Viewing profile — ATechGuy

This is very useful. Thanks for sharing!

In the last couple of months, several new solutions for sandboxing AI agents have launched (microVMs, WASM runtimes, browser isolation, hardened tool containers, etc.). Curious to …

+1

You built https://github.com/FootprintAI/Containarium for this purpose?

In the last couple of months, several new solutions for sandboxing AI agents have launched (microVMs, WASM runtimes, browser isolation, hardened tool containers, etc.). Curious to …

Lately we've been noticing a non-trivial amount of traffic in our logs that doesn't look like typical bots. Not the usual noisy crawlers or obvious scrapers. The behavior is differ…

[Posting again in hopes of gaining further perspectives and insights] Do you still browse the web the same way you did (say 5 years ago) or you use AI to browse, summarize, etc. on…

TBH, this looks like an LLM-assisted response.

+1. It is confusing.

And how are you going to define what ocaps/flows are needed when agent behavior is not defined?

Do you still browse the web the same way you did (say 5 years ago) or you use AI to browse, summarize, etc. on websites? Is it about speed/efficiency, instant answers (gratificatio…

Interesting. I'd appreciate an example. Thanks!

Would love to see performance numbers with nested virtualization, particularly that of IO-bound workloads.

> a website can expose functions like searchProducts(query, filters) or orderPrints(copies, page_size) with full parameter schemas How would this not create backend load and abuse?…

That's a good start I'd say, but I agree with you that detection is not trivial. I wonder if there's enough value in distinguishing between AI agents (with full browser) and humans…

Yes, but how can you tell if it was an agent with full browser?

Thanks for your insights! QQ: does uxwizz also show AI agents visiting websites? have you seen traffic from AI agents?

There's a lot of talk about agentic systems that AI can take actions, run workflows, and operate autonomously. However, when I look at AI startups, most of them seem to be building…

I agree. However, how to define these permissions when agent behavior is undefined?

I understand the concern. However, you can customize the profile (e.g., allowlist) to only allow network access to required domains. Also, looks like your sandboxing solution is Do…

That's right. But they (E2B) rely on the underneath Cloud infra to achieve high scalability. Personally, I'm still not sure about the value they add on top of Cloud hosted VMs. GCP…

To the commenters here: thanks for correcting me! So AWS is losing AI sandboxing market to GCP due to high cold start times of EC2...very interesting!

You can customize curr_dir_access_profile.sb to block access to network/fs/etc. Why is this not enough?