Compare Experiments and Investigate Weave Traces

Ask your AI assistant to work with Weights & Biases: compare experiments and investigate weave traces.

What to Ask Leina to Do with Weights & Biases

Copy a prompt, add your details, and send it to Leina in your connected team chat.

Compare configuration and metrics for two known runs.

Compare W&B runs [run A ID] and [run B ID] in entity [entity] project [project], then retrieve their sampled histories to explain metric differences.

Discover trace fields before querying and counting records.

Infer classic Weave trace schema in [entity/project], query traces matching [criteria], and count matching traces; summarize inspected examples separately from counts.

Get Started with Weights & Biases

  1. Connect Your Account

    Connect using your Weights & Biases W&B API Key.

  2. Try a Task

    Tell Leina what you need in your team chat. Include the source, destination, and expected result.

    Set Up Leina in Your Chat →
  3. Check the Result

    Review the result and any changes in the connected app.

Supported Weights & Biases Capabilities

Weights & Biases connects experiment metrics, artifact context, and classic Weave traces to AI investigation and reporting.

Compare Training Runs

Compare configuration and metrics for two known runs.

Investigate Trace Patterns

Discover trace fields before querying and counting records.

View All 22 Actions
  • Query Weave Traces
  • Count Weave Traces
  • Resolve Trace Roots
  • Query Wandb
  • Create Report
  • Log Analysis
  • List Entities
  • List Projects
  • List Automations
  • List Integrations
  • Infer Trace Schema
  • Search Docs
  • Get Run History
  • List Registries
  • List Registry Collections
  • List Artifact Versions
  • Get Artifact Details
  • Compare Artifact Versions
  • Compare Runs
  • Summarize Evaluation
  • Diagnose Run
  • Probe Project

Visit Provider Website ↗

Frequently Asked Questions

Does the hosted MCP support Multi-tenant Cloud?

The hosted endpoint supports Dedicated Cloud, not Multi-tenant Cloud; Self-Managed deployments need a separate public server.

Is run history exhaustive?

The history action retrieves sampled time-series metrics.

Can I save an analysis?

Create a report or log analysis data as a new W&B run with explicit entity and project.

Your AI employee for Weights & Biases

Tell Leina what you need in your team chat. Include the source, destination, and expected result.