Beginner's Guide to Agent Evaluations

Поделиться
HTML-код
  • Опубликовано: 24 янв 2025

Комментарии • 9

  • @js-craftacademy6740
    @js-craftacademy6740 15 дней назад +1

    watched the whole thing :) Big like for the Agent example. Thanks Dave

  • @rohitkochikkatfrancis
    @rohitkochikkatfrancis 18 дней назад +1

    Finally !!!
    A well defined and detailed professional code for customer service agent

  • @sweetcaramel6349
    @sweetcaramel6349 17 дней назад

    Awesome! Thanks!
    Need more videos (and text tutorials) like this, in customer needs 🔥

  • @WinonaNagy
    @WinonaNagy 18 дней назад +3

    Finally, 'The Judge' is here! Evaluating agents is no small feat. Can't wait to dive into the golden dataset and your strategies. Off to check the notebook now!

  • @olivierramier8335
    @olivierramier8335 12 дней назад

    Very interesting, thank you!
    Could you please also make a video about the ideal workflow of building large datasets from production usage, in order to iterate after release + build datasets for fine-tuning models and prompts optimization (when using dspy). I saw that Langgraph studio can add examples to datasets easily, but it's not super clear how to do that in practice.
    I love the tooling around Langgraph, but this part around maintaining and improving an agent after release lacks tutorials

  • @charlesmccullough7149
    @charlesmccullough7149 17 дней назад +1

    That's nice, but when will LangGraph Studio be available for anything besides Mac OS?

    • @emmyrichy515
      @emmyrichy515 17 дней назад

      you can use docker, through the langgraph cli

    • @olivierramier8335
      @olivierramier8335 12 дней назад +1

      honestly it's better to use the development server with the web UI. I have mac os but the setup for the desktop app with docker is a nightmare if you don't start with one of their template