AURA-3D

What the company appears to be: AURA-3D is a self-reported educational technology project that aims to synchronize 3D visualizations with a teacher's spoken instruction in real time, using AI and voice recognition. It is described as a multimodal copilot for classroom presentations, designed to reduce interruptions during lectures by automatically displaying relevant 3D content when triggered by the teacher’s speech.

What changed: The project was submitted to the OpenAI 2026 hackathon, indicating it is in an early development or prototype stage. It is not evidenced to have launched a product or reached customers.

Single most important open question: Is there any evidence of real-world testing or adoption by educators? The description states no revenue, customers, or traction data are available beyond the author’s own account.

The description states that AURA-3D is a multimodal copilot for classroom presentations. It works in two phases:

1. Pre-course preparation: A studio converts learning objectives and topics into structured multimedia cues using an OpenAI API (gpt-5.6-sol) with strict schema outputs.
2. During the course: Real-time voice recognition transcribes speech, a local 26M-parameter planifier decides whether to trigger visual changes, and these are executed via Three.js.

The system is described as local-first, using edge computing and ONNX models for execution in real time without cloud dependency.

Inference: The product is not a finished SaaS offering but a prototype built for a hackathon. It includes no evidence of commercial deployment or customer usage.

The author states that AURA-3D aims to modernize teaching by synchronizing visual content with spoken instruction, freeing teachers from manual switching between slides and models.

Key claims:

• The system follows the teacher instead of the other way around.
• It does not replace pedagogy but liberates it.
• It reduces cognitive load on students by avoiding interruptions.
• It uses structured outputs and local execution to ensure safety and control.

Inference: The positioning is centered on pedagogical efficiency, with a focus on teacher empowerment and reduced cognitive friction. No evidence of market positioning beyond the author’s own description.

The description states that AURA-3D targets teachers in technical education, particularly those teaching subjects like automation, infographics, and industrial electronics.

It is described as useful for:

• Teachers who want to reduce interruptions during lessons.
• Educators who need to show 3D models or visualizations while explaining concepts.

Inference: The ICP appears to be technical educators in secondary or higher education, especially in STEM fields. No evidence of segmentation, customer personas, or market size.

The description does not state any business model or pricing information.

Not evidenced: There is no mention of monetization, licensing, or revenue streams.

The system uses:

• OpenAI API (gpt-5.6-sol) for pre-course cue generation.
• ONNX runtime with a 26M parameter model for real-time decision-making.
• Browser-based speech recognition (French/English).
• Three.js for rendering 3D visuals.
• Structured outputs, schema validation, and deterministic action registry.

Key technical features:

• Local execution to avoid latency or dependency on cloud.
• Attention-weighted lexicon filtering to prevent false triggers.
• Strictly limited actions (13) and parameters.
• Manual override capability.

Inference: The system is designed for low-latency, safe, local execution, with a strong emphasis on control and predictability over raw AI power.

The description states that AURA-3D was submitted to the OpenAI 2026 hackathon. It includes:

• A functional prototype (bilingual voice/text to 3D).
• A reproducible benchmark with 100% accuracy in decision, target, and action lists.
• A local learning mode that adapts to teacher preferences.

However, there is no evidence of real-world adoption, revenue, or customer feedback beyond the author’s own account.

Not evidenced: No data on usage, retention, or impact.

The description does not mention any competitors. It is unclear whether similar tools exist in the edtech space for synchronized visual instruction.

Not evidenced: No competitive analysis or market positioning relative to existing solutions.

• No traction or customer data: The project is described as a hackathon submission with no evidence of real-world use.
• Unproven pedagogical impact: While the author claims benefits, there is no data on learning outcomes or student attention.
• Limited scope: The system is focused only on 3D visuals and lacks integration with other media types (e.g., graphs, diagrams).
• Single-person team: A team of one may limit development speed or scalability.

Inference: The project is in a very early stage. It has not demonstrated commercial viability or real-world effectiveness.

1. What specific feedback have you received from educators who tested the prototype?
2. How do you plan to scale beyond a single classroom or instructor?
3. Have you validated the pedagogical impact of AURA-3D with actual students or teachers?
4. What are your plans for monetization, if any?
5. Are there any technical limitations in scaling the local execution model to multiple classrooms or devices?