Deflaker
- Company
- Dropbox
- Approach type
- Agent
- Work
- Coding
- Human involvement
- Unknown
- Invocation
- Event-driven
- Deployment stage
- Deployed
- Evidence strength
- Detailed primary
- Entry reviewed
Purpose
Deflaker investigates and repairs flaky tests for Dropbox engineers using Nova.
How it works
Representative workflow: Athena flaky-test detection → CI-validated fix or capped attempts. Research details
Athena identifies flakiness; Deflaker gathers passing and failing logs.
Nova diagnoses the likely cause and proposes a change.
Failed validation starts another attempt with new logs and prior notes; the workflow lands a fix or stops after five attempts.
Where people stay involved
Each scope pairs its normal attention boundary with supporting evidence. See the supervision definitions for the level mapping and limits.
Unreported: The source describes an automated fix-and-validate loop and publication outside the agent, but does not state the required human approval or exception-handling policy.
Athena flaky-test detection → CI-validated fix or capped attempts
Unknown · Level unknown
Catalog interpretation: Unclassified for Athena flaky-test detection → CI-validated fix or capped attempts; human attention boundary: unknown.
Observed in 2026
Implementation details
- Model
- Not reportedNot documented for this subject in the reviewed source.
- Harness
- Durable remediation workflow calling Nova; publication and CI remain outside the coding agent.
- Sandbox
- Not reportedNot documented for this subject in the reviewed source.
- Tool access
- Not reportedNot documented for this subject in the reviewed source.
- Knowledge
- Not reportedNot documented for this subject in the reviewed source.
- Context management
- Prior attempt notes and new test logs accompany retries.
- Credentials
- Not reportedNot documented for this subject in the reviewed source.
- Interfaces
- Not reportedNot documented for this subject in the reviewed source.
Validation and failure handling
CI repeats the test at least 100 times, depending on its failure rate.
Reported observations
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.
Unreported: The reviewed source does not document this for the named subject.
Lessons
Unreported: The reviewed source does not document this for the named subject.
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.
- Introducing Nova, our internal platform for coding agentshttps://dropbox.tech/machine-learning/introducing-nova-our-internal-platform-for-coding-agents
Question coverage and scope
- purpose
- Reported
- workflow
- Reported
- human involvement
- Unreported: The source describes an automated fix-and-validate loop and publication outside the agent, but does not state the required human approval or exception-handling policy.
- implementation
- Reported
- validation
- Reported
- observations
- Unreported: The reviewed source does not document this for the named subject.
- lessons
- Unreported: The reviewed source does not document this for the named subject.
Research details for every claim on this page
- Summary
- Statement type
- Fact
- Provenance
- Reported
- Confidence
- High
- Confidence reason
- A linked first-party source states the claim.
- SupportsIntroducing Nova, our internal platform for coding agentsHow we’re using the platform: Flaky test remediation; What we learned
- Harness
- Statement type
- Fact
- Provenance
- Reported
- Confidence
- High
- Confidence reason
- A linked first-party source states the claim.
- SupportsIntroducing Nova, our internal platform for coding agentsHow we’re using the platform: Flaky test remediation; What we learned
- Context management
- Statement type
- Fact
- Provenance
- Reported
- Confidence
- High
- Confidence reason
- A linked first-party source states the claim.
- SupportsIntroducing Nova, our internal platform for coding agentsHow we’re using the platform: Flaky test remediation; What we learned
- Collect evidence
- Statement type
- Fact
- Provenance
- Reported
- Confidence
- High
- Confidence reason
- A linked first-party source states the claim.
- SupportsIntroducing Nova, our internal platform for coding agentsHow we’re using the platform: Flaky test remediation; What we learned
- Propose a repair
- Statement type
- Fact
- Provenance
- Reported
- Confidence
- High
- Confidence reason
- A linked first-party source states the claim.
- SupportsIntroducing Nova, our internal platform for coding agentsHow we’re using the platform: Flaky test remediation; What we learned
- Validate repeatedly
- Statement type
- Fact
- Provenance
- Reported
- Confidence
- High
- Confidence reason
- A linked first-party source states the claim.
- SupportsIntroducing Nova, our internal platform for coding agentsFlaky test remediation: CI runs the proposed change 100 or more times depending on failure rate
- Retry or finish
- Statement type
- Fact
- Provenance
- Reported
- Confidence
- High
- Confidence reason
- A linked first-party source states the claim.
- SupportsIntroducing Nova, our internal platform for coding agentsHow we’re using the platform: Flaky test remediation; What we learned
- Operating model assessment
- Statement type
- Inference
- Provenance
- Catalog judgment
- Confidence
- Unverified
- Confidence reason
- The source describes an automated fix-and-validate loop and publication outside the agent, but does not state the required human approval or exception-handling policy.
- Observation date
- 2026
- SupportsIntroducing Nova, our internal platform for coding agentsFlaky test remediation: workflow lands a working fix or reaches five attempts; diagram describes the automatic retry loop