quality_assurance · saas · workflow
PerfInsights: Uber's GenAI system detects Go performance antipatterns with 93.10% engineering time savings
Uber's top 10 Go services cost more than multi-million dollars in compute per month, while traditional performance tuning demanded deep expertise and days or weeks of profiling work, making systematic optimization non-trivial for most engineering teams.
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 · Production profile collection
PerfInsights leverages CPU and memory profiles from production services using Uber's daily fleet-wide profiler during peak traffic periods.
Tools used
LLMLLMCheckOptix
Outcome
PerfInsights reduced engineering time to detect and fix performance issues by 93.10%, achieved a 33.5% reduction in antipatterns over four months, and merged hundreds of diffs into Uber's Go monorepo.
What failed first
Initial single-shot LLM-based antipattern detection produced inconsistent and unreliable results with hallucinations and often non-runnable code, and false positive rates exceeded 80%.
Results
Time savedTasks that once required days now take hours
Volumehundreds of diffs already generated and merged
Cost replacedmulti-million dollars
Grounding & classification
Source type: technical build writeup
44 fields verified against source quotes.
anomaly detectioncode generationquality inspectioncode diff prfailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedlogisticssoftwareaccuracy improvementcost reductionemployee productivityerror reductiontime savedtechnical build writeupquality assuranceagentic task executionmonitor detect alert