Hackathon Portal
AI Tinkerers - New York City
Sign in

AI Tinkerers - New York City Hackathon

Sign in
Founding Applied AI Lead - Paxos Health
Build healthcare AI agents in NYC. Apply now.
DevRel Lead - Restate
Restate is building durable infrastructure for AI agents and backends. We're looking to hire our first DevRel Lead to spread the word and bring Restate to developers.
All Jobs
Final round winners have been announced. View Results
Team

sowcantcode

Project Concept

Adaptive Pitch Arena
What we’re building

Adaptive Pitch Arena is a coaching product for practicing short professional opening statements (starting with a 45-second interview intro).
Instead of giving generic feedback in a chat window, the product changes the interface itself after each attempt based on the user’s weakest dimension.

Most AI coaching tools only change the advice.
Our project changes the workspace.

Entry

Status: Submitted

Last saved: February 21 at 6:13 PM EST

View Entry

Team Roster

You must be registered for the event to view the team message board.

Soulemane Sow Team Lead RSVP Approved

Student at Student
I built the entire project solo. - Anthropic: I integrated Anthropic’s Messages API (POST /v1/messages) as the second-pass coaching intelligence layer. My backend sends transcript + deterministic metrics + prior attempts + rubric context, and uses structured output (output_format: json_schema) so Claude returns machine-usable coaching fields (diagnosis summary, bottlenecks, drill assets, mode recommendation, UI hints, and why-changed reasons). I also added server-side validation and logging around response handling for reliability. - Redis: I integrated Redis for fast session persistence and retrieval of attempt history. Each analyzed attempt is stored by session ID, with metadata and TTL controls, and exposed through session history endpoints so the adaptive interface can recover state and show progression across retries without relying on mock data.
I am a passionate and motivated student developer based in New York City with a strong interest in AI, full-stack development, and open-source tools. I have built and contributed to award-winning applications across hackathons, internships, and personal projects. With experience in React, Python, Tailwind, and Next.js, I thrive in teams where creativity meets code. I aim to use technology to solve real-world problems while continuing to learn, mentor, and grow in the tech community.
I am interested in AI for accessibility, computer vision, ethical machine learning, developer tooling, and collaborative product design. I’m eager to connect with people building solutions in healthcare, sustainability, and education. I also want to explore advanced web frameworks and learn more about scalable AI infrastructure and deployment.
I am exploring ideas for a first-person EVtol (electric vertical takeoff and landing) simulation game. He plans to design the game with immersive flight mechanics and realistic controls, integrating 3D environments and physics. While not actively building at the moment, he's researching game engines and development tools to bring this concept to life.