AnthropicVerified interview challenge
Image Processing Pipeline
Build an image-processing pipeline from JSON recipes, then improve its throughput on a larger batch.
Unlock with Full AccessThe challenge
You are given image files, ordered transformation recipes and file-handling helpers. Implement the pipeline on a small image set, then carry the same code into a second part with larger images and a choice of worker count. Compare runs while keeping the transformed outputs correct.
- Correctness and timing
- Your score reflects the generated images. Processing times are recorded separately so you can compare approaches as you optimise.
What you'll practise
Transformation pipelines
Apply a sequence of image operations in the right order and save the resulting files.
Batch processing
Organise the work across images and recipes without losing or overwriting results.
Concurrency
Compare execution approaches on a larger workload and measure the effect of using more workers.
Current partFurther parts unlock as you progress
solution.pyPython 3.13
# Build on your implementation
# Run checks for the current part
# Full starter code includedCurrent-part checks
Run your code to see results.
The complete sequence, starter code and checks are included with Full Access.