← All implementations

Dropbox · Platform

Nova

Nova is Dropbox's internal service for running coding agents in its cloud. Engineers launch parallel sessions from a web UI, CLI, or API, and internal systems call agents inside automated workflows like CI triage and migrations. Callers attach validation commands that Nova runs after each attempt.

1

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
Coding, CI triage, On-call, Maintenance
Human involvement
Human in loop
Invocation
Event driven, Interactive
Interfaces
Web, Cli, Api, Slack
Deployment stage
Scaled
Evidence strength
Detailed primary
Entry reviewed

How it works

The workflow the sources report for this implementation.

Bounded iteration with feedback on failure; deterministic systems control test execution

1

Dropbox context-engineering system feeding agents across the SDLC

1

Where people stay involved

  • agent-assisted SDLC workflow → accepted changeUnknown · Level unknown

Unclassified for agent-assisted SDLC workflow → accepted change; human attention boundary: unknown.

1

Observation date
2026-05-22

Implementation details

Sandbox

Isolated env with a codebase snapshot at a specific commit; full Dropbox monorepo via Bazel; hermetic remote execution + caching

1

Harness

Validation loop (propose → validate → feed back) with continue_on_validation_failure and max_iterations (~5); branch management kept outside the agent

1

Model

Platform-agnostic; multiple coding agents behind one interface; swap models without rebuilding infra; prompt-eval tooling

1

Interfaces

web, cli, api, slack

1

Tool access

Skills/plugins to gather evidence, read logs, inspect failures; MCP integrations; Bazel-aware selectivity tools

1

Knowledge

Localized AGENTS.md per service; Dash (Dropbox context engineering); passing + failing test logs

1

Credentials

Operates within Dropbox's existing infra and validation paths; same auth/authz as engineers

1

Context management

Session history (notes/logs) carried across retry attempts

1

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

Dozens of agents can run in parallel from one runbook

1

The source does not report the denominator of this figure.

Reported by
Dropbox
Scope
Migration-owner orchestration of dozens of agents from a shared runbook; qualitative capacity description
Key observation

Flaky-test remediation (Deflaker): 100+ validation runs

1

The source does not report the denominator of this figure.

Reported by
Dropbox
Scope
CI validation runs per proposed Deflaker flaky-test fix
Method
Run the test 100 or more times depending on its failure rate; retry capped at five fix attempts
Key observation

Predecessor Goose-based migrator used across thousands of migration entries before workflows moved onto Nova

1

The source does not report the denominator of this figure.

Reported by
Dropbox
Scope
Predecessor Goose-based migrator, before workflows moved onto Nova
Key observation

Dozens of agents launchable from one runbook

1

The source does not report the denominator of this figure.

Reported by
Dropbox
Scope
Migration-owner orchestration of dozens of agents from a shared runbook; qualitative capacity description

Lessons and interpretation

Platform value exceeds code generation; validation, guardrails, and context matter as much

1

Context, validation, and guardrails reinforce each other to make background work trustworthy

1

Not every step belongs in the agent loop; deterministic systems should control test execution and timing

1

Integrate with existing engineering infrastructure rather than building separate AI-specific workflows

1

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. Introducing Nova, our internal platform for coding agentshttps://dropbox.tech/machine-learning/introducing-nova-our-internal-platform-for-coding-agentsEngineering blog · First party · Last source verification: 2026-08-31
    Preserved copy ↗
  2. Hacker News submission for Novahttps://news.ycombinator.com/item?id=48235065Hn thread · Community · 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
    High
    Confidence reason
    A linked first-party source states the claim.
    Reported by
    Dropbox
    Scope
    Migration-owner orchestration of dozens of agents from a shared runbook; qualitative capacity description
    Denominator
    Not reported
    Method
    Not reported
    Observation date
    Not reported
  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. Key observation
    Statement type
    Metric
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
    Reported by
    Dropbox
    Scope
    CI validation runs per proposed Deflaker flaky-test fix
    Denominator
    Not reported
    Method
    Run the test 100 or more times depending on its failure rate; retry capped at five fix attempts
    Observation date
    Not reported
  14. Key observation
    Statement type
    Metric
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
    Reported by
    Dropbox
    Scope
    Predecessor Goose-based migrator, before workflows moved onto Nova
    Denominator
    Not reported
    Method
    Not reported
    Observation date
    Not reported
  15. Key observation
    Statement type
    Metric
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
    Reported by
    Dropbox
    Scope
    Migration-owner orchestration of dozens of agents from a shared runbook; qualitative capacity description
    Denominator
    Not reported
    Method
    Not reported
    Observation date
    Not reported
  16. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  17. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  18. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  19. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  20. Operating model assessment
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Unverified
    Confidence reason
    The source documents human participation but does not locate one consistent attention boundary across Nova workflows.
    Observation date
    2026-05-22
Back to the directory →