quality_assurance · logistics · workflow
PerfInsights: Uber's GenAI system detects Go performance antipatterns and cuts optimization engineering time by 93%
Uber's top 10 Go services cost more than multi-million dollars in compute in March 2024 alone, yet optimizing Go services required deep expertise and days or weeks of manual profiling and analysis—making systematic performance tuning prohibitively expensive for most 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
CPU and memory profiles are collected from production services during peak traffic periods using Uber's daily fleet-wide profiler.
Tools used
PerfInsightsLLMLLMCheckOptix
Outcome
PerfInsights reduced engineering time per performance issue from 14.5 hours to almost 1 hour—a 93.10% time savings—and cut false positives from over 80% to the low teens, with hundreds of diffs already merged into Uber's Go monorepo.
What failed first
Initial single-shot LLM-based antipattern detection produced inconsistent and unreliable results—responses varied between runs, included hallucinations, and often generated non-runnable code, with false positives exceeding 80%.
Results
Time saved265
Volumeover 80%
Cost replacedmulti-million dollars
Grounding & classification
Source type: technical build writeup
41 fields verified against source quotes.
anomaly detectioncode generationcode diff prfailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedlogisticssoftwarecost reductionemployee productivityerror reductiontime savedtechnical build writeupback office opsquality assuranceextract classify routemonitor detect alert