Final results
Two tracks, judged and ranked separately. Each project carries the judges' marks out of 80, plus up to 10 for Facebook reactions and 10 for GitHub stars, for a total out of 100.
Crisis Tech
Marked independently by 2 judges, and averaged. Engagement scaled against the best in this track: 221 reactions and 188 stars both score 10.
| # | Project | Judge 1 /80 | Judge 2 /80 | Average /80 | Facebook /10 | GitHub /10 | Total /100 |
|---|---|---|---|---|---|---|---|
| 1st | NongorLogarithm · Khulna | 73.5 | 38.5 | 56 | 10221 reactions | 10188 stars | 76 |
| 2nd | Jagoo Baheeপ্রতিধ্বনি · Khulna | 62.0 | 34.5 | 48.25 | 8.96198 reactions | 8.62162 stars | 65.83 |
| 3rd | Acoustic Voice-Call Data RelayLone Warriors · Dhaka | 59.5 | 52.5 | 56 | 3.7182 reactions | 0.5310 stars | 60.24 |
| 4 | SongketBinary Bandits · Pabna | 73.5 | 41.0 | 57.25 | 2.4955 reactions | 0.377 stars | 60.11 |
| 5 | PigeonMesh: Flying Messages Beyond BlackoutsCapture_The_Autocrats · Dhaka | 69.5 | 41.5 | 55.50 | 1.4532 reactions | 0.6412 stars | 57.59 |
| 6 | BornomalaDU_RJOY · Dhaka | 62.5 | 39.5 | 51 | 4.2193 reactions | 1.6531 stars | 56.86 |
| 7 | Setu — offline-first community lifelineOnepath · Rajshahi | 61.5 | 36.5 | 49 | 4.93109 reactions | 2.2943 stars | 56.22 |
| 8 | CloudAlert BridgePandas · Dhaka | 56.5 | 34.5 | 45.50 | 3.9487 reactions | 1.7633 stars | 51.19 |
| 9 | TruthRelayTernaryOps · Dhaka | 52.5 | 30.0 | 41.25 | —uncounted | 00 stars | 41.25 |
Judges' comments
Nongor
Judge 2: Suffers from classic crisis tech problems, ensuring distribution of the app. If there are not enough devices with the app installed, the whole premise of utility falls through.
Jagoo Bahee
Judge 2: Inaudible presentation, hard to understand what the speaker is saying. Similar ideas to the other projects.
Acoustic Voice-Call Data Relay
Judge 2: Interesting idea although the concept is incomplete. The demo is a web interface for converting text to audio and back. The challenge would be to incorporate the whole workflow within a caller app.
Songket
Judge 2: I really like the app's simplicity. However, it would be a no-brainer to add a few more useful features specifically designed for crisis situations.
PigeonMesh: Flying Messages Beyond Blackouts
Judge 1: Too technical for laypeople. Not all routers support OpenWrt, and most household routers do not meet the requirements for its installation. However, the project is impressive. If enough routers are interconnected, this could provide a solution during a crisis.
Judge 2: Key questions like minimum distance between routers, what would happen to the network without electricity, etc are unanswered which makes it less feasible.
Bornomala
Judge 2: They understood the issue with crisis tech but did not pursue that with the solution. Using SMS as the communication layer is a clever idea. Encrypting the text is also useful for avoiding surveillance. But compressing Bangla text using an AI model is an attempt in a misleading direction.
Setu — offline-first community lifeline
Judge 2: Distribution and critical mass of devices in the network remain the central challenge. Presentation could have been better.
CloudAlert Bridge
Judge 1: The app isn't compiled. Who's gonna use that?
Judge 2: Useful idea but we lack the critical layer beneath to be able to send real time updates. The manual input option requires 2 admin approvals which cannot send out realtime updates.
TruthRelay
Judge 2: Presentation was very messy, very hard to follow through.
How this was marked
Each judge scored every finalist out of 80 across the five criteria in Section 9 of the guideline: impact and relevance to track (25), technical execution (20), innovation and originality (15), feasibility and resilience (10), and presentation and usability (10). The judges' column is the mean of their marks, not a sum.
The remaining 20 points are public engagement, scored exactly as Section 8 described before the sprint began: proportional to the best in the track. The highest Facebook reaction count in a track scores the full 10, and every other project scores its count ÷ the highest count × 10. GitHub stars are scaled the same way against the highest star count in that track. Counts were frozen on 1 August at 23:59.
Rank-based and logarithmic scaling would both narrow the distance between a widely shared post and a quiet one, and there is a fair argument that either measures engagement better than raw proportion does. Neither is used here, because the proportional rule is the one teams could read before they built anything. Changing the formula after the counts were frozen would move points on a rule nobody had seen.
A component that was never counted is shown as uncounted and scores nothing, rather than being averaged away as if it were a zero somebody measured.