Koroglu
1. A 15–18-year-old in an Azerbaijani, Turkish, or Turkmen class (or diaspora Saturday school). They know “Koroglu” from a statue, a test, or a grandparent’s radio. Today they get recitation or Wikipedia. They never ride, never choose justice over revenge, never shout a verse. They close the tab. 2. A heritage teacher with one short period. They cannot assign a 400-page dastan. Today they show a slide titled “Epic of Koroglu” and hope a summary sticks. They have no two-minute thing a student can play. 3. A young player who already games on horse-and-sword loops. That hour goes to a made-up kingdom. Their own oral epic sits unused next to the habit that could carry it. What is actually broken: the encyclopedia already exists. What is missing is practice — mounted choice, poetry as courage, a moral fork they can get wrong.
Preliminary score
- Value for the user17.0 / 25
A specific problem and a clear outcome from solving it.
- Prototype and use of AI15.0 / 30
A working core scenario, and what AI actually contributes to the result.
- Quality testing11.0 / 20
Tests, examples of failures, and comparison with the current approach.
- Feasibility5.0 / 15
Data requirements, running costs and a clear next step.
- Originality7.0 / 10
A meaningful difference from common solutions.
What the judges wrote
- Claude Opus 5.5Preliminary49/100
- Strengths
- You name three specific users: the 15–18-year-old heritage student, the teacher with one short period, and the young horse-and-sword gamer. Your problem framing, 'the encyclopedia exists, practice is missing', is sharp. Your core loop follows the dastan faithfully, from Ali Kishi's blinding through the allies and the captain to Nigar and Çamlıbel, and adds distinctive mechanics such as verse that slows enemies and the ashik's saz that heals. Your testing slide is refreshingly honest: it lists real breakages (WebGL white-screen with a 2D fallback, the hug-only ending, box horses, allies bunching without a navmesh) and fairly compares the game with a lecture rather than a AAA title.
- To improve
- The 'AI' in this build is scripted ally and enemy behaviour (greedy moveToward) plus fixed dialogue trees. AI does not yet change the result, so an LLM-driven ashik, a verse generator in Azerbaijani, Turkish or Turkmen, or adaptive Nigar counsel would make it essential. Your 'higher heritage retention' outcome is only proposed, so run even a small test: five to ten students playing versus reading the Wikipedia page, with a short quiz afterwards. Your README is a single title line, and you give no data needs, running or hosting costs, or concrete next step such as a school pilot or a curriculum partner. Adding these would strengthen feasibility considerably.
- GPT-6 AstraPreliminary61/100
- Strengths
- Your project identifies specific learners and teachers who could benefit from a short, playable introduction to Koroğlu. Your poetry combat and ashik healing connect cultural material to gameplay rather than simply putting heritage text around generic combat. Your testing notes identify concrete failures and fixes, especially the WebGL fallback, silent ending, and remaining ally-navigation problems.
- To improve
- Your submission would be stronger with implementation evidence showing reactive agents and quest transitions; the supplied README contains only a title, so the documented playthrough remains difficult to verify independently. Your retention claim needs a small comparison against a text-only lesson, alongside repeatable gameplay tests with recorded results. Your feasibility plan should explain regional-lore validation, hosting and model costs, and a scoped next milestone such as fixing ally navigation.
The team
Gunash FarzaliyevLead
developer