Catch prompt regressions before you merge.
The telemetry.dev GitHub Action runs your evals on each pull request and fails the check when a score drops below your pass mark.
In the video, deleting the warranty line from the prompt takes Correctness from 100% to 75%.
The telemetry.dev GitHub Action runs your evals on each pull request and fails the check when a score drops below your pass mark.
In the video, deleting the warranty line from the prompt takes Correctness from 100% to 75%.
2
2
7
525
We're still live on Product Hunt, we'd love your support❤️
#4 on Product Hunt, help us get to #1 🙏
producthunt.com/products/telem…
2
7
16
586
Introducing the new telemetry.dev
LLM observability, now easy on the eyes. We redesigned every page: traces, sessions, logs, alerts, MCP analytics, and setup.
Light and dark, and it works on any device.
LLM observability, now easy on the eyes. We redesigned every page: traces, sessions, logs, alerts, MCP analytics, and setup.
Light and dark, and it works on any device.
1
15
46
3,275
Ask Claude Code why your agent failed.
telemetry.dev has a read-only MCP server. Claude Code, Cursor, or ChatGPT can read your traces, errors, and costs, and work out what went wrong.
In this run, it found a refund that was converted to cents twice.
telemetry.dev has a read-only MCP server. Claude Code, Cursor, or ChatGPT can read your traces, errors, and costs, and work out what went wrong.
In this run, it found a refund that was converted to cents twice.
5
0
7
422
When an agent gets stuck in a loop, telemetry.dev emails you.
Turn on the Agent loop alert and it checks your traces every 5 minutes. If one costs more than $2 or runs more than 30 spans, the email names the agent and the tool it kept calling, and Investigate opens that trace.
Turn on the Agent loop alert and it checks your traces every 5 minutes. If one costs more than $2 or runs more than 30 spans, the email names the agent and the tool it kept calling, and Investigate opens that trace.
1
5
8
640
In the video, a support agent kept calling lookup_order after every call timed out. 41 spans in 29 seconds for under a cent, so the span limit caught it, and the email came 10 minutes after the run ended. A trace over the cost limit alerts one check sooner.
Alerts docs: telemetry.dev/docs/platform/…
Alerts docs: telemetry.dev/docs/platform/…
0
0
0
75
See what each Claude Code prompt costs on telemetry.dev.
With Claude Code's tracing beta on, each prompt arrives as a trace with every model request and tool call. This one fixed two failing tests for $0.13 at API prices.
Setup guide: telemetry.dev/docs/integrati…
With Claude Code's tracing beta on, each prompt arrives as a trace with every model request and tool call. This one fixed two failing tests for $0.13 at API prices.
Setup guide: telemetry.dev/docs/integrati…
0
2
3
633
It's live. Add telemetry.dev as an OpenTelemetry destination in the Claude Console, no code changes.
Setup guide: telemetry.dev/docs/integrati…
Setup guide: telemetry.dev/docs/integrati…
Claude traces are coming to telemetry.dev, from the SDKs, the Messages API and Managed Agents.
You'll see tokens, cost and latency for every Claude call, counted once. Setup guide soon.
0
2
4
258
Claude traces are coming to telemetry.dev, from the SDKs, the Messages API and Managed Agents.
You'll see tokens, cost and latency for every Claude call, counted once. Setup guide soon.
You'll see tokens, cost and latency for every Claude call, counted once. Setup guide soon.
Now in public beta, Claude Platform can send OpenTelemetry traces from the Messages API, Claude Managed Agents, and the Claude SDKs to your observability stack.
1
3
6
578
When an agent run goes wrong, open its trace on telemetry.dev.
Every model call and tool step is there, in order, with how long each took. The failed step is red, and you can read what went in and what came out.
Connect with our TypeScript or Python SDK, or point any at it.
Every model call and tool step is there, in order, with how long each took. The failed step is red, and you can read what went in and what came out.
Connect with our TypeScript or Python SDK, or point any at it.
0
5
9
1,044
Telemetry retweeted
i have an extra free pro month of @telemetrydev left since the two went really fast
for the last one, i’m giving it directly to anyone who’s willing to try it and give us feedback on what’s missing or what they like a lot about telemetry.dev
for the last one, i’m giving it directly to anyone who’s willing to try it and give us feedback on what’s missing or what they like a lot about telemetry.dev
0
8
20
661