← All implementations

DoorDash · Platform

Flux / Agentic AI Platform

DoorDash's internal agentic AI platform; a unified cognitive layer over company data and operations, with an AI Marketplace of specialized agents and the Flux cloud-agent runtime for engineering tasks.

1 Supports2 Supports3 Supports

Supporting infrastructure

This entry describes supporting infrastructure that other work builds on. The catalog classifies it as a platform. The record also reports a workflow.

Approach type
Platform
Work
Code review, Coding, CI triage, On-call, Maintenance, Data
Human involvement
Drafts reviewed
Invocation
Event driven, Interactive, Scheduled
Interfaces
Slack, Github, Scheduled, Cli, Skill, Cursor
Deployment stage
Scaled
Evidence strength
Detailed primary
Entry reviewed

How it works

The workflow the sources report for this implementation.

Isolated Firecracker microVM with repos, tools, secrets, runtime deps

3

Governed, audited access to CI, observability, issue trackers, deploy, code search

3

YAML unit of agentic work: task, inputs, skills, tools, permissions, validation, outputs

3

Identifies schemas, generates grounded SQL, validates via EXPLAIN before execution

2

Workflows -> agents -> deep-agent hierarchies -> swarms; governance hardens as control decentralizes

2

Where people stay involved

  • engineering task → reviewed agent outputWork product review · Level 3

Level 3 for engineering task → reviewed agent output; human attention boundary: work-product-review.

3

Observation date
2025-11-11

Implementation details

Sandbox

Firecracker microVMs; <5s p95 end-to-end setup (boot, clone repos, install tools, configure harness)

3

Harness

Maturity model: deterministic workflows -> ReAct agents -> hierarchical deep agents -> experimental swarms

2

Model

Model-agnostic platform primitives support third-party or in-house agent components

3

Interfaces

slack, github, scheduled, cli, skill, cursor

3

Tool access

In-house MCP gateway ('Agent Gateway'); LangGraph orchestration; prospective A2A; tools declared per playbook with scoped, logged permissions

2 Supports3 Supports

Knowledge

AI Marketplace of specialized agents; DataExplorer for grounded analytics; DoorDash-specific context in playbooks

2 Supports3 Supports

Credentials

Scoped per playbook; brokered through the gateway, never on the laptop; provenance on every action

3

Context management

Hybrid retrieval: BM25 + dense semantic + reciprocal-rank fusion -> RAG; schema-aware SQL with EXPLAIN validation

2

Reported results and limitations

The catalog records what the sources report, with the scope and the denominator of every figure. A qualification below limits the figure it sits under.

Reported metrics

Headline claim

130,000 engineering tasks automated in one month

1

The source does not report the denominator of this figure.

Reported by
DoorDash
Scope
Engineering tasks automated in one reported month; calendar measurement month unspecified
Observation date
2026-08-11
Key observation

130,000 engineering tasks automated in one month

1

The source does not report the denominator of this figure.

Reported by
DoorDash
Scope
Engineering tasks automated in one reported month; calendar measurement month unspecified
Observation date
2026-08-11
Key observation

25,000+ automated code reviews per week

1

The source does not report the denominator of this figure.

Reported by
DoorDash
Scope
Weekly automated code reviews powered by Flux
Observation date
2026-08-11
Key observation

300+ playbooks; 10,000+ invocations per week

3

The source does not report the denominator of this figure.

Reported by
DoorDash
Scope
Unique playbooks and weekly invocations on Flux

Lessons and interpretation

Start narrow to earn trust; began with automated code review before CI triage, on-call, maintenance, ticket-driven dev

3

Make the work visible; public Slack threads drove adoption; private per-run channels did not build team habits

3

Playbooks need enablement; workshops and hackathons turn repeated operational work into reusable playbooks

3

Earn complexity by exhausting simpler primitives first; keep swarms at the research frontier until governance catches up

2

Deterministic verification before probabilistic judgment; SQL linting and EXPLAIN before deeper validation; LLM-as-judge + DeepEval

2

Log provenance so any answer traces back to source queries, documents, and inter-agent activity

2

Sources and research details

Citations link to the original publisher. Each source also keeps a preserved copy in the repository, so a changed or removed page stays checkable.

  1. Delegating Engineering Work To Cloud-Based Agents (Flux)https://x.com/AIatDoorDash/status/2087285008906240193Social post · Direct participant · Last source verification: 2026-08-31
    Preserved copy ↗
  2. Beyond single agents: DoorDash's collaborative AI ecosystemhttps://careersatdoordash.com/blog/beyond-single-agents-doordash-building-collaborative-ai-ecosystem/Engineering blog · First party · Last source verification: 2026-08-31
    Preserved copy ↗
  3. Delegating Engineering Work To Cloud-Based Agentshttps://careersatdoordash.com/blog/delegating-engineering-work-to-cloud-based-agents/Engineering blog · First party · Last source verification: 2026-08-31
    Preserved copy ↗
Research details for every claim on this page
  1. Summary
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  2. Headline claim
    Statement type
    Metric
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    Dated August 11, 2026 report of a one-month count; this is the observation date, not the measurement window.
    Reported by
    DoorDash
    Scope
    Engineering tasks automated in one reported month; calendar measurement month unspecified
    Denominator
    Not reported
    Method
    Not reported
    Observation date
    2026-08-11
  3. Sandbox
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  4. Harness
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  5. Model
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  6. Interfaces
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  7. Tool access
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  8. Knowledge
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  9. Credentials
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  10. Context management
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  11. Supporting component
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  12. Supporting component
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  13. Supporting component
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  14. Supporting component
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  15. Supporting component
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  16. Key observation
    Statement type
    Metric
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    Dated August 11, 2026 report of a one-month count; this is the observation date, not the measurement window.
    Reported by
    DoorDash
    Scope
    Engineering tasks automated in one reported month; calendar measurement month unspecified
    Denominator
    Not reported
    Method
    Not reported
    Observation date
    2026-08-11
  17. Key observation
    Statement type
    Metric
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    Dated August 11, 2026 report; weekly measurement boundaries are not supplied.
    Reported by
    DoorDash
    Scope
    Weekly automated code reviews powered by Flux
    Denominator
    Not reported
    Method
    Not reported
    Observation date
    2026-08-11
  18. Key observation
    Statement type
    Metric
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
    Reported by
    DoorDash
    Scope
    Unique playbooks and weekly invocations on Flux
    Denominator
    Not reported
    Method
    Not reported
    Observation date
    Not reported
  19. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  20. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  21. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  22. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  23. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  24. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  25. Operating model assessment
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The platform spans several workflows; the cited engineering examples retain human review of agent output.
    Observation date
    2025-11-11
Back to the directory →