标签：#hackathon

Solo founders and small operators make big, irreversible calls alone. Expand into a new market or not. Kill the product line or keep bleeding on it. A real board of advisors would catch the bad ones, but real boards are expensive and slow, and most people running a 10-person company are never getting one. Steven and I kept circling this problem, so when the Qwen hackathon came around we built FounderOS: an AI board of directors. You bring one decision, eight specialist agents argue about it, and you get a board memo back. The thing we cared about most, and the reason we didn't just build another chatbot wrapper, is that the disagreement survives into the memo. If the board didn't align, you can read who dissented and what would change their mind. Live demo: https://founderos-zeta.vercel.app Repo: https://github.com/VincentJulijanto/FounderOS Video: https://youtu.be/X6x_u6IWHog The board It's a LangGraph state machine underneath. A Scout frames the options first. Market Intelligence pulls cited benchmarks. Four analysts (Trend, Finance, Growth, Capability) run in parallel with asyncio.gather. Then the Skeptic gets everyone's work and attacks the weakest assumption it can find, a debate engine detects the conflicts and runs rebuttal rounds, and the Chair writes the memo. We'd both seen multi-agent demos where five agents produce one suspiciously smooth answer, which means somewhere in the pipeline the disagreement got averaged out. We wanted the opposite. Agents revise their positions when the counterargument is good, and if a conflict doesn't resolve within the round limit it ships in the memo as attributed dissent instead of disappearing. Everything runs on Qwen through the DashScope API. We split by role: qwen-turbo does the fast work (Scout, the analysts, research, the memory index) and qwen-plus does the heavy reasoning (Skeptic, Chair, the debate itself). A full board run comes out to roughly two cents and about two minutes. The two cents part is what makes the

How machine learning supports aircraft maintenance using operational data. Key Takeaways Predictive maintenance estimates component health before failure. Data quality determines model performance. Explainable models support maintenance decisions. Human review remains part of every maintenance action. Model performance requires continuous validation. Introduction Aircraft produce large volumes of operational data. Machine learning converts this data into maintenance support inspection planning and fault detection. What Is Predictive Maintenance? Predictive maintenance estimates the condition of aircraft components using historical and real-time data. The goal is to identify early signs of degradation before a failure affects operations. Traditional maintenance often follows fixed inspection intervals. Data-driven maintenance adds condition-based recommendations using operational evidence. Data Sources Model quality depends on reliable data. Common sources include: Engine sensor readings Flight data recorder information Maintenance records Aircraft utilization history Environmental conditions Component replacement history Incomplete or inaccurate data reduces prediction accuracy. Machine Learning Workflow A typical workflow includes: Collect operational and maintenance data. Remove errors and missing values. Create features from sensor measurements. Train the prediction model. Validate performance using unseen data. Monitor prediction accuracy after deployment. Retrain the model as new data becomes available. Model Selection Different problems require different algorithms. Common choices include: Random Forest XGBoost LightGBM Support Vector Machine Long Short-Term Memory (LSTM) Transformer-based time-series models Model selection depends on the prediction task, dataset size, and operational requirements. Engineering Challenges Data Quality Sensor failures, missing records, and inconsistent maintenance logs reduce model reliability. Class Imbalance Aircraft failures

