OBSERVABILITY PLATFORM · Profile revision 1

Arize Phoenix

An open-source observability and evaluation platform that accepts OTLP traces and uses OpenInference semantics for model, retrieval, agent, and tool activity.

observabilityopeninferenceopentelemetryself-hosted

Why it is in the map

Phoenix is a high-signal OpenInference/OTLP implementation with sessions, annotations, export/query, self-hosted privacy, and retention controls.

Tracevity boundary

A documented field can support reconstruction, but its presence alone does not prove completeness, authenticity, authorization, or external settlement.

Profile findings

What the documentation can—and cannot—establish

Each row distinguishes source evidence from Tracevity's bounded interpretation. “Not documented” describes the reviewed sources; it does not prove an implementation cannot record the artifact.

01

System identity

Documented

Trace/span hierarchy, session identity, timing, and resource attributes support distributed execution correlation.

Tracevity interpretation

Stable agent definition and version still depend on the emitting instrumentor.

Limit

Canonical agent instance and agent-definition/version fields are not guaranteed for every trace.

Primary evidence (1)
02

Principal and delegation

Partially documented

Application-supplied user attribution can be recorded.

Tracevity interpretation

A user attribute is not verified initiating-principal or authority evidence.

Limit

Authentication, delegation chain, credential type/scope/expiry, and elevation are not canonical.

Primary evidence (1)
03

Instruction and context

Documented

Instructions, prompt data, retrieval content, and contextual metadata are representable.

Tracevity interpretation

Capture does not prove source authenticity, completeness, or consistent versioning.

Limit

Context fingerprints and explicit missing-context representation are not standardized across instrumentors.

Primary evidence (1)
04

Decision artifacts

Partially documented

Evaluator output and explicit assessment artifacts can be retained with provenance category.

Tracevity interpretation

An explanation is a recorded assessment, not hidden reasoning or proof of the agent's motive.

Limit

Plan, decision summary, selected alternative, policy decision, calibrated confidence, and refusal are not universal.

Primary evidence (1)
05

Model activity

Documented

Core model interaction and performance evidence is representable.

Tracevity interpretation

Exact provider version and field completeness depend on the chosen instrumentor and capture settings.

Limit

Provider build/version, raw request/response, cache, and token details are not guaranteed across integrations.

Primary evidence (1)
06

Tool and MCP activity

Documented

Tool invocation, result, error, timing, and trace correlation are representable.

Tracevity interpretation

Tool telemetry does not establish authorization or downstream settlement.

Limit

MCP server, call ID, retry, credential authority, and downstream correlation depend on instrumentation.

Primary evidence (1)
07

Effects

Not documented

Phoenix represents tool activity, not a universal external-effect settlement chain.

Tracevity interpretation

A successful tool span cannot establish that the destination changed.

Limit

Requested effect, acceptance, external effect state, and state delta are not canonical Phoenix records.

Primary evidence (1)
08

Human control

Partially documented

Human review and evaluation evidence can be recorded.

Tracevity interpretation

Human annotation is not necessarily pre-action approval, rejection, or intervention.

Limit

Approval, rejection, edit, interruption, takeover, rollback request, authority, and timing are not universal.

Primary evidence (1)
09

Outcome

Partially documented

Execution-reported and evaluated outcomes can be correlated in a trace.

Tracevity interpretation

Span success and evaluation do not independently verify external state.

Limit

Externally verified success, settlement ambiguity, rollback, and compensation are not canonical.

Primary evidence (1)
10

Trace integrity

Not documented

Timestamps and retained hierarchy support correlation, not independently verifiable integrity.

Tracevity interpretation

Self-hosted custody does not itself make a record immutable.

Limit

Clock provenance, immutability, append-only enforcement, signing, tamper evidence, and independent verification are absent.

Primary evidence (1)
11

Portability

Documented

OTLP, OpenInference, and query/export surfaces provide strong transport and analysis portability.

Tracevity interpretation

Phoenix annotations and vendor extensions may not round-trip through every OTel destination.

Limit

Schema versions, import/export symmetry, documented conversions, and exact semantic loss remain incomplete.

Primary evidence (1)
12

Privacy

Documented

Self-hosted custody and retention/deletion controls are documented while rich trace payloads may remain sensitive.

Tracevity interpretation

No-egress custody is not automatic redaction, filtering, minimization, or safe retention.

Limit

Client-side redaction, hashing, screenshot controls, and actual capture completeness depend on instrumentation and deployment.

Primary evidence (1)

Reconstruction reading

Do not collapse these findings into one score.

This profile describes documented evidence surfaces. Whether they are sufficient depends on the reconstruction question and the other identity, authorization, tool, and destination records available.

Potentially useful evidence

  • Identity: Trace/span hierarchy, session identity, timing, and resource attributes support distributed execution correlation.
  • Principal: Application-supplied user attribution can be recorded.
  • Context: Instructions, prompt data, retrieval content, and contextual metadata are representable.
  • Decisions: Evaluator output and explicit assessment artifacts can be retained with provenance category.
  • Models: Core model interaction and performance evidence is representable.

Explicit gaps or uncertainty

  • Effects: Requested effect, acceptance, external effect state, and state delta are not canonical Phoenix records.
  • Integrity: Clock provenance, immutability, append-only enforcement, signing, tamper evidence, and independent verification are absent.

Source register

7 reviewed primary sources

  1. What are Traces?Arize AI · OFFICIAL DOCUMENTATION · observed August 28, 2026 · current
    Open source ↗
  2. How does tracing work?Arize AI · OFFICIAL DOCUMENTATION · observed August 28, 2026 · current
    Open source ↗
  3. Extract data from spansArize AI · OFFICIAL DOCUMENTATION · observed August 28, 2026 · current
    Open source ↗
  4. SessionsArize AI · OFFICIAL DOCUMENTATION · observed August 28, 2026 · current
    Open source ↗
  5. Annotations APIArize AI · OFFICIAL DOCUMENTATION · observed August 28, 2026 · current
    Open source ↗
  6. PrivacyArize AI · OFFICIAL POLICY · observed August 28, 2026 · current
    Open source ↗
  7. Data retentionArize AI · OFFICIAL POLICY · observed August 28, 2026 · current
    Open source ↗

Next question

What evidence does your use case require?

Move from documented field presence to an explicit reconstruction target, or examine selected directional format mappings without changing this system's documentation posture.

Trace Reconstruction Requirements Explore compatibility evidence