CtrlK
BlogDocsLog inGet started
Tessl Logo

ainativedev/aidevcon-2026-ldn

AI Native DevCon 2026 London — all conference sessions as interactive skills

70

Quality

88%

Does it follow best practices?

Impact

—

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

quote.mdtalk-marsden-agent-desktops/

Notable verbatim quotes

#QuoteTopicSection
1"all information work is eventually going to become. About managing agents."Thesis§1
2"one of them decided to get stash to work for all the other ones would do it. And then the following day a different agent decided to RM minus RF dot on my git checkout. And this actually happened."Pain motivating the work§2
3"this idea of making the snake eat its own tail by actually using our own stuff that we were building to build itself."Dogfooding§2
4"My opinion number one is you should give each agent their own computer, not each human."Centralization§4
5"you wouldn't hire a team of software developers and ask them all to share one computer. You should give each agent their own computer."Centralization analogy§4
6"Claude Code started making us like not look at the code so much. And I genuinely feel like it made me stupider."IDE opinion§5
7"do you know Claude Code is implemented in React? And so they've ended up having to implement basically a web browser and terminal. It's just. Like, can't we just have a working text box?"Tooling rant§5
8"They end up kind of devolving into enterprise politics because they were trained on all of this human data of how humans argue with each other about stupid stuff."Org-shape scaling failure§6
9"if you want like a good background agent experience. That feels like the foreground agent experience. You end up implementing GPU accelerated desktops"Why GPU desktops§7
10"We use Zed because it's fast. And we also forked it so that you can remote control it."Forked Zed§7
11"if you get the agent to write a plan before it does the work, you get much better results because you can then correct it and you can kind of do that design work before the agent has gone off in the wrong direction"Spec-driven rationale§8
12"the terminal like Claude Code is actually a terrible place for reviewing and commenting on documents. It's much nicer to use a Google Docs style UI"Spec review UX§9
13"our niche pitch is that this is the best way to run Zed on your iPad while you're at the gym. And I had one person commenting that's like, I feel seen."Mobile experience§10
14"it took 40 minutes to build our stack from scratch in Docker. And there's really no point being able to spawn agent sandboxes rapidly if those agents are going to say 40 minutes before they can do any useful work"Bootstrap-speed problem§11
15"most of my day now when I'm doing technical work is that I'm reviewing the specs and I find two lines in the spec where the agent got it wrong … and just comment on those two lines"Day-to-day after dogfooding§12
16"These open source models like Llama 3.1 and so on and can now do pretty much 80% of the work that you need to do."Local models§13
17"instead invest in some hardware with like 8x RTX 6000 Pro in it … you can still kind of burst out to Claude Opus 4.1. If you feel something really hard."Model-mix strategy§13
18"the agent can be like, oh, can you do two factor auth please? Now? LinkedIn thinks I'm human. And I kind of am. I'm a human that's. Like using an agent kind of like a mechanical suit."Human-agent collaboration§14
19"we're already doing better than like opening the floor on your man. Ini. When I saw the open Claude one Password extension, I was like."Security stance§16
20"you need an IDE on the inside. You also need the meta IDE which is like the control plane for all of the different agency running."IDE + meta-IDE§18

talk-marsden-agent-desktops

outline.md

quote.md

SKILL.md

transcript.md

README.md

tile.json