quality_assurance · saas · workflow
How Delivery Hero's agent merges 100+ pull requests a day with Claude
Delivery Hero's engineering teams across dozens of regional operations each had different build systems, infrastructure setups, and engineering cultures inherited from independent acquisitions. Centralizing AI tooling was hampered by procurement delays and a decentralized experimentation phase that made consistent measurement and scaled adoption impossible.
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 · Task assigned via Jira
Herogen picks up tasks assigned through Jira.
Tools used
ClaudeClaude Opus 4.5Claude CodeHerogenVertex AI · partnerLiteLLMJiraGemini
Outcome
Herogen now merges over 100 pull requests per day at an 85% success rate, achieving 18 times the original Q1 2026 quarterly goal. Claude accounts for 95% of LiteLLM model requests across central engineering teams, with a 9-to-2 preference for Claude emerging from a survey of the CTO group.
Results
Time saved>100
Volume85%
Cost replaced95%
Running sinceQ4 2025
Grounding & classification
Source type: vendor customer story
39 fields verified against source quotes.
agentic workflowai agentcode generationmulti agent workflowcode diff prfailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedsource backedtools describedworkflow describedlogisticssoftwareautomation ratecycle time reductionemployee productivitythroughput increasevendor customer storyquality assuranceagentic task executionai draft human approval