# GEPA with Lakshya A. Agrawal - Weaviate Podcast #127!

Page: https://stenobird.com/podcast/weaviate-podcast-6288219/gepa-with-lakshya-a-agrawal-weaviate-podcast-127
Text version: https://stenobird.com/podcast/weaviate-podcast-6288219/gepa-with-lakshya-a-agrawal-weaviate-podcast-127.md
Podcast: [Weaviate Podcast](https://stenobird.com/podcast/weaviate-podcast-6288219)
Published: 2025-08-13T13:52:24+00:00
Episode link: https://podcasters.spotify.com/pod/show/weaviate/episodes/GEPA-with-Lakshya-A--Agrawal---Weaviate-Podcast-127-e36qaq1
Audio file: https://anchor.fm/s/cffc3468/podcast/play/106817793/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2025-7-13%2F3a8297e4-ba0e-05fa-c8b9-69fbc33d37df.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/weaviate-podcast-6288219/episodes/gepa-with-lakshya-a-agrawal-weaviate-podcast-127
Duration seconds: 3715

## Resource

Lakshya A. Agrawal is a Ph.D. student at U.C. Berkeley! Lakshya has lead the research behind GEPA, one of the newest innovations in DSPy and the use of Large Language Models as Optimizers! GEPA makes three key innovations on how exactly we use LLMs to propose prompts for LLMs, (1) Pareto-Optimal Candidate Selection, (2) Reflective Prompt Mutation, and (3) System-Aware Merging. The podcast discusses all of these details further, as well as topics such as Test-Time Training and the LangProBe benchmarks used in the paper! I hope you find the podcast useful!

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/weaviate-podcast-6288219/episodes/gepa-with-lakshya-a-agrawal-weaviate-podcast-127/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/weaviate-podcast-6288219/gepa-with-lakshya-a-agrawal-weaviate-podcast-127.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.