A single long-lived sandbox per project would need provisioning for peak load and months of uptime.
Instead, repositories live on S3-backed storage and each agent runs in its own ephemeral sandbox, so a crash loses only unsubmitted work.
Perplexity says one long-lived sandbox per project would require provisioning for peak load and months of uptime. Its design stores repositories on S3-backed storage and runs each agent in its own ephemeral sandbox, so a crash loses only unsubmitted work.
Part of a thread · earlier post
A single long-lived sandbox per project would need provisioning for peak load and months of uptime.
Instead, repositories live on S3-backed storage and each agent runs in its own ephemeral sandbox, so a crash loses only unsubmitted work.
Source: Perplexity · x.comPublished · added here