Syeed Talha@Sayed_Talha

First-round interviews don't scale. Recruiters lose days scheduling phone screens, every candidate gets different questions, and decisions come down to gut feeling — while great candidates accept faster offers elsewhere. InterviewCoach replaces the entire first round with a structured AI voice interview. An employer signs up, describes the role (JD, topics, pass score), and gets an AI-drafted question bank with scoring rubrics plus one auto-generated, shareable interview link. A candidate opens the link — no account, no scheduling — and talks to Talha, a live AI interviewer powered by the AssemblyAI Voice Agent API (real-time STT, managed LLM, TTS, barge-in). A video avatar listens while they speak and talks back; every answer is scored on clarity, depth, and STAR structure with instant spoken coaching. When the interview ends, the verdict appears immediately: beat the bar and a personal next-round pass link is auto-issued on the spot. Employers review transcripts, scores, pass rates, and passes in the hiring dashboard. Built with: AssemblyAI Voice Agent API (voice pipeline + turn detection), Python stdlib + SQLite backend (zero pip dependencies), Mistral AI question drafting with a role-aware local fallback, and a tool-call loop (get_question → evaluate_answer → get_session_summary).

The problem. Every free file converter on the internet makes you upload private presentations to someone else's server — a privacy risk wrapped in paywalls, watermarks, queues, and forced accounts, all for a 10-second task. Desktop suites are heavy overkill, and true conversion normally demands expensive server infrastructure. The solution. SlideShift flips the model: the converter is the webpage. Drop a .pptx and get a clean PDF; drop a .pdf and get a real .pptx — with drag & drop, paste support, quality and layout options, live progress with a per-slide log, and one-click download. Direction is auto-detected from the file, and a conversion counter in localStorage tracks usage without accounts. How it works. Four client-side engines do everything: PDF → PPTX renders each page to an image with PDF.js and places it full-bleed on its own slide with PptxGenJS (16:9 or 4:3). PPTX → PDF unzips the .pptx in-browser with JSZip, reads slides in true presentation order, extracts text and images, and rebuilds a styled PDF with jsPDF. Open DevTools → Network during a conversion: zero file traffic. Files never leave the tab. Honest engineering. This is a content-preserving converter, not a pixel-perfect clone — stated openly on the site: .pptx only (no legacy .ppt), PPTX → PDF keeps text and images but not exact fonts, animations, or charts, and PDF → PPTX slides are faithful images rather than editable text. No password-protected PDFs. Why it matters. Because there is no backend, no database, and no build step — just public/index.html, styles.css, app.js plus CDN libraries — the entire app deploys on free static hosting forever, costs nothing to run, and can't leak your files because it never receives them.

CineCaption AI is a video captioning agent built for the AMD Developer Hackathon Track 2. It downloads a video clip, extracts eight evenly-spaced key frames using ffmpeg, and sends them to Kimi K2.6 — a vision-language model on Fireworks AI — which produces a detailed factual description of the scene. That description is then passed to DeepSeek V4 Pro, a text model that generates four styled captions: formal, sarcastic, humorous-tech, and humorous-non-tech. The pipeline processes multiple videos in parallel using ThreadPoolExecutor, completing each clip in 30-60 seconds. It includes automatic retry logic, JSON parsing with fallback, and a per-style fallback caption generator to guarantee output for every requested style. The entire agent runs inside a lightweight Docker container (python:3.11-slim + ffmpeg) and is deployed to GitHub Container Registry with a linux/amd64 manifest.

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

🌎 Hybrid Hackathon | 💻 Online Build: 3–8 November 2026 | On-site Phase: 8 November 2026 📍 On-site Venue: Pierpont Place 163 W Pierpont Ave, Salt Lake City, UT 84101, USA ✨ Please note that travel and accommodation are not covered.

🌎 Hybrid Hackathon | 💻 Online Build: October 16–19, 2026 | 📍 On-site: October 19–20, 2026 The official hackathon of AI & Big Data Expo Europe, organized by TechEx Events and lablab.ai. Build AI applications and agents across AI, cybersecurity, cloud, IoT, automation, edge computing, digital transformation, and data infrastructure, then showcase your project live at one of Europe's largest enterprise technology events. 📍 On-site Venue (October 19–20): RAI Amsterdam Europaplein 24, 1078 GZ Amsterdam, Netherlands 📍 If approved for the on-site experience, you'll also have the opportunity to showcase your project live. Travel and accommodation will not be covered.

🌎 Hybrid Hackathon | 💻 Online Build: 12-17 October 2026 | On-site phase: 17-18 October 2026 To participate in the hackathon, simply click Sign up with AMD. If you are not already a member of the AMD AI Developer Program (ADP), you will need to create an account. The AMD Developer Hackathon: ACT III is a hands-on event for developers, founders, engineers and builders who want to push what’s possible with AI on real infrastructure. 📍 If approved for the on-site experience, you'll also have the opportunity to showcase your project live. Travel and accommodation will not be covered.

🌎 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.