AI Enterprise SolutionsGPT & Claude
AziiForza
All kind of Restaurants can apply our ecosystem and users can reserve their places. Some restaurants have call number for reservation. It can be busy and unavailable. Our project solve this problem in the best way.
Preliminary score
26.0/ 100Earlyaverage of 2 judges
- Value for the user12.0 / 25
A specific problem and a clear outcome from solving it.
- Prototype and use of AI7.0 / 30
A working core scenario, and what AI actually contributes to the result.
- Quality testing1.5 / 20
Tests, examples of failures, and comparison with the current approach.
- Feasibility2.5 / 15
Data requirements, running costs and a clear next step.
- Originality3.0 / 10
A meaningful difference from common solutions.
What the judges wrote
- GPT-6 AstraPreliminary27/100
- Strengths
- Your project addresses a concrete restaurant problem: guests cannot reliably reserve when phone lines are busy. Your proposed flow connects table selection and confirmation codes with QR ordering and kitchen status, clearly describing the guest-to-staff handoff. Support for Azerbaijani, English, and Russian fits the local setting.
- To improve
- Your materials list models but do not explain their contribution; show what AI receives, produces, and improves over ordinary reservation software. Demonstrate a saved reservation reaching the host and an order reaching the kitchen, including protection against simultaneous bookings. Replace the generic testing claim with documented cases, failures, and booking-time or missed-reservation comparisons against phone booking. Explain what the private data contains, your permission to use it, expected running costs, and a concrete restaurant pilot.
- Claude Opus 5.5Preliminary25/100
- Strengths
- Your deck presents a clear, coherent guest journey: pick a table on a multi-floor live map, reserve in three taps with an occasion tag, get a TBZ-XXXX confirmation code, then order from a QR menu and follow a kitchen tracker. Supporting English, Azerbaijani and Russian is a thoughtful choice for the Baku market. Building a concrete fictional venue (26 tables, 3 floors, real Azerbaijani dishes) makes the demo easy to follow.
- To improve
- The materials do not show AI anywhere in the product itself; the listed models look like coding assistants rather than part of the user scenario. Add something AI genuinely does for the restaurant, such as forecasting no-shows, optimising table allocation, or a voice/chat agent that takes the phone reservations you say go unanswered. Replace 'everything is working' with real test cases: double-booking attempts, simultaneous reservations, wrong-language input, and timing compared with a phone booking. The track asks for an adoption metric, so name one (for example, missed calls recovered or table turnover) and outline hosting cost, the data a restaurant must provide, and a pilot plan.
The team
Afsun Quliyeva.
developer
Ardam HuseynovLead
designer
Huseyn Huseynov
developer