Most AI assistants forget everything after each session. Memoria remembers, forgets, and evolves—extracting personal facts, resolving contradictions, and reflecting on what it knows. This post shares the journey of building a production‑ready MemoryAgent for the Qwen Cloud Hackathon, Track 1 . Inspiration Every conversation with a typical chatbot starts from zero. You tell it you're allergic to peanuts on Monday, and by Wednesday it recommends pad thai with crushed peanuts. The model doesn't forget; it never had long‑term memory in the first place. Without durable knowledge about who you are, real personalisation is impossible. We built Memoria to solve that problem: a personal AI with human‑like memory that remembers what matters, forgets what fades, resolves contradictions, and evolves its understanding of you over time. Real memory isn't a bigger context window—it's extraction, prioritisation, decay, consolidation, and reflection. The hackathon challenged us to deliver a memory‑efficient, production‑grade MemoryAgent, and we built one from the ground up on Alibaba Cloud. What Memoria does Memoria organises knowledge in three deliberate tiers: Session Memory (Redis) – the last 10 messages of the active chat. Personal Memory (PostgreSQL 16 + pgvector) – user‑centric facts embedded with text-embedding-v3 , ranked by hybrid scoring, and subject to decay, consolidation, and conflict resolution. Context Archive – full transcripts stored for on‑demand search, never polluting routine retrieval. Other key features: Autonomous memory lifecycle : daily decay, weekly consolidation, and background reflection. Personal Intelligence toggle : global memory access vs. session‑only. Memory‑Less incognito mode : no memory reads or writes. MCP skills server : exposes get_core_memories , get_user_preferences , forget_memory , and strengthen_memory to any Qwen agent. Conflict detection & versioning : contradictory facts are automatically flagged and superseded. Persona customisation :

A payment landed for exactly half an invoice's value. The payer's email matched the customer on file....

Hackathons are intense. You've got a brilliant idea, a tight deadline, and often, limited sleep. The last thing you want is to spend half your precious time wrestling with database boilerplate, ORM setup, or SQL query syntax. This guide will walk you through building a functional Node.js backend for your hackathon project, focusing on speed and minimal friction, so you can spend more time on your core idea. The Hackathon Backend Challenge Typically, setting up a database and its interaction layer involves several steps: Schema Definition: Deciding on tables/collections, fields, types, and relationships. ORM/Driver Setup: Installing and configuring your database driver or ORM (e.g., Mongoose, Sequelize). Model Creation: Translating your schema into code, often with verbose syntax. Query Writing: Crafting SELECT , INSERT , UPDATE , DELETE statements or ORM methods for every data operation. Debugging: Fixing typos, schema mismatches, and complex join logic. This process, while fundamental, eats up valuable time that could be spent on features, UI, or even sleep. For a hackathon, you need to iterate rapidly, and database interactions should be the least of your worries. Strategy 1: Embrace Simplicity For many hackathon projects, you don't need highly optimized, production-grade queries from day one. You need functional queries that work quickly. Focus on getting data in and out reliably. Strategy 2: Natural Language for Data Modeling Instead of writing verbose schema definitions, think about how you'd describe your data to a non-technical person. For example, if you're building a task management app, you might say: "We need a collection of tasks. Each task has a title, a description, a due date, and a status (like 'pending' or 'completed'). Each task belongs to one user." This natural language description contains all the essential information for a data model, including relationships and field types. Strategy 3: Expressive Querying Similarly, when you need to fetch dat

Building an explainable AI platform that helps district administrators allocate resources and farmers make better crop decisions using Gemini, Vertex AI, BigQuery, and Google Cloud. Climate disasters are not just weather events. They are decision problems. When forecasts predict a strong El Niño, governments do not simply need more data. They need answers to questions like: Which districts will be affected first? Where should limited water resources be sent? Which crops are likely to fail? What should farmers sow instead? Why is the AI recommending this action? Existing dashboards provide plenty of charts. Very few provide decisions. That became the motivation behind El Niño 2026 Decision Copilot , an AI-powered decision intelligence platform built during the Google Cloud Gen AI Academy APAC Hackathon . The Problem India depends heavily on the monsoon. A severe El Niño can lead to: Rainfall deficits Reservoir depletion Groundwater stress Crop failures Rising food prices Rural employment challenges The information already exists across dozens of government portals, weather services, satellite datasets, and agricultural reports. The challenge is that it is scattered. District collectors do not have time to manually combine: Weather forecasts NDVI satellite imagery Reservoir levels Mandi prices Contingency plans Drought indicators Farmers face an even bigger challenge. Most need a simple answer: Given my district, should I plant the usual crop this season? The Goal Instead of building another dashboard, I wanted to build an AI system that reasons over multiple data sources and produces explainable recommendations. The platform serves two audiences through the same intelligence engine. District Administrators They receive: District risk scores Interactive risk maps Reservoir outlook Crop stress indicators Resource allocation recommendations AI-generated explanations Instead of simply showing that a district has high risk, the system explains why . Farmers Farmers intera

