MLSG - The Agent Harness Revolution

This month, we return to the crowd-favourite topic of Agentic Systems & Harnesses!

Talks:
"Patterns of Successful Agent Harnesses" - Sam Witteveen
In a talk he previously delivered at Google Cloud Next in Las Vegas, Sam will focus on the core patterns and components of successful agents and harnesses, covering patterns from coding agents like Claude Code & Codex through personal agents like OpenClaw & Hermes. These patterns clearly show what is working in building modern agents.

"Local Models & Self-Evolving Harnesses" - Martin Andrews
In his talk, Martin will first explain how a number of the recently announced self-updating harness systems work. Then, in light of the recent turbulence in the world of Foundation Models, he'll talk about Local Models, and how to increase business robustness.

FOOD UPDATE : Google has told us that there WILL BE pizza at the event

---

Talks will start at 7:10pm (entry at 6:45pm) and end at around 9:00pm, at which point attendees can come up to the front for a bit of a chat with each other, and the speakers.

Due to some recent security incidents at the venue please take note of the new DevSpace security procedures https://bit.ly/devspace-security
Attendees will not be admitted later than 15min after the talks have started.

As always, we're actively looking for more speakers - both '30 minutes long-form', and lightning talks. For the lightning talks, we welcome folks to come and talk about something cool they've done with keras, PyTorch, JAX and/or Deep Learning for 5-10mins (so, if you have slides, then #max=10). We believe that the key ingredient for the success of a Lightning Talk is simply the cool/interesting factor. It doesn't matter whether you're an expert or an enthusiastic beginner: Given the responses we have had to previous talks, we're sure there are lots of people who would love to hear what you've been playing with. If you're interested in talking, please just introduce yourself to Martin at one of the events.