Agent Swarms Do Months of Work in Days | Dexter Horthy artwork

Agent Swarms Do Months of Work in Days | Dexter Horthy

MTS

November 6, 2026

HumanLayer founder and CEO Dexter Horthy breaks down why his multiplayer coding agent platform is joining Factory and open-sourcing its code base.

0:00

Dexter Horthy

The fact that Swarms of Agents are now able to do months worth of work in a couple days makes it all the more important that humans can get together and align either one human with the agent or a team of humans working with that agent. And the human strap is in software, in teams where there's regulated industries, we can't just go to lights off and ship 100,000 lines of slop and hope for the best. If something is wrong, someone's getting fined millions of dollars.

0:27

Sophie

Hi everyone, welcome back to MTS. Today, I am joined by Dexter Horthy, the founder and CEO of HumanLayer, the multiplayer coding agent, IDE and cloud for running agents locally or in the background. And today, they had an exciting announcement. They officially announced that they are joining the factory team. So welcome Dexter to MTS.

0:46

Dexter Horthy

Hey, what's up? Great to be here.

0:48

Sophie

Great to have you. Big congratulations to you and all of factory. Tell us a little bit about what you guys announced today.

0:55

Dexter Horthy

Yeah, so we announced that we are joining forces with the factory team. And we're going to bring all of the really cool multiplayer stuff that we've built in HumanLayer and proved out with hundreds, and in some cases, thousands of engineers, into the factory product.

1:11

Sophie

Lots of cool human stuff that you're bringing from HumanLayer to factory. So for people who aren't super familiar with HumanLayer, tell us a little bit more about it. What are the features? What are the tools that you're bringing to factory?

1:23

Dexter Horthy

Yeah, so when we were building and we were working, and we spent a lot of time sitting with larger teams at larger enterprises and trying to solve problems that were probably not quite as well served by off-the-shelf coding agents, off-the-shelf coding harnesses. And one of the things we realized that was a lot of the work needed to shift left in the SDLC and the software lifecycle and move collaboration on not only the code at the end of the work, but the planning and the documents and the incremental commits that were being put into features. And so we built a ton of tech to sync all of that information real time. The code changes, the actual agent session back and forth, and any documents and plans were built fully collaborative so that whether an agent is running locally on your workstation or in a background worker or anywhere else, anybody in the team can jump in and collaborate on the work being done.

2:14

Sophie

Yeah. Tell us a little bit about the big shift that's happening right now in 2026 Of course, people are using agents when they're coding. That's not super new to this year, but the multiplayer aspect is a bit new. People don't totally know how they should be interacting with multiplayer coding agents. So tell us a little bit how the landscapes changed.

2:33

Dexter Horthy

Well, I think the biggest benefit to multiplayer, right? You can say it and it does a cool demo, but the real question is like, does it help you ship faster? And in working with customers, what we saw was when people were able to align on an outline of the work, a high level 200 line plan document before they get to the coding, it reduced the need for rework later on what was built.

And that has led to a much greater velocity for people who are adopting and trialing these workflows in HumanLayer. So this collaboration drives speed and outcomes more than anything else.

3:09

Sophie

Yeah. And I know you spent the last time actually talking to a lot of these enterprise customers and like you alluded to, things work great in a demo, but then when you get to production, there are all these issues that enterprise customers are facing that maybe weren't as obvious. Can you tell us a little bit about that?

3:26

Dexter Horthy

Well, so multiplayer brings with it a lot of interesting challenges in the enterprise, especially around audit and authentication and access to the systems. If I'm talking to my agent, the agent can just act on my behalf and perhaps look at my Slack, edit notion documents as me, interact with GitHub. But as soon as you have multiple people in a single conversation, you need to compute what is the minimum surface that all those people have access to, or assign a specific authentication profile to that session. And then when things are done on behalf of the agent, there's all these audit needs as well. And so it's like, how do you actually track and attribute specific actions to a human upstream from what was said and how do you bring that all together? So I think the enterprise and what Factory has done really, really well is build a system with all of these governance and controls and even things like cost tracking, which are not really like a compliance thing, but are incredibly useful when you have a large team with hundreds of engineers.

Read the other 9 minutes of this episode here.

$15 gets you this episode and 99 more. Credits never expire. After checkout, one link brings you back here to read it.

Not what you expected? Full refund within 14 days.

Thousands of transcripts fetched by people building searchable podcast archives

Fetch transcripts with code

The same credits work from a script or an AI agent. The demo key returns a sample episode in full, no card needed:

request
curl -H "x-api-key: pt_demo" \
  https://spoken.md/transcripts/1000651996090

Markdown with the speakers named, for your notes, your knowledge base, or anything that makes HTTP calls.

From $0.10 per transcript. No subscription. Credits never expire. Prices exclude VAT, added at checkout for EU customers. Not what you expected? Email us within 14 days with 20 or fewer credits used and we refund the pack in full.

Using your own key:

request
curl -H "x-api-key: YOUR_KEY" \
  https://spoken.md/transcripts/1000800231917