ScheduleProof

Note

This analysis is based solely on the self-reported project description provided by the author. No external verification, revenue data, customer feedback, or performance metrics are available.

• The description states that ScheduleProof accepts structured institutional data such as exams, rooms, capacities, time periods, instructor availability, and conflict information.
• Users can also enter additional requirements in ordinary language (e.g., “Professor Ibrahim can only supervise on Friday”).
• A language model translates these sentences into formal rule types; users review interpretations before activating them.
• Confirmed rules are converted into logical formulas and passed to Z3 (an automated theorem prover), which returns a timetable if constraints are satisfiable.
• An independent Python validator checks the final schedule without relying on Z3’s internal model.
• If no valid solution exists, ScheduleProof identifies conflicting sets and suggests low-cost repairs.
• The system aims to preserve existing timetables during repair processes.

Inference The product is described as a hybrid system combining NLP, formal logic, and constraint solving. It is not merely an optimization engine but one that emphasizes explainability and trustworthiness.

• The author positions ScheduleProof as a solution to the “everyday pain” of academic scheduling — particularly in higher education.
• Key claims include:
  • Fast timetable generation (seconds).
  • Conflict explanation and repair suggestions.
  • Independent validation of results.
  • Support for natural-language input.
• The project evolved from a hackathon submission into a more complete workflow, emphasizing usability and correctness over visual appeal.
• The author notes that the system is not just about solving constraints but presenting solutions in a way that users understand.

Claim vs Fact

These are self-reported claims. There is no evidence of actual deployment, user testing, or performance benchmarks beyond the author’s own account.

• The primary target audience appears to be academic institutions (e.g., universities) facing scheduling challenges.
• Specific use cases mentioned include:
  • Exam scheduling.
  • Room allocation.
  • Instructor availability management.
• The system is tailored for institutional needs, including privacy controls and tenant-scoped access.

Not evidenced No explicit customer list, size of target market, or segmentation data. The ICP is inferred from the stated use case and domain-specific features.

• Not evidenced.

Absence of evidence

There is no mention of pricing models, monetization strategies, or business model assumptions in the description.

• Built with:
  • Backend: Python, FastAPI.
  • Frontend: React, TypeScript.
  • Solver: Z3 (SMT solver).
  • Language processing: GPT-5.6.
  • Testing tools: pytest, Selenium.
  • Deployment: Docker.
• Architecture separates responsibilities:
  • NLP layer translates requirements.
  • Z3 handles scheduling logic.
  • Python validator ensures correctness.
• Includes automated tests, benchmarks, import fixtures, privacy controls, and release-validation scripts.
• The author emphasizes adversarial review and documentation of rule translations using LaTeX.

Inference The architecture suggests a modular approach to handling complexity, though it lacks evidence of production readiness or scalability beyond prototype-level use.

• Not evidenced.

Absence of evidence

No data on users, adoption rates, revenue, or product maturity is provided. The project is described as a hackathon submission and prototype.

• Not evidenced.

Absence of evidence

No mention of competitors, market positioning, or competitive landscape. The description does not reference existing scheduling tools or platforms.

• Scalability concerns: SMT solving is computationally difficult; large or dense constraint sets may require decomposition techniques.
• Dependency on NLP accuracy: Natural-language input must map to supported formal rules — unsupported or ambiguous inputs are rejected, but this could limit usability.
• Limited scope: The system assumes single-room exams and does not support split rooms, student-specific accommodations, or cross-campus scheduling.
• Prototype nature: Described as a hackathon project with no commercial traction or deployment history.
• Privacy assumptions: While privacy controls are included, their effectiveness in real-world environments is unproven.

Inference These risks stem from the described limitations and lack of validation in production settings.

1. What specific types of constraints have been tested successfully in practice?
2. How does the system handle edge cases like overlapping exams with no valid solution?
3. Has the NLP layer been validated against real-world inputs from actual users?
4. Are there any known performance bottlenecks when scaling to larger datasets?
5. What is the current status of the validation process — how often does it detect errors in Z3 outputs?
6. Have you considered integrating with existing institutional systems (e.g., LMS, HR databases)?
7. How do you plan to address the computational complexity of large-scale scheduling problems?