endorsedOngoing

Zapier-to-AWS Backend Migration, API Development & AI Chatbot Improvements for GetOnyx

Services Covered:

AI and Machine Learning • Cloud Consulting and Services

Industry

Information Technology

12 months

Budget

Confidential

Start Date

1 December 2024

Team Size

6-10

Engagement Model

Offshore

Project Capability Score (PCS)

77/100

Good

Project Capability Score (PCS) estimates how capable Valere is of successfully delivering a project like this, based on its past experience, track record, and ability to handle similar work. Learn more about PCS

Client

GetOnyx

United States of America

Project Summary

Valere migrated the client's backend from a Zapier-based architecture to AWS, developed custom APIs, redesigned the UX/UI, and trained and fine-tuned AI models to improve chatbot performance. The engagement produced measurable improvements including a 50% boost in chatbot response accuracy, a 30% increase in user satisfaction, and a 40% gain in feature implementation efficiency. The team also supported integration with Microsoft licensing data and performed load and scalability optimization.

Key Challenges

Complete backend migration from a Zapier-based architecture to AWS
Custom API development using AWS services for advanced features
AI model deployment, training and fine-tuning with prompt optimization
Integration with existing Microsoft licensing data systems
Load testing and scalability optimization to support enterprise customers

Project Deliverables

Migration from Zapier to AWS backend architecture
Custom API development
Complete UX/UI redesign
AI model training and fine-tuning with iterative prompt optimization
Chatbot response accuracy improvements
System integration with Microsoft licensing data
Load testing and scalability optimization

Project Solution

Valere executed a full migration from a Zapier-based backend to AWS, developed custom APIs to support advanced features, and completed a UX/UI redesign for an enterprise-grade interface. The team trained and fine-tuned AI models with iterative prompt optimization to improve chatbot accuracy, integrated the system with existing Microsoft licensing data, and performed load testing and scalability optimization. The client engaged 6–10 Valere team members and the work is ongoing since December 2024.

Project Outcome

50% improvement in chatbot response accuracy
30% increase in user satisfaction scores
40% efficiency gain in feature implementation
Enabled enterprise market entry and targeting of $100M+ revenue customers
Elimination of recurring platform costs from the previous solution

Platforms

Cloud
AI/ML Platform
API/Integration Platform

Tech Stack

Amazon Web Services (AWS)
REST API

Client Endorsement

Overall Review Rating

Timeliness

Cost Rating

Willing to Refer

Quality of Deliverables

Our chatbot's response accuracy is up 50% thanks to Valere. User satisfaction scores have risen 30%, and we're implementing features 40% more efficiently. On top of that, they're flexible and honest, and they're committed to doing high-quality work within the timeline we set.
Chris Brown
Co-Founder
Date: 12/22/2025