Kunal Pandey @Kp435573

Briefly turns conversations about a software project into clear, reviewable outputs. A user speaks with an AssemblyAI voice agent about a new idea, a bug, or a requested change. The agent asks follow-up questions and captures the answers in structured fields that the user can correct and edit. In Project Brief mode, Briefly creates an editable brief and five separate Markdown files: a PRD, app flow, tech stack, frontend guidelines, and backend structure. BugTalk gathers reproduction details and creates a structured bug ticket plus an investigation prompt. ScopeCheck compares a proposed change with the original brief and keeps it separate for human review. The live app is deployed on Render. We tested spoken corrections, document generation, bug reporting, and scope proposals. Briefly reduces the work of rewriting conversations while keeping final decisions in human hands.

Bug reports often describe a symptom without providing enough evidence to reproduce or verify the problem. This creates unnecessary back-and-forth between developers, testers, and reviewers. A developer may fix the visible issue, but without a reliable reproduction and regression test, the same bug can easily return later. BugReplay is a small evidence-first debugging prototype built around this problem. It demonstrates a fictional checkout defect where the SAVE10 coupon is applied twice to a $50 cart. The correct result after one 10% discount is $45, but the original buggy implementation returns $40 because the same discount is subtracted twice. The prototype allows a user to enter notebook and pen-set quantities, provide a coupon code, choose between the original bug and repaired code, and calculate the checkout total. The original variant reproduces the incorrect result, while the repaired variant applies the discount once and returns the expected total. The verification page then presents the before-and-after evidence together with the regression-test outcome. The workflow is intentionally simple: report the problem, reproduce it with controlled inputs, inspect the calculation, apply a focused repair, add a regression assertion, and verify the result. This makes the debugging process easier to understand and review. BugReplay is intended for developers and reviewers who need a clear connection between a bug report, the code change, and the proof that the change works. It uses only fictional synthetic data. There is no real payment processing, customer information, authentication, or production integration. The project is built with Next.js, React, TypeScript, Vitest, and IBM Bob IDE. It is deployed as a working prototype on Vercel. GitHub repository: https://github.com/Kunal435573/bugreplay Live demo: https://bugreplay.vercel.app/bugs/BUG-001 Verification page: https://bugreplay.vercel.app/bugs/BUG-001/verification

Six Matches. One leaderboard. Build on AMD, earn points and compete for prizes.

💻 Online Hackathon | ⏳ Build: 48 hours | 📅 September 25–27, 2026 The official IBM Bob 2.0 hackathon. Build what's next in AI-assisted development, alongside the developers and experts shaping it. ⭐ Get help from experts throughout the event 🤝 Join a team or build solo 💰 Prize pool: $12,000 🧑🏻‍💻 Register before the Kick-Off Stream to start building with Bob

🌎 Online Hackathon | 💻 Month-long challenge | Dates: Sep 1–30, 2026 | 🏆 $10,000 Prize Pool ($5k cash + $5k in AAI credits) A month-long online challenge run by lablab.ai together with AssemblyAI, the Voice AI infrastructure company for builders. Every participant builds on AssemblyAI. You can join at any point — registration stays open for the whole build window, so you can start on day one or pick the project up halfway through and still submit. 🌍 Fully online hackathon. Join and build from anywhere in the world.