back_office_ops · ecommerce · workflow
Zalando uses LLMs to migrate UI component libraries across 15 B2B applications
Zalando's Partner Tech department had two distinct in-house UI component libraries causing inconsistent partner experience, duplicated design and development efforts, and increased maintenance complexity across 15 B2B applications.
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 · Component prompt crafting
Transformation prompts are crafted by providing component source code to the LLM to generate interfaces, transformation rules, and example migrations.
Tools used
GPT-4ocontinue.devllmPython
Outcome
The LLM-powered migration achieved over 90% accuracy across large file volumes and cost less than $40 per code repository, delivering significant time and resource savings.
What failed first
Initial LLM migration attempts without structured prompting produced inconsistent results; interface-only prompting yielded low accuracy; and automated mapping generation introduced flaws such as incorrect visual size equivalencies between the two libraries.
Results
Time saved30 and 200 seconds per file
Volumemore than 90%
Cost replacedless than $40
Running sinceSeptember 2024
Grounding & classification
Source type: technical build writeup
28 fields verified against source quotes.
code generationcode diff prbuilder submittedfailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedecommerceaccuracy improvementautomation ratecost reductionemployee productivitytime savedtechnical build writeupback office opsai draft human approval