quality_assurance · saas · workflow
Uber scales from 2 to 500+ Claude AI skills in 5 months through grassroots engineering adoption
Uber needed to move its entire SDLC toward agentic engineering across 200+ microservices and thousands of globally distributed engineers, while avoiding the top-down AI mandate pattern that has caused adoption to stall at other companies.
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 · Skill loaded from Golden Marketplace
Golden Marketplace skills are auto-loaded for all engineers and work out of the box.
Tools used
ClaudeClaude CodeLLM-as-a-JudgeiOS simulators
Outcome
A single engineer's side project grew organically into 500+ specialized AI skills powering Uber's engineering org, with 200+ curated skills in a governed Golden Marketplace and 300+ experimental tools in team repos, with twenty new skills being added per week.
Results
Time savedTwenty
Volume500+
Running sinceOctober 2024
Grounding & classification
Source type: listicle or blog summary
33 fields verified against source quotes.
agentic workflowai agentcode generationragcode diff prknowledge basehuman review describedmetric backednamed customerproduction runtime claimedsource backedtools describedvendor confirmedworkflow describedsoftwareautomation rateemployee productivitythroughput increaselisticle or blog summaryit supportquality assuranceagentic task executionai draft human approval