely on it for a multi-turn conversation. See [Disable Tracing of Content](/latest/sdk/features/tracing#disable-tracing-of-content), [Limit Content Length](/latest/sdk/features/tracing#limit-content-length), [Guardrails](/latest/sdk/features/guardrails) and the full [Configuration](/latest/sdk/configuration) reference.+ </Note><Tabs><Tab title="Manual instrumentation"><Tabs>