The Client
AMPECO
- • Software for management of EV charging stations
- • Funded by BMW iVentures
- • Operates 4.5M+ charging sessions
Join the age of practical AI
We build end-to-end AI solutions that leverage existing data to its fullest potential
AI Consulting 
and ML Development
a team of AI technology experts specializing in AI consulting and developing ML algorithms
VALUE POINTS
Case
Studies
The Challenge
What we had to solve
- • Charger users anxious about station availability
- • Station crowding at peak times
- • EV Station operators cannot set dynamic rates and plan repairs
- • Planning and balancing issues for grid operators
Our Solution
How we solved the problem?
Predict Usage of EV Charging Stations with AI
Our Approach
How we solved the problem
State-of-the-Art Algorithms
• Build upon existing academic AI research with papers as recent as 2022
Hybrid Model
• Combining domain knowledge and AI raised prediction accuracy from 70% to game-changing 85%
Minimally Invasive
• We accessed only the necessary data and integrated the solution without disrupting existing processes
Created Value
Our contribution
For Station Users:
- • Seamless EV charging experiences
• Efficient trip planning
For Station Operators:
- • Maximize profits through dynamic rates
- • Plan repairs during downtime
Outcome
The end result
- • Solution leveraged customer’s existing infrastructure and partnerships
- • 85% prediction (business applicable) accuracy for stations in Europe
- • MLOps retraining pipeline to handle data drift* and ensure long-term performance
The Client
SCHÖELLY
- • Top 10 medical device company
- • High-end German optical devices
- • Global reach
The Challenge
What we had to solve
Traditional QA:
- • Manual inspection of endoscopes for blurring, contamination, misalignment
Challenges:
- • Time-Consuming
- • Subjective
- • Costly
Our Solution
How we solved the problem?
AI-Powered QA for Production of Optical Devices
Our Approach
How we solved the problem
Hybrid Algorithm
• Combining traditional computer vision with domain-specific measurements
Integration of MTF
• Modular Transfer Function for measuring endoscope blur compatible with manual inspection
In Line with ISO13485
• ISO protocol for medical devices – 2000 page compliance validation
Created Value
Our contribution
- • Faster QA
- • Eliminated human bias
- • Recall/Rework reduction
- • Automated compliance
Used in the USA, Canada, and China
Outcome
The end result
- • Benchmarked against industrial-grade software
- • 100% replicability through ISO-mandated testing
- • In-Browser proprietary solution in line with medical regulations
- • On-Premises Hosting avoiding international compliance problems
Technical
Stack
