OpenAI 2026 hackathon

ShotSense

Creative direction that survives production.

Solo project by Stephen Cloete · 1 likes · 0 comments

Archive position — measured, not model output

1 like on Devpost

506 of the 7,856 archived projects have more likes, and 1,758 share exactly 1 — so this project's #1,916 place in the like-ranked listing is a tie-break inside that group, not a ranking.

Projects (log scale)

1
10
100
1k
10k
05,592
11,758
2285
3–4132
5–975
10+14

Likes on Devpost. ▲ marks this project's group.

Show the figures
LikesProjectsShare of archive
05,59271.2%
11,75822.4%
22853.6%
3–41321.7%
5–9751.0%
10+140.2%
Devpost like counts for all 7,856 archived projects, captured when this archive was built.

Executive Summary

Company: ShotSense

Self-reported basis: The description is entirely self-reported and unverified, based on a Devpost submission for the OpenAI 2026 hackathon. No independent verification or historical evidence is available.

What it appears to be: A tool that uses AI (specifically GPT-5.6) to interpret natural-language creative direction from animation directors and convert it into structured, actionable retake instructions for animators. It is described as a workflow tool for preserving director intent during production, built during OpenAI Build Week.

What changed: The project was initiated as an internal prototype (MEC Command), and now is being restructured into a focused product workflow using Codex and GPT-5.6 during the hackathon.

Single most important open question: Is there evidence of any real-world testing or adoption in animation production, or has the tool only been conceptualized and prototyped?

Back to contents

What The Product Actually Is

The description states that ShotSense is a system that transforms natural-language creative direction from an animation director into structured retake instructions for animators. It uses GPT-5.6 as its reasoning engine and Codex as a development partner.

It is described as being built during OpenAI Build Week, with the goal of turning a production problem (loss of creative intent) into a testable workflow.

Evidence:

  • ShotSense "transforms a shot reference, production context and a director's natural-language note into a clear, structured animation retake."
  • It uses GPT-5.6 as its reasoning engine.
  • It is built using Codex and GPT-5.6 during OpenAI Build Week.

Inference:

  • The tool appears to be in early prototype or hackathon stage, not yet deployed in production.

Back to contents

Positioning & Claim Evolution

The description states that ShotSense was created to preserve the director's creative intention as feedback moves through production. It is positioned as a tool that protects and communicates director intent, rather than replacing it.

Evidence:

  • "ShotSense was created to preserve the director's creative intention as feedback moves through production."
  • "The director remains the creative authority. Every AI-generated interpretation can be reviewed, edited and approved before it becomes a production task."
  • "Instead of attempting to replace the animation director, ShotSense is designed to protect and communicate the director's intent."

Inference:

  • The positioning has evolved from an internal prototype (MEC Command) into a more structured product workflow.

Back to contents

Target Customer & ICP

The description states that ShotSense is intended for animation directors working in production environments where creative direction is lost or fragmented during review and retake processes.

Evidence:

  • "At Minds Eye Creative, animation direction often begins as nuanced, conversational feedback."
  • "An animator may receive the requested change without fully understanding the reason behind it."

Inference:

  • The primary user is an animation director.
  • The target environment is animation production pipelines with review and retake workflows.

Back to contents

Business Model & Pricing Evidence

Not evidenced.

The description does not contain any information about pricing, monetization, or business model.

Back to contents

Technical & Delivery Signals

The project was built during OpenAI Build Week using Codex and GPT-5.6. It is described as being developed in a structured way, with documentation through Codex session history, Git commits, and build logs.

Evidence:

  • "ShotSense is being developed during OpenAI Build Week using Codex as our primary development partner and GPT-5.6 as the reasoning engine inside the product."
  • "We are documenting the new work through Codex session history, timestamped Git commits and a dedicated build log."

Inference:

  • The tool is in an early-stage prototype or hackathon project.
  • It uses AI tools for development and reasoning.

Back to contents

Traction & Maturity Signals

Not evidenced.

There is no evidence of revenue, customers, adoption, or usage beyond the internal prototype (MEC Command) and a hackathon prototype.

Back to contents

Competitive Context

Not evidenced.

The description does not mention competitors or similar products in the market.

Back to contents

Key Risks & Red Flags

  • The tool is described as being in an early prototype stage, with no evidence of real-world testing or adoption.
  • It is built during a hackathon and not yet part of any production pipeline.
  • No information on how it integrates into existing workflows or whether it has been tested with actual directors or animators.
  • The reliance on GPT-5.6 and Codex suggests a high degree of dependency on external AI tools, which may not be scalable or stable.

Back to contents

Diligence Questions To Ask The Founders

  1. What is the current stage of development beyond the hackathon prototype?
  2. Has ShotSense been tested with actual directors and animators in a production environment?
  3. How does it integrate into existing animation production tools or workflows?
  4. What are the limitations of GPT-5.6 in interpreting nuanced creative direction?
  5. Are there any plans to monetize or scale this tool beyond the hackathon?

Back to contents

Investment/Partnership Verdict

Not evidenced.

There is no evidence of traction, revenue, customers, or product-market fit. The project is described as a prototype built during a hackathon and not yet tested in production. It is unclear whether it has any commercial viability or strategic value at this stage.

Back to contents

Source

Submitted to the OpenAI 2026 hackathon on Devpost. Project home on DevPost.

The analysis above was generated by a language model from the project's own one-line description. It is not independent research and contains no verified traction, revenue or customer data.