InfraAnthropicConfirmed
Story 4 of 7 in the Wednesday 14 October editionAnthropic adds OpenTelemetry tracing to the Claude Platform in public beta
Teams can follow each model call and tool use of their Claude agents in the monitoring tools they already use.

Anthropic opened the public beta on 14 October. OpenTelemetry is a vendor-neutral standard for monitoring data: each request produces a trace, made of spans, one for every step such as a model call or a tool use. Because Claude’s spans use OpenTelemetry’s naming conventions for generative AI, tools that follow them recognise the data with no extra configuration.
There are two ways to collect traces. An admin adds a destination in the Claude Console, and the API sends spans for Messages API requests and for each Claude Managed Agents turn, model run and server tool. The Claude SDK, in Python, TypeScript, C#, Go, Java, PHP and Ruby, adds spans for tools the application runs itself.

By default, spans carry IDs, timing, status, token counts and the names of agents and tools. A Full content mode adds prompts and responses, but organisations with HIPAA, FERPA or K-12 restrictions get only metadata at Console destinations.
Anthropic lists 12 partner tools, including Datadog, Grafana Cloud, Honeycomb, New Relic and Sentry, and any tool with a standard OTLP endpoint works. API tracing runs on the Claude Platform and Claude Platform on AWS. Delivery is best effort, so Anthropic points to its Usage API for complete usage counts. Neither the announcement nor the docs mention a charge.
Sources
- PrimaryAgent observability on the Claude Platformclaude.com · Anthropic announcement, 14 October 2026
- OfficialOpenTelemetry for the Claude APIplatform.claude.com · Docs on setup, content modes and partners
- OfficialUse OpenTelemetry with the Claude APIplatform.claude.com · Docs on Console destinations
- OfficialClaude Platform release notesplatform.claude.com · Entry for 14 October 2026
- On X@ClaudeDevs on X: OpenTelemetry traces now in public betax.com · Anthropic’s launch post
- On X@sentry on X: Claude Platform traces with Sentry Agent Tracingx.com
- On X@newrelic on X: Claude Platform traces in New Relicx.com
- On X@testingcatalog on X: Claude Platform supports OpenTelemetry tracesx.com
The rest of the day
Read the whole day01ModelSpaceXSI
SpaceXSI’s Grok Voice 3.0 tops Artificial Analysis’s speech-to-speech index
The new voice model is in SpaceXSI’s Voice Agent API at the same per-minute price as Grok Voice 2.0, and already runs in Tesla cars and Starlink’s call centres.
02Coding agentAnthropic
Anthropic reworks the Claude Code desktop app for running many sessions at once
Anthropic announced the update in a post and video from its developer account on X, without release notes.
03ResearchMeta
Meta shares ten health studies that researchers wrote with its Muse models
Medical researchers went from first prompt to manuscript in under two weeks, and their report lists the errors that only clinicians caught.
05InfraOpenAI
OpenAI will shut down GPT-4o and GPT-4.1 in its API on 14 January 2027
Five snapshots get three months’ notice, and OpenAI recommends gpt-6-luna as the replacement for each, fine-tuned versions included.
Spotted an error? Email aiforsuccess.in+compass@gmail.com or tag @ai_for_success on X






