Notifications
Clear all
Topic starter
20/08/2026 5:44 pm
TL;DR: Enterprise agents are moving into production, but teams still lack a shared way to capture what agents actually did across tool calls, model hops, and handoffs, making OpenTelemetry and OpenInference the practical path to portable, comparable traces, according to Arize. The governance question is no longer observability alone: without standardised telemetry, auditability, evaluation, and migration all remain vendor-bound.
NHIMG editorial — based on content published by Arize: Why agent telemetry needs standards
Questions worth separating out
Q: How should security teams govern AI agents that choose tools at runtime?
A: Security teams should treat runtime tool choice as a governed access event, not a normal application call.
Q: Why do AI agents create a governance problem for IAM teams?
A: AI agents create a governance problem because they authenticate and act as autonomous software entities with tool access.
Q: What breaks when agent telemetry schemas are not standardised?
A: Evaluators, alerts, dashboards, and guardrails break first because they bind to specific field paths.
Practitioner guidance
- Define a standard agent trace schema Map prompts, tool calls, retrieval steps, model outputs, and handoffs to a shared schema so every agent produces comparable telemetry across platforms and teams.
- Preserve identity context in every trace Include service account, delegated credential, and tool-session context in telemetry so investigators can tie agent behaviour to the permissions actually used.
- Build evaluations from production traces Use real trajectories to feed continuous evaluation, debugging, and safety review rather than relying only on static test sets that miss runtime variation.
What's in the full article
Arize's full article covers the operational detail this post intentionally leaves for the source:
- How OpenTelemetry and OpenInference map prompts, tool calls, retrieval steps, and handoffs into a usable agent trace model
- What portability looks like when teams need to move telemetry across frameworks, models, and observability backends without re-instrumentation
- How production traces support continuous evaluation, debugging, and safety review in real enterprise agent workflows
- Why shared semantics matter for auditability when agents use delegated access, service accounts, or secret-backed tool use
👉 Read Arize's analysis of why agent telemetry needs standards →
Agent telemetry standards: are your traces portable and auditable?
Explore further
20/08/2026 6:27 pm
Standardised agent telemetry is now a governance control, not just an observability preference. Once agents can rewrite requests, call tools, and hand off work, their behaviour becomes a security-relevant event stream. Without common semantics, teams cannot compare runs or prove what happened across systems. The practitioner conclusion is simple: if the trace is inconsistent, the control is incomplete.
A question worth separating out:
Q: How do security teams know if agent observability is actually working?
A: Observability is working only when teams can tie together token activity, tool calls, and latency for a specific agent session. If those signals are disconnected, the logs may show traffic but not governance. The test is whether investigators can reconstruct the path of a meaningful agent action from start to finish.
👉 Read our full editorial: Why agent telemetry standards matter for enterprise AI governance
