Ai Presenter

The company appears to be a solo project named "Ai Presenter", self-described as a platform that turns business knowledge into an AI representative capable of presenting, answering questions, navigating content, and remembering interactions. The author states this was built by one person (Chirag Rakeshka) with the help of Codex, using technologies like GPT-5.6 Terra, Next.js, Supabase, and Vercel.

The project is presented as a hackathon submission to the OpenAI 2026 hackathon, and no evidence of revenue, customers or traction is provided beyond self-reported claims.

The single most important open question is: What is the actual commercial viability of this concept, and how does it differ from existing tools in the AI presentation or conversational AI space?

The description states that AI Presenter transforms a company’s approved knowledge into Maya, a live voice-and-text representative. It allows visitors to:

• Ask questions by voice or text
• Explore branded topics
• View project information, floor plans and visual navigation
• Receive concise, knowledge-grounded answers
• Continue through voice mode if the live avatar session ends
• Switch between configurable presenter experiences

The platform records session transcripts and interaction signals so owners can understand the questions, interests and objections raised by visitors.

Inferred: The product is a conversational AI interface that integrates with business knowledge bases to provide dynamic, branded responses in real-time. It supports voice, text, and visual avatar modes.

The author states:

• “I am not a professional developer” — positioning the project as a non-developer-led innovation.
• “Ordinary presentations cannot answer questions, respond to objections, adapt to each visitor or remember what happened after a meeting.” — this is the core problem being solved.
• “AI Presenter transforms a company’s approved knowledge into Maya, a live voice-and-text representative.” — this is the solution.
• “Codex became my engineering partner and helped turn that idea into a working product.” — implies a tool-assisted development approach.

Inferred: The positioning evolved from a personal problem (poor presentation interactivity) to a scalable solution (AI-driven, branded, knowledge-grounded representative). The claim is that this is a new way to deliver business knowledge in an interactive format.

The description states:

• “AI Presenter transforms a company’s approved knowledge into Maya, a live voice-and-text representative.”
• “Visitors can ask questions by voice or text” — implies the target audience includes external users (e.g., clients, prospects).
• “The platform records session transcripts and interaction signals so owners can understand the questions, interests and objections raised by visitors.” — suggests internal business use for lead generation or analytics.

Inferred: The primary customer is a business that wants to present its knowledge in an interactive way. The ICP likely includes companies with branded content (e.g., real estate, education, corporate training) that want to offer live, AI-driven Q&A experiences to external audiences.

Not evidenced. The description does not mention any pricing model, monetization strategy, or business model. It only describes the product and its features.

The author states:

• Built with: Next.js 14, TypeScript, GPT-5.6 Terra, OpenAI Responses API, Supabase, Vercel, HeyGen, LiveAvatar, Playwright, React
• Uses deterministic controls to protect restricted information and sensitive actions before requests reach the model
• Session telemetry and transcripts stored in Supabase
• Vercel hosts the application
• Avatar only loads after visitor chooses to start it

Inferred: The product is built on a modern web stack with AI integration, and includes some level of data handling and access control. It supports voice/text/visual modes and has session recording capabilities.

The description states:

• Live HSA, Skyhawks, Sunwa.AI and CS Media demonstrations
• A working product built by a non-developer with Codex
• Multiple presenter configurations from one platform
• Voice, text and visual navigation in one experience
• Responsive desktop and mobile interfaces

Inferred: The project has demonstrated functionality through live demos and has some level of maturity. However, no evidence of revenue, customers, or adoption is provided.

Not evidenced. No mention of competitors or market context is provided in the description.

• Solo founder: The project is built by a single person (Chirag Rakeshka), which raises questions about scalability and long-term maintenance.
• Unverified claims: All features, functionality, and outcomes are self-reported without external validation.
• No revenue or customer data: No evidence of monetization, traction, or adoption.
• Hackathon project: The product is a hackathon submission, which often lacks commercial viability or long-term planning.
• AI dependency: Heavy reliance on GPT-5.6 Terra and OpenAI APIs introduces risk from API availability, cost, and model changes.

1. What specific business use cases are you targeting, and how do they differ from existing tools?
2. How is the knowledge base managed and updated? Is there a process for ensuring accuracy?
3. What is your plan to scale beyond the current demo environment?
4. Are there any legal or compliance considerations around session recording or data handling?
5. How do you intend to monetize this product, and what is your go-to-market strategy?
6. What are the technical limitations of the current implementation that would prevent a production rollout?