gitwtfhub

wtf is mastering-ai-observability-workshop?

dpguthrie/mastering-ai-observability-workshop — explained in plain English

Analysis updated 2026-05-18

16PythonAudience · developerComplexity · 3/5Setup · moderate

TL;DR

A hands on workshop app that demonstrates using Braintrust to trace, evaluate, and iteratively improve an AI support agent's behavior.

Mindmap

mindmap
  root((AI Observability Workshop))
    What it does
      Runs a chat agent
      Traces agent behavior
      Builds eval datasets
    Tech stack
      Python
      Braintrust
      uv package manager
    Use cases
      Live workshop demo
      Agent evaluation
      Trace to test case flow
    Requirements
      Braintrust API key
      Tool calling model
      Local database

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

Why would anyone build with this?

REASON 1

Run a local chat interface backed by a live AI support agent to explore its behavior.

REASON 2

Seed and run an evaluation dataset in Braintrust to measure an agent's quality.

REASON 3

Import sanitized example traces and turn them into draft evaluation test cases.

REASON 4

Follow a live workshop exercise on building an AI observability and improvement workflow.

What's in the stack?

PythonBraintrustuv

How it stacks up

dpguthrie/mastering-ai-observability-workshop920linjerry-stack/capital-studioadya84/ha-world-cup-2026
Stars161616
LanguagePythonPythonPython
Setup difficultymoderateeasyeasy
Complexity3/53/52/5
Audiencedeveloperresearchergeneral

Figures from each repo's GitHub metadata at analysis time.

How do you spin it up?

Difficulty · moderate Time to first run · 30min

Requires a Braintrust API key and a chat model that supports tool or function calling to use live features.

Wtf does this do

This repository is the hands on workshop app used for a session called Mastering AI Observability, presented at the AI Engineer World's Fair using a company called Braintrust. It demonstrates what the README calls a trace-backed agent improvement flywheel, meaning a workflow where you watch how an AI support agent behaves in practice, turn interesting real examples into test cases, and use those test cases to keep evaluating and improving the agent over time. After installing the project's Python dependencies and copying an example environment file, a local chat interface runs at a local web address, backed by a small seeded database. To actually talk to a live AI model through this chat interface, you need your own Braintrust API key and to specify which chat model to use, and that model must support tool or function calling since the support agent relies on that capability. The repository is organized around a set of shortcut commands rather than a single script. These commands can seed an evaluation dataset in Braintrust from a local file of example cases, run that evaluation, push custom scoring definitions to Braintrust, import a shared bundle of sanitized example traces, generate draft evaluation cases from those traces, and write ongoing production style traces back to Braintrust for later analysis. A readiness command checks that the environment, local database, and live model access are all working before starting the workshop exercises. The README itself is intentionally short, since detailed instructions live in a separate workshop guide file and a second document describing a custom classification prompt used in the exercises. As presented here, this is workshop supporting material rather than a general purpose, standalone product, and it does not state an open source license.

Yoink these prompts

Prompt 1
Walk me through setting up this workshop app with Braintrust to chat with the support agent.
Prompt 2
Explain what make ready checks before the workshop exercises can start.
Prompt 3
Help me understand how make import-sample-traces turns traces into evaluation cases.
Prompt 4
Show me how to swap in a different model for a single Braintrust evaluation run.

Frequently asked questions

wtf is mastering-ai-observability-workshop?

A hands on workshop app that demonstrates using Braintrust to trace, evaluate, and iteratively improve an AI support agent's behavior.

What language is mastering-ai-observability-workshop written in?

Mainly Python. The stack also includes Python, Braintrust, uv.

How hard is mastering-ai-observability-workshop to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is mastering-ai-observability-workshop for?

Mainly developer.

View the repo → Decode another repo

This repo across BitVibe Labs

Don't trust strangers blindly. Verify against the repo.