braintrust-tracing

Community

Debug AI sessions with Braintrust traces.

Authorscooter-lacroix
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides detailed insights into AI session execution by integrating with Braintrust for comprehensive tracing, enabling deep debugging and performance analysis of complex AI workflows.

Core Features & Use Cases

  • End-to-End Tracing: Captures session starts, user prompts, tool usage, and agent stops.
  • Sub-Agent Correlation: Links parent agent tasks to their respective sub-agent execution traces.
  • Debugging & Analysis: Facilitates identification of performance bottlenecks and errors within AI sessions.
  • Use Case: When a multi-agent workflow produces unexpected results, use Braintrust tracing to pinpoint which agent failed, what input it received, and what output it generated, allowing for precise debugging.

Quick Start

Enable Braintrust tracing by setting TRACE_TO_BRAINTRUST to true in your local settings.

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: braintrust-tracing
Download link: https://github.com/scooter-lacroix/Maestro/archive/main.zip#braintrust-tracing

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.