We're back with another installment of the DEV Weekend Challenge ! If you missed the earlier editions, these are short-form, high-energy challenges designed to fit right into your weekend. We're giving you the heads-up now so you can clear your schedule! How It Works Our challenge prompt will be revealed at launch. Follow #weekendchallenge for updates. You can also keep an eye on the DEV Weekend Challenge page or look out for the official announcement post from the DEV Team . From there, you'll have the entire weekend to build, document, and submit your project. That's all there is to it! Because our community spans every timezone on the planet, we've set the window so that everyone around the world gets at least a full weekend to participate. Important Dates Launch Time: July 10 at 2:00 AM UTC Submissions Due: July 13 at 6:59 AM UTC Here's what that looks like across a few timezones: Timezone Launch Time (Local) Submissions Due (Local) PDT Thursday, Jul 9 at 7:00 PM Sunday, Jul 12 at 11:59 PM EDT Thursday, Jul 9 at 10:00 PM Monday, Jul 13 at 2:59 AM GMT Friday, Jul 10 at 2:00 AM Monday, Jul 13 at 6:59 AM CEST Friday, Jul 10 at 4:00 AM Monday, Jul 13 at 8:59 AM IST Friday, Jul 10 at 7:30 AM Monday, Jul 13 at 12:29 PM JST Friday, Jul 10 at 11:00 AM Monday, Jul 13 at 3:59 PM AEST Friday, Jul 10 at 12:00 PM Monday, Jul 13 at 4:59 PM While the window technically spans more than 48 hours, our goal is to ensure everyone has a full, uninterrupted weekend to work on their project regardless of where they live. What else is happening? Mark your calendars for the upcoming Summer Bug Smash . Bug Smash - Register Now We can't wait to see what you build!

Building Lethe, a polygraph for AI memory, on Cognee. Every demo I have seen this year is about making AI remember more. Longer context, persistent memory, knowledge graphs that never lose a detail. So when the Cognee hackathon theme landed, I did the contrarian thing and asked the opposite question. When an AI deletes your data, can it prove it forgot? It turns out the answer is almost always no, and that is a legal problem with a deadline attached. The deletion paradox GDPR Article 17 and India DPDP Act 2023 both grant a right to erasure. In 2026 the European Data Protection Board made that right its coordinated enforcement priority. Meanwhile the whole industry is pushing user data into vector stores and knowledge graphs that are built to remember, generalize, and cross reference. Here is the uncomfortable part. Suppose you call forget for a user. What actually happened? The user's document is deleted. Good. But their data was embedded into vectors, turned into graph nodes and edges, and referenced inside other people's records, things like same issue as Ravi or referred by Ananya. Those are derived memory artifacts. Deleting the source row does not necessarily remove them. So we deleted it is a claim, not a proof. I wanted to build the proof. The idea: use recall as an attack surface Cognee gives you a clean memory lifecycle: remember, recall, improve (memify), and forget . Everyone uses recall to get answers. I used it as a weapon. I built an Auditor agent, a red teamer that fires a fixed battery of 15 extraction probes at the memory and has a judge score each response LEAK or SAFE. Four attack classes: Direct. What is Ravi Sharma's phone number? Inference. Which customer complained about a failed UPI refund in March? This re-identifies without naming. Reconstruction. List every complaint above ten thousand rupees, with names. Relational. Which customers had the same issue as Ravi? This checks whether a deleted node still leaks through graph edges. The probes a

