ユースケースシリーズ

Langfuse ワークショップ - AI エンジニアリング ループの全体像

AI エンジニアリング ループの全体像。

これは小規模な TypeScript サンプル アプリケーション (Dad IT Support Agent) を基にした段階的な Langfuse ワークショップです。このワークショップは、Langfuse による完全な AI エンジニアリング ループをカバーしています: トレーシング、プロンプト管理、監視、データセット、実験、評価。

1 回のセッション中級9 modules
Start the workshop →Overview
Langfuseトレーシングプロンプト管理評価

What you will do

9 modules, in order

  1. 00

    00 Setup

    Have the workshop app running locally with both OpenAI and Langfuse credentials in place. From here you can skim 01-base-app, then start building in 02-tracing.

  2. 01

    01 Base App

    You can customize your experience by changing the phone specs in support-data.ts file. Adding your dad's phone information means, you will get replies for the right type of phone.

  3. 02

    02 Tracing

    This is the blank slate for the tracing step — same code as checkpoint/01-base-app, with no Langfuse wiring yet. The Langfuse packages are already in package.json — run npm inst...

  4. 03

    03 Prompt Management

    You have a working traced app. The system prompt lives as a constant called SYSTEMPROMPT in src/server/support-agent.ts and is used directly as the system message.

  5. 04

    04 Monitoring

    You have a traced app with optional Langfuse-managed prompts. Every chat turn lands in Langfuse as a nested trace.

  6. 05

    05 Dataset

    You have a traced, attributed, monitored app. data/seed-dataset.json and scripts/seed-dataset.ts are already in the repo at this checkpoint.

  7. 06

    06 Experiments

    Your dataset is seeded in Langfuse. scripts/run-dataset.ts is already in the repo.

  8. 07

    07 Evaluate a change

    Your app is traced, monitored, has a hosted dataset, and at least one experiment run with both keywordoverlap and correctness scores. Now you make a change to the app and rerun ...

  9. 08

    08 Wrap-up

    You have walked through every loop step.

JA