Ludiqentra:Your Game Deserves More Than a Guess.
User: indie and small-studio game developers (and the publishers and investors who fund them) who have a game concept and must decide, before months of development, whether it is worth building and when to launch it on Steam. Problem today: the market is flooded. About 12,000 games launched in the first half of 2026. In the last week of August 2026 alone, 720 games launched on Steam (about 103 a day), and 530 of them ended with fewer than 10 reviews. To judge a concept, developers open dozens of tabs (SteamDB, Gamalytic, VG Insights, GameDiscoverCo, SteamPeek), search by tags that return hundreds of loosely similar games, and compare them by hand. These tools answer “how did last year’s games do?” None of them answers the question that decides a launch: “Who am I launching against in the coming months, and should I move?” Outcome: the developer describes the game in plain text. An LLM extracts genres, mechanics, modes, perspective and price, and asks follow-up questions when details are missing. Ludiqentra then finds comparable games through IGDB search, ranks them by how they actually play, and the developer approves the list. In about 45 seconds the developer gets a KEEP / MOVE / MITIGATE verdict with a revenue range, a market saturation score, predicted reception and a week-by-week release-risk calendar for the next 26–52 weeks. Every number is tagged as a fact (Steam), an estimate (Gamalytic) or a prediction (our deterministic scoring engine).
Preliminary score
- Value for the user20.5 / 25
A specific problem and a clear outcome from solving it.
- Prototype and use of AI21.5 / 30
A working core scenario, and what AI actually contributes to the result.
- Quality testing13.5 / 20
Tests, examples of failures, and comparison with the current approach.
- Feasibility10.0 / 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 5.5Preliminary72/100
- Strengths
- Your problem framing is sharp: a specific user (indie developers and their funders), a concrete pain backed by your own Steam numbers, and a decision-shaped output (KEEP / MOVE / MITIGATE plus a weekly release-risk calendar) rather than another dashboard. The architecture looks well engineered and is deployed. It has a clear concept → approve comparables → report flow, live IGDB/Steam/Gamalytic data, and Grok used for interpretation, follow-up questions and ranking. Your provenance tagging of facts, estimates and predictions, along with your refusal to fabricate missing revenue or semantic scores, shows unusual honesty about uncertainty. Your write-up of what broke, such as mislabelled similarity and $0 versus unavailable revenue, is specific and credible.
- To improve
- Your 253 unit tests show the software runs, but you have no evidence yet that the recommendations are right. Backtest on past Steam launches, for example by checking whether MOVE verdicts would have avoided crowded weeks or whether revenue ranges contained the actual Gamalytic figures, and report hit rates alongside the failures. Add a timed comparison against the manual multi-tab workflow on a few real concepts to support your claim that the tool saves effort. State your running costs per report, covering Grok calls and IGDB and Gamalytic limits, and how the free-tier data dependency scales. Name a concrete next step, such as pilot studios or a validation dataset.
- GPT-6 AstraPreliminary73/100
- Strengths
- Your workflow addresses a concrete decision for small studios: which games genuinely compete with their concept and when to launch. Combining AI-assisted interpretation with developer-approved comparables and clearly labeled facts, estimates, and predictions makes the recommendations reviewable. Your reported fixes for mislabeled similarity, missing revenue, and unsupported release-risk explanations show thoughtful attention to evidence integrity.
- To improve
- Your prototype evidence would be stronger with a reproducible concept-to-report example showing actual provider responses, final recommendations, and measured latency. Extend your software tests with historical backtests using only information available before each launch, plus a timed comparison against developers' current research workflow. Quantify per-report API and hosting costs, provider limits, and realistic upcoming-release coverage. Clarify what information enters temporary Redis previews so your server-side storage claims match the implementation.
The team
Aykhan Amirov
product
Shamil Aliyev
developer
Kamal MusayevLead
data