Agent Analytics privacy modes

An Agent Analytics privacy mode controls whether prompt and response text leaves your infrastructure. There are three modes: full sends message content, metadata_only sends none, and customer_enriched sends none but uses quality labels you compute yourself. Every mode still sends tokens, cost, latency, model names, and session grouping.

Choose the mode before wide rollout, because it determines what your legal review needs to cover. Regulated environments, such as healthcare and finance, typically run metadata_only or customer_enriched.

What each mode sends

Amplitude-generated enrichments (signals, topics, custom evaluators) run in every mode. What differs is what those enrichments see. In modes without content, content-dependent signals such as task completion and response quality carry less information. Structural signals, such as errors, behavioral friction patterns, cost, and latency, stay useful.

full

Message content, system prompts, tool inputs and outputs, and score comments all reach Amplitude. Amplitude's built-in enrichment runs and produces the fullest signal set.

• The system prompt is optional, so you can omit it.
• The AI SDK redacts PII by default. It scrubs emails, phone numbers, SSNs, credit card numbers, and IP addresses before events leave your process. Built-in phone and SSN detection targets US formats. For international locales or domain-specific identifiers, add custom regex patterns or plug in your own redaction, such as Presidio.

metadata_only

No message content, system prompts, tool payloads, or score comments leave your process. You still get tokens, cost, latency, model names, and session grouping, so analyses that don't need content still work.

customer_enriched

No content leaves your process. Amplitude enrichment runs on the labels you send through trackSessionEnrichment() instead, so your labels are the only session-level quality data.

You can send Session Enrichment events in any mode. customer_enriched is the mode where those events are the only source of session-level quality data.

Apply the mode

How you apply the mode depends on your instrumentation path:

• AI SDK (Node, Python): Set contentMode (Node) or content_mode (Python) once on AIConfig. The SDK routes every content-bearing channel through one gate. Refer to Choose a privacy mode in the SDK reference.
• OpenTelemetry: Turn content capture on or off in your OpenTelemetry instrumentation. Refer to Apply your privacy mode.
• HTTP API or a standard Amplitude SDK: You redact or omit four content-bearing properties yourself, before you call track(). Refer to Redact content before tracking.