quality_assurance · saas · workflow
Atlassian builds Firecracker microVM platform in four weeks using Rovo Dev AI agents
Building a Firecracker microVM orchestrator on Kubernetes required constructing a scheduler, autoscaler, node agents, envoy ingress layers, raft persistence, and more — a scope previously considered too long, too complex, and beyond the team's domain expertise.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Multi-workspace agent setup
A developer runs three workspaces, each checked out on a different branch with an agent working.
Tools used
Rovo DevFirecrackerKubernetesBitbucket · partnerPipelines · partnerHelmeBPFAWS
Outcome
Atlassian built the Fireworks platform — a Firecracker-based microVM system with 100ms warm starts and live migration — in four weeks, entirely by LLMs using Rovo Dev agents.
Results
Time saved100ms warm starts
Grounding & classification
Source type: technical build writeup
31 fields verified against source quotes.
agentic workflowai agentcode generationmulti agent workflowcode diff prhuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedsoftwarecycle time reductionemployee productivitythroughput increasetechnical build writeupquality assuranceagentic task executionai draft human approval