quality_assurance · ecommerce · workflow
ASOS introduces Test-Driven Vibe Development (TDVD) to deliver MVP 7–10× faster than estimate
Vibe coding with AI agents produced code without sufficient rigour, with hallucinations, hidden defects, and security risks. LLMs' attention diffusion in large contexts caused accuracy to decline as prompt complexity grew, making naive AI-assisted development unreliable for enterprise product builds.
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 · Plan: define intent test-first
The workflow begins with defining the solution intent in a test-first manner before any code generation.
Tools used
Azure FunctionsReactAI agent
Outcome
The team delivered the MVP plus additional capabilities in 4 weeks, which was 7–10 times faster than the original estimate of 4–6 months, with 42 hours of total active development time.
What failed first
Initial vibe coding attempts matched widely documented concerns about quality and rigour. During the TDVD trial, early over-sized feature prompts caused LLM context loss, requiring the team to tear down and rebuild the solution twice.
Results
Time saved4 weeks
Volume7–10 times faster
Grounding & classification
Source type: technical build writeup
26 fields verified against source quotes.
agentic workflowcode generationcode diff prfailure mode describedhuman review describedmetric backednamed customersource backedtools describedworkflow describedretailcycle time reductionemployee productivitytime savedtechnical build writeupquality assuranceagentic task executionai draft human approval