Building software factories and making the transition from a pre-AI to post-AI world as a large company w/ Zohar Einy #271
The Engineering Leadership Podcast

Building software factories and making the transition from a pre-AI to post-AI world as a large company w/ Zohar Einy #271

B2Upper-intermediateOctober 6, 202638 min
  • Interview
  • Technology

Zohar Einy, CEO & Co-Founder @ Port, shares best practices for building a software factory, how software factories impact the organizational structure of your org, and scaling strategies. He and Jerry discuss why software factories can contribute to a significant ROI, tools for helping your teams navigate the transition from building a product for agents vs. people, and what scary (but healthy) decision-making looks like as an eng leader in a post-AI world. Zohar also shares some of his core beliefs when it comes to developing talent & hiring young engineers @ Port. ABOUT ZOHAR EINY Zohar E...

Play episode

Opens the player: the full transcript, every word clickable, with translation and flashcards.

Try it: tap any word

Real sentences from the start of this episode. Every word is marked with its level.

Sentence 2 of 12 · 0:04

When an agent doesn't do what we expected,

because it's actually something that a person or a team can actually fix.

Hear this sentence

Tap a word to see its meaning in your language.

Do you know these words?

8 harder words from this episode. Tap one to see what it means, then mark it.

  • B20:04
  • B27:00
  • B213:03
  • B219:02
  • B226:31
  • B229:30
  • B236:19
  • B243:03

Mark a few words and we'll tell you how this episode fits your level.

Is this episode right for you?

B2

B2 · Upper-intermediate

Comfortable if you already follow TV news

A1 27%A2 34%B1 23%B2 14%C1 2%
  • 84% of the words are B1 or easier.
  • 217 words a minute: natural, fairly fast speech.
  • 180 harder words (B2 and up) in the whole episode.

Transcript

The opening of the episode. The whole transcript is in the player.

0:00

When an agent doesn't do what we expected, the context that it was working from is one of the most useful places to look because it's actually something that a person or a team can actually fix. Think of it as a chain.

0:15

The intent is what a person actually wants to get done. The harness is the machinery that receives that information, and it keeps memories and calls tools and runs the steps. Then the model supplies the intelligence at the end.

0:27

There's a whole discipline about improving models. there's another whole discipline about improving harnesses, but almost nobody is asking about improving the context. The CAFE's framework is a definition framework

That was the opening. The rest of the episode (38 min) is in the player: every word clickable, with translation, saved words and flashcards.

Continue in the player

Automatically generated from the audio. May contain errors. Audio belongs to its publisher and is played from their feed. Rights holders can request removal — copyright & takedown policy