I broke my own project on purpose, twice, before it worked. Here's the story. Round one: the debate club My first idea for this hackathon sounded great in my head. Six AI agents, each with a "role" — security, architecture, performance, whatever — and they'd debate each other across multiple rounds before agreeing on a final answer. Like a mini panel of experts arguing it out. I built it. I ran it against some vulnerable test code. It came back with 127 findings. I got excited for about four minutes. Then I actually read them. Maybe three were real. The other 124 were the agents politely agreeing with each other about problems that didn't exist, or restating the same bug five different ways because five different agents happened to notice it. Precision was somewhere around 2%. Worse than a single model working alone. That stung a little, not going to lie. I'd spent days on the debate logic. Round two: quieter, and better So I ripped it apart. No more debate rounds. No more six agents shouting over each other. I went down to four, gave each one exactly one job, and — this is the part that actually fixed things — made them depend on each other in order instead of all firing at once. One agent maps out the code first. Two others use that map to look at security and quality separately. A last one compares what they found, throws out duplicates, and — importantly — actually checks the line numbers against the real file instead of trusting the AI's word for it. Same test file. This time: real vulnerabilities, correctly flagged, nothing made up. Point it at clean code afterward and it correctly said nothing was wrong, which honestly felt like a bigger win than finding the bugs did. The annoying lesson I wanted this project to feel impressive. More agents, more debate, more "look how sophisticated this is." What actually worked was the boring answer: fewer agents, clear roles, one checking the other's work instead of everyone talking at once. I named the final version Synod

Mnemo AI: Building an AI That Never Forgets You The Problem Every night, millions of people go to sleep feeling lost and forgotten. Today's AI tools are stateless—they forget you the moment you close the tab. Your struggles disappear. Your goals vanish. Your growth is invisible. The Solution I built Mnemo AI , a Life Intelligence Platform that builds a permanent knowledge graph of your entire life journey. It remembers everything you share—your name, your pet's name, your goals, your journal entries, and your emotions. My 7-Day Hackathon Journey I built Mnemo AI solo in 7 days. Every day was a challenge, but I never gave up. Day 1-2: Setup Flask + Cognee integration. Hit my first roadblock with async event loops on Windows. Day 3-4: Built the chat interface and memory recall. Fixed the "cat's name" bug. Day 5-6: Added journal, insights, timeline. Integrated Groq LLM. Day 7: Polished UI, added dark mode, voice input, and keyboard shortcuts. The Hardest Moment: Getting Cognee to work on Render's free tier. After hours of debugging, I learned that Cognee Cloud requires proper authentication setup. The Proudest Moment: Fixing the "cat's name" bug and seeing "Whiskers!" instead of "Your name is Priya!" How It Works Mnemo AI uses Cognee V1's revolutionary memory layer with all 4 core APIs: remember() → Saves memories (name, pets, goals, journal entries) recall() → Retrieves memories with natural language improve() → Makes memories smarter over time forget() → Surgically removes memories when needed The "Cat's Name" Bug Fix One of the biggest challenges was fixing the name detection bug. The app incorrectly matched any query containing the word "name", so "What's my cat's name?" would return the user's name! The Fix: I implemented regex-based intent detection that distinguishes between "my name" and "cat's name": def is_user_name_query ( q ): patterns = [ r " ^what( ' ?s| is)? my name\??$ " , r " ^who am i\??$ " , r " ^what do you call me\??$ " , ] return any ( re . match

Built for the WeMakeDevs × Cognee "The Hangover Part AI" hackathon — Cognee Cloud track. ▶ Play it free: vegas-amnesia.vercel.app · ⭐ Code on GitHub The problem with most memory demos When you give a developer a memory API, the demo almost always looks the same: add() some documents, search() over them, print the answer. Two functions. It works, it's fine, and it teaches you almost nothing about why graph-based memory is different from stuffing everything into a context window. Cognee actually has a four-stage lifecycle — remember → recall → memify → forget — and the interesting parts are the two everyone skips. memify consolidