OpenAI 2026 hackathon

SPEKICAD

From site photos to verified engineering specifications. Reworking a construction project again? SpekiCAD - now even your dog can handle it. (Created by an engineer tired of drafting)

Solo project by Boris TERENTENKO · 8 likes · 0 comments

Archive position — measured, not model output

8 likes on Devpost

19 of the 7,856 archived projects have more likes, and 7 share exactly 8 — so this project's #25 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

What the company appears to be

SPEKICAD is a self-reported tool that claims to convert site photos into verified engineering specifications using AI and 3D modeling technologies. It is presented as a solution for construction professionals, with a focus on simplifying rework processes.

What changed

The project was submitted to the OpenAI 2026 hackathon by one individual (Boris TERENTENKO), indicating an early-stage development effort. No evidence of prior traction or commercial activity exists in the description.

Single most important open question

Is there any evidence that SPEKICAD has moved beyond a proof-of-concept prototype, and if so, how does it function technically and what is its current stage of development?

Note: This analysis is based solely on the self-reported project description provided by the caller. All claims are unverified and should be treated as such.

Back to contents

What The Product Actually Is

The description states that SPEKICAD converts "site photos to verified engineering specifications" using AI and 3D modeling tools like three.js, gpt-5.6, openai-codex, and others. It also mentions integration with pdf.js and QR code generation, suggesting document handling capabilities.

However, the description does not clarify:

  • Whether SPEKICAD is a web-based tool or desktop application.
  • The exact workflow from photo input to specification output.
  • How "verified" engineering specifications are generated or validated.

Inference: Based on the technology stack and tagline, it seems likely that SPEKICAD uses AI for image interpretation and possibly 3D rendering to produce architectural or engineering data. But this is speculative without further detail.

Claim: The author states that SPEKICAD allows users to generate engineering specifications from site photos.

Evidence: Yes — in tagline and technology stack.

Inference: It likely uses AI for photo interpretation and 3D modeling.

Confidence: Low.

Back to contents

Positioning & Claim Evolution

The tagline reads: “From site photos to verified engineering specifications. Reworking a construction project again? SpekiCAD - now even your dog can handle it.”

This suggests:

  • A focus on simplifying complex construction tasks.
  • A humorous tone implying ease-of-use.
  • A potential niche in rework scenarios within the construction industry.

There is no indication of prior positioning or evolution beyond this single self-reported statement.

Claim: The author positions SPEKICAD as a tool for converting site photos into engineering specs, especially useful for reworking projects.

Evidence: Yes — tagline and context (hackathon submission).

Inference: Humor implies simplicity; no evidence of prior branding or messaging evolution.

Confidence: Low.

Back to contents

Target Customer & ICP

The description implies a target audience in the construction industry, particularly those involved in reworking projects. The phrase “reworking a construction project again?” suggests this is aimed at professionals who deal with modifications or corrections to existing structures.

No explicit customer segments or personas are described.

Claim: The author states that SPEKICAD targets construction professionals working on rework projects.

Evidence: Yes — tagline and implied use case.

Inference: Likely includes engineers, architects, contractors.

Confidence: Low.

Back to contents

Business Model & Pricing Evidence

There is no mention of pricing, monetization strategy, or business model in the description. The project appears to be a hackathon submission with no indication of commercial intent or revenue streams.

Claim: No evidence provided regarding business model or pricing.

Evidence: Not evidenced.

Confidence: Very low.

Back to contents

Technical & Delivery Signals

The author declares that SPEKICAD was built using:

  • cloudflare-pages
  • gpt-5.6
  • javascript
  • openai-codex
  • pdf.js
  • qrcode
  • three.js
  • vite

These technologies suggest a modern web-based tool leveraging AI and 3D visualization capabilities.

However, there is no evidence of:

  • A live demo or working prototype.
  • Technical architecture diagrams or deployment details.
  • Any form of user interface or interaction design.

Claim: The author states that SPEKICAD was built with specific technologies including GPT-based AI and 3D rendering.

Evidence: Yes — technology stack listed.

Inference: Likely a web app using AI for image processing and 3D visualization.

Confidence: Low.

Back to contents

Traction & Maturity Signals

There is no evidence of:

  • Customers or users.
  • Revenue or funding.
  • Product adoption or usage metrics.
  • Any form of traction beyond the hackathon submission.

The project was submitted to a hackathon, suggesting it may be in an early prototype phase.

Claim: No evidence of traction or maturity beyond hackathon submission.

Evidence: Not evidenced.

Confidence: Very low.

Back to contents

Competitive Context

No competitive landscape is described. The author does not reference existing tools or platforms that perform similar functions, nor does the description indicate awareness of competitors in the construction tech space.

Claim: No evidence provided about competitive positioning or market context.

Evidence: Not evidenced.

Confidence: Very low.

Back to contents

Key Risks & Red Flags

Key risks and red flags include:

  • Lack of verified functionality or product demo.
  • Single-founder team with no external validation.
  • No mention of scalability, security, or compliance in construction environments.
  • Heavy reliance on AI tools (gpt-5.6, openai-codex) — raises questions about accuracy, reliability, and cost.
  • No evidence of market research or customer feedback.

Inference: The tool may be a conceptual prototype with limited real-world applicability.

Confidence: Medium to high based on lack of evidence.

Back to contents

Diligence Questions To Ask The Founders

  1. What is the current stage of development? Is there a working prototype?
  2. How does SPEKICAD validate or verify engineering specifications derived from site photos?
  3. Have you tested the tool with real construction professionals or in actual field conditions?
  4. What are your plans for monetization and go-to-market strategy?
  5. Are there any known limitations or edge cases where the AI fails to produce accurate outputs?
  6. How do you plan to scale beyond a single developer?

Back to contents

Investment/Partnership Verdict

At this stage, SPEKICAD appears to be an early-stage idea or prototype submitted for a hackathon. There is no evidence of traction, revenue, or even a fully functional product.

Verdict: Not ready for investment or partnership consideration.

Reasoning: No demonstrated product-market fit, no customers, no business model, and no evidence of technical maturity beyond basic tooling.

Confidence: Very low.

Back to contents

Customer Segments

inferred

The description states that SpekiCAD was created by "an engineer tired of drafting" and is intended to make construction project rework easier, suggesting it targets professionals in the construction industry who engage in engineering design or documentation.

Back to contents

Value Propositions

inferred

The tagline “From site photos to verified engineering specifications” implies that SpekiCAD transforms visual data (site photos) into structured engineering documents. The phrase “now even your dog can handle it” suggests ease of use, though this is not a formal value proposition but rather a marketing tone.

Back to contents

Channels

inferred

The project was submitted to the OpenAI 2026 hackathon on Devpost, indicating that its initial channel for reaching users or feedback is through hackathon platforms and developer communities. No other channels are mentioned.

Back to contents

Customer Relationships

inferred

Given that the project is a single-person effort (1 member team), customer relationships are likely minimal or non-existent at this stage. The description does not indicate any formal support, engagement, or community-building mechanisms.

Back to contents

Revenue Streams

not evidenced

There is no mention of pricing models, monetization strategies, or revenue generation plans in the provided description.

Back to contents

Key Resources

evidenced

The author declares that SpekiCAD was built with: cloudflare-pages, gpt-5.6, javascript, openai-codex, pdf.js, qrcode, three.js, vite. These tools and technologies form part of its technical infrastructure and development stack.

Back to contents

Key Activities

inferred

Based on the technology stack and the stated goal of converting site photos into engineering specifications, key activities likely include image processing, data extraction, AI-based drafting, and possibly 3D modeling or document generation.

Back to contents

Key Partnerships

not evidenced

No partnerships, collaborations, or integrations are mentioned in the description. The project appears to be independently developed by one individual.

Back to contents

Cost Structure

inferred

The use of cloudflare-pages and OpenAI APIs (gpt-5.6, openai-codex) implies that costs may include usage fees for these services. However, no explicit cost breakdown is provided in the description.

Back to contents

Evidence & Gaps

  1. Customer Segments: Marked as inferred. Would be evidenced by a clear statement of target user groups or industries.
  2. Value Propositions: Marked as inferred. Would be evidenced by a direct statement of what value the product delivers to users.
  3. Channels: Marked as inferred. Would be evidenced by explicit mention of how the product reaches its audience (e.g., marketing channels, distribution methods).
  4. Customer Relationships: Marked as inferred. Would be evidenced by information about support systems, user engagement, or feedback loops.
  5. Revenue Streams: Marked as not evidenced. Would be evidenced by a description of pricing, monetization, or business model.
  6. Key Resources: Marked as evidenced. The list of technologies used is directly stated in the description.
  7. Key Activities: Marked as inferred. Would be evidenced by explicit descriptions of core operations or processes involved in building or running the product.
  8. Key Partnerships: Marked as not evidenced. Would be evidenced by mentions of collaborators, vendors, or integrations.
  9. Cost Structure: Marked as inferred. Would be evidenced by a description of expenses or resource costs.

The entire analysis is based on self-reported and unverified information from the project description provided.

Back to contents

._business-model-canvas

Mac OS X  2q�ATTR�� � com.apple.provenance�� ��j>

._executive-summary

Mac OS X  2q�ATTR�� � com.apple.provenance�� ��j>

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.