Role: Product Designer & AI Strategist
Traditional manual bookkeeping takes 40+ hours per month, has high error rates, and accountants spend most of their time on repetitive categorization tasks.
Design a semi-automated AI workflow that dramatically reduces bookkeeping time while maintaining accuracy.
60% reduction in bookkeeping time, 97% classification accuracy, and 75% fewer manual reviews.
"Not every step needs AI — the key is finding the optimal split point for human-machine collaboration."
We route classification results into three processing paths based on the AI model's confidence score, balancing efficiency with accuracy:
High-confidence results pass automatically, no human intervention needed
Medium-confidence results are quickly reviewed and confirmed by accountants
Low-confidence results are handed off for full manual processing
We started with a high threshold (99%) and gradually lowered it as model accuracy was validated, letting the system grow through earned trust.
The experience when AI makes mistakes matters more than when it's correct. Every automated step has clear fallback mechanisms and human intervention points.
Every human review becomes training data for model improvement. The longer the system is used, the less human intervention is needed, creating a positive feedback loop.
"The core of AI product design isn't pursuing 100% automation — it's finding the balance point where humans and machines each deliver maximum value. True wisdom is knowing when to let AI decide, and when to hand the decision back to humans."
This project taught me deeply that the best AI products don't replace humans — they amplify human judgment. When we position AI as an "assistant" rather than a "replacement," user acceptance and trust increase dramatically.