DoorDash’s Flux Runs 130,000 Engineering Tasks Through Cloud-Based Agents
DoorDash has moved engineering agent workloads from developer laptops to its Flux cloud platform. The platform automated 130,000 engineering tasks in one month and supports more than 25,000 automated code reviews weekly. Flux uses isolated Firecracker microVMs, an MCP gateway, reusable playbooks, and multiple invocation surfaces to run agent workflows with scoped access and centralized auditing.…
DoorDash has transitioned engineering agent workloads from developers' personal computers to its Flux cloud platform, automating 130,000 engineering tasks in a single month in 2026. This platform supports over 25,000 automated code reviews per week, with more than 300 playbooks and over 10,000 weekly invocations, enabling workflows to operate unattended and in parallel.
DoorDash developed Flux due to the limitations of agent workloads running on individual laptops, which were restricted by CPU and memory capacity, dependent on device connectivity, and posed security risks. The platform's architecture revolves around four key components: cloud sandboxes, an MCP gateway, reusable playbooks, and invocation surfaces.
These elements allow for sandboxed, isolated execution environments, controlled access to internal systems, and various initiation methods such as Slack, GitHub, scheduled jobs, or conversational interfaces. DoorDash's implementation of Flux began with automated code review, a common and quantifiable workflow, and has since expanded to include CI triage, on-call tasks, maintenance workflows, and ticket-driven development.
The company also modified its Slack integration to public threads, allowing engineers to observe agent executions, review results, and assess how other teams allocate work.
Written by urgent.news from InfoQ's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.