Skip to content
Y CombinatorY Combinator

How Meta Prompting and Rubrics Make LLM Agents Reliable

Through rubric-based evals and explicitly layered meta prompting; Parahelp's agent prompt shows how role, task, and output-format layers drive LLM calls.

Garry TanhostJared FriedmanhostDiana HuhostHarj Taggarhost
May 30, 202531mWatch on YouTube ↗

CHAPTERS

  1. 0:00 – 0:58

    Intro

  2. 0:58 – 4:59

    Parahelp’s prompt example

  3. 4:59 – 6:51

    Different types of prompts

  4. 6:51 – 7:58

    Metaprompting

  5. 7:58 – 12:10

    Using examples

  6. 12:10 – 14:18

    Some tricks for longer prompts

  7. 14:18 – 17:25

    Findings on evals

  8. 17:25 – 23:18

    Every founder has become a forward deployed engineer (FDE)

  9. 23:18 – 26:13

    Vertical AI agents are closing big deals with the FDE model

  10. 26:13 – 27:26

    The personalities of the different LLMs

  11. 27:26 – 29:47

    Lessons from rubrics

  12. 29:47 – 31:00

    Kaizen and the art of communication

  13. 31:00 – 31:26

    Outro

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome