Afqilla Putri@bloommm

Tirexx entered the tablekeeper track of Dark Factory with a small factory of three coding-agent seats in BAND Desktop: a Lead that coordinates, a Builder that writes the code, and a separate Reviewer that verifies it. One human message, the dispatch, started the run, and nothing was sent after it. In 73 minutes the band built a restaurant reservation service for stage 1, with a Dockerfile, run instructions and its own tests. The Reviewer rebuilt the Docker image and rejected the first revision after reproducing a real failure: importing an incomplete restaurant returned success and then broke a later request. The Builder fixed it with a regression test, and the Reviewer accepted the second revision after reproducing the fix against the built image. The shipped checks report stage 1 pass and claimed stage 1. We also document what failed and cost time: a handoff the Builder could not read, and a server with too few CPUs for the harness. This room used Codex seats, and FACTORY.md records the limits and unproven parts openly.

Weather forecasts describe conditions, but they rarely tell field teams how to adjust their work safely. WeatherTact bridges this gap by turning location-based forecasts into structured and actionable field-operation plans. An Admin selects a work location from the map, chooses the type of work, assigns workers, and defines the schedule. WeatherTact retrieves hourly Open-Meteo data and sends the work context to Featherless AI. The AI produces a structured plan containing the recommended work sequence, timing, recovery periods, weather-related controls, required equipment, risk explanations, and stop-work conditions. Before being saved or distributed, every AI response is validated by the system and reviewed by an Admin. Approved plans are then shared with assigned workers through a simplified briefing interface. Workers can acknowledge their assignments and report changing field conditions. When conditions change, WeatherTact can generate an updated plan using the latest forecast and worker reports. The application uses Supabase for authentication, organization-isolated data, role-based access, and server-side AI orchestration. It was built with Native Builder and designed as decision support not as an automatic work permit so final operational authority always remains with the responsible human supervisor

🌎 Online Hackathon | 💻 Online Build: Sept 26 - Oct 5, 2026 A virtual, global hackathon. Build from anywhere in the world. Dark Factory is the official hackathon of WeAreDevelopers World Congress North America, presented by BAND, but you don't need to be in San Jose to take part. For one week, you build a software factory in BAND Desktop: a band of coding agents that plans work, implements it and checks its own results. 🎟️ Bonus for sign-ups: you are eligible for a free ticket to WeAreDevelopers World Congress North America in San Jose (Sep 23–25). If you do go, stop by the BAND booth: a surprise is waiting for you.

🌎 Online Hackathon | 📅 August 3–10, 2026| 💻 Powered by native.builder The official native.builder hackathon, hosted by NativelyAI and lablab.ai. Join founders, developers, designers, and builders to create real AI-native applications powered by native.builder: from idea to deployed product, fully in the cloud. 💻 This hackathon is fully online. No travel required.