September 2, 2025

How Tilt Global Proved Their AI Coaching Vision With Celerik

Overview

Industry:

  • Professional Services / EdTech


Region:

  • United States

Project Duration

  • PoC: 12 weeks
  • Post-Delivery Support: 3 months

Services Provided:

  • AI Strategy & Prototyping
  • Full-StackDevelopment
  • UX Design for Investor Demos
  • Data Engineering


Tech Stack:

  • Frontend: React + Vite
  • Backend: Python, FastAPI
  • AI & Cloud: Azure AI Studio, OpenAI, CosmosDB, Azure Blob Storage

The Challenge

Tilt Global set out to do something no one had done before: create an AI-powered coaching assistant that could detect decision-making biases without offering direct advice. Their mission was ambitious and technically untested.

With just two founders and limited funding, they needed to:

  • Prove technical feasibility with a bias-detection engine
  • Deliver a compelling, investor-ready demo to secure funding
  • Lay the groundwork for a scalable platform that could support multiple clients
  • Do it all on a tight timeline and budget

“Juan Carlos (Celerik CEO) understood our financial situation and offered to delaypayment—something we hadn’t expected. That flexible partnership set Celerik apart.”
Brennon Martin, Co-Founder, TiltGlobal

Our Solution

1. AI Feasibility POC

We ingested real Decision-Making Lab (DML) transcripts into CosmosDB and built a Python-based API to tokenize text and run bias detection using GPT-4o. This provided fast, context-rich outputs while preserving data structure and performance integrity.

2. UX That Wins Investors

We crafted a clear, interactive dashboard in React/Vite that highlighted bias patterns and dynamics within teams. We ran design iterations every 48 hours, incorporating feedback from five early users to ensure the demo aligned perfectly with Tilt Global’s narrative.

3. Built to Evolve

While the initial POC remained local and didn’t implement cloud automation or CI/CD,it was structured with clear paths for scalability. Future phases include moving infrastructure to Azure and enabling real-time coaching interfaces.

The Results

  • Technical proof of concept delivered with full bias detection logic
  • Demo-ready UX
  • 500 ms median API response time under demo load
  • ✅Delivered 20% under original engineering budget

“We accomplished the objective of proving our vision’s technical feasibility with minimal cost and effort. Now we know our AI coaching model is viable and ready to scale.”
Brennon Martin, Co-Founder, TiltGlobal

 

What We Learned

  • Lock in deliverables early: A “definition of done” workshop will guide future engagements.
  • Agile needs a leader: Embedding a dedicated Scrum Master ensures tighter sprint execution.
  • Plan for scale early: Future features include group analytics, real-time chat, and mobile dashboards.

📩 Contact us to get started

Related articles

You may also like these

Subscribe to The Edge

Strategies on AI, data, and automation, plus success stories from leading businesses, straight to your inbox!

Let’s Create Your Own Success Story

Let’s discuss how we can deliver measurable impact for your business.
Book a call
© 2025 Celerik. All right reserved.
Privacy Policy