Notifications
Clear all
Topic starter
18/08/2026 2:32 pm
TL;DR: Native agent tracing can turn Worker-based agent runs into structured production traces, linking model calls, tool use, approvals, and infrastructure context for later evaluation, according to Braintrust. For teams governing agentic systems, the key issue is not visibility alone but whether traces become an auditable control surface for behaviour, quality, and access decisions.
NHIMG editorial — based on content published by Braintrust: Trace and improve Cloudflare Agents
Questions worth separating out
Q: How should security teams govern AI-enabled workflows that can act on their own?
A: Treat them as identity-governed execution paths, not just software features.
Q: Why do AI agents make non-human identity governance harder?
A: AI agents make governance harder because they can request tools, act autonomously, and change behaviour across sessions while still relying on machine credentials.
Q: How do teams know whether agent traces are actually useful for control review?
A: Useful traces show the full decision path, not just the final response.
Practitioner guidance
- Treat agent traces as governance evidence Define which agent spans must be retained for review, including model calls, tool calls, approvals, and subagent activity.
- Protect tracing credentials like production secrets Store the BRAINTRUST_API_KEY in a restricted secret store, scope access to deployment automation only, and rotate it on the same schedule as other runtime credentials used by the Worker.
- Separate evaluation data from live execution paths Use traces to build eval datasets after execution rather than feeding live decisions back into production without review.
What's in the full article
Braintrust's full post covers the operational detail this post intentionally leaves for the source:
- Step-by-step OpenTelemetry setup for routing Cloudflare Agent spans into Braintrust without a Worker SDK
- JavaScript instrumentation patterns for Cloudflare Agents SDK, @cloudflare/ai-chat, @cloudflare/think, and Flue
- Worker deployment requirements including nodejs_compat, secret handling, and trace flushing
- How traced production runs become eval datasets for comparing models, prompts, and subagents
👉 Read Braintrust's guide to tracing Cloudflare Agents in production →
Cloudflare agent tracing: what it means for production governance?
Explore further
18/08/2026 3:19 pm
Agent tracing is becoming a governance control, not just an observability feature. Once AI systems can take tool actions in production, teams need evidence of what was invoked, approved, and returned. That evidence supports incident review, policy validation, and model change control. In practice, tracing should sit alongside access governance, not outside it.
A question worth separating out:
Q: What should organisations do when tracing secrets are used in AI workloads?
A: Manage tracing keys like sensitive operational credentials. Restrict who can create or read them, store them in approved secret management, and rotate them on a defined schedule. If the tracing layer is compromised, attackers can tamper with visibility, exfiltrate telemetry, or weaken review of agent behaviour.
👉 Read our full editorial: Cloudflare agent tracing clarifies production evaluation for IAM teams
