quality_assurance · saas · workflow

uReview: Scalable, Trustworthy GenAI for Code Review at Uber

Uber's code reviewers were overloaded by the rising volume of changes driven by AI-assisted development, leaving insufficient time to catch subtle bugs, security vulnerabilities, and best-practice violations—leading to missed errors, slower feedback loops, production incidents, and wasted resources.

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 · Developer submits code change
When a developer submits a change on Uber's code review platform, uReview's automated review process begins.
Tools used
uReviewCommenterFixerClaude-4-Sonneto4-mini-highApache HiveApache Kafka
Outcome

uReview is deployed across all six of Uber's monorepos, analyzes over 90% of the approximately 65,000 weekly diffs, maintains a 75% usefulness rate, sees 65% of its comments addressed in the same changeset, and saves approximately 1,500 developer hours per week—equivalent to nearly 39 developer years annually—with a median review turnaround of 4 minutes.

What failed first

Third-party AI code-review tools were evaluated and found unsuitable: most required GitHub (Uber uses Phabricator), suffered from many false positives and low-value true positives, and could not interact with Uber's internal systems. Their per-diff costs at Uber's scale were also an order of magnitude higher than running uReview in-house.

Results
Time savedover 90%
Volume~65,000
Cost replacedorder of magnitude less
Source

https://www.uber.com/us/en/blog/ureview/

How we source this →

Grounding & classification
Source type: technical build writeup
39 fields verified against source quotes.
agentic workflowmulti agent workflowquality inspectioncode diff prbuilder submittedfailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedlogisticssoftwareaccuracy improvementemployee productivityerror reductionthroughput increasetime savedtechnical build writeupquality assuranceai draft human approvalextract classify route