MLflow

@MLflow

The open source developer platform to build AI applications and models with confidence.

San Francisco, CA

mlflow.org

Joined August 2018

48 Following

11.7K Followers

Replies Reposts Media

MLflow
@MLflow
Oct 16
The Claude SDK makes it fast to build an agent. With native @opentelemetry export and MLflow, it is just as fast to know whether the agent works. 🔹 Trace every model call by pointing a standard OTel exporter at MLflow 🔹 See each run as one trace, with model calls and tool
5 Simple Tips to Supercharge Your Claude SDK Experience with MLflow | MLflow
From mlflow.org
1
MLflow
@MLflow
Oct 15
Part 2 of MLflow Ambassador Jonathan Bown’s series on self-improving AI workflows with MLflow is live. He walks a support agent through the loop: traces, feedback, expectations, and judges in; a versioned prompt and an evaluation dataset out; then a production alias move so the
Self-Improvement & MLflow: Part 2
From opendatascience.com
1
MLflow
@MLflow
Oct 15
Claude Platform now supports native @opentelemetry tracing across its agent ecosystem. Bring traces from the Claude family into one backend using OTLP, the OpenTelemetry Protocol: 🔹 Messages API and Claude SDKs: model requests and tool-runner activity 🔹 Claude Code and Agent
How to trace Claude agents via Native OpenTelemetry Export | MLflow
From mlflow.org
3
MLflow
@MLflow
Oct 14
MLflow AI Gateway now supports TypeSafe System One calls. Create an endpoint for a Jev model, keep the TypeSafe API key on the server, and send structured questions using the endpoint name. You can change the configured Jev model without changing each application that calls it.
MLflow
@MLflow
Oct 12
Yes/no evals don’t need a general-purpose LLM on every row. That gets slow and expensive at volume. In MLflow 3.17, TypeSafe’s Jev models work as judges. Keep your existing mlflow.genai.evaluate() flow and set model="typesafe:/jev-latest" on make_judge(). Jev returns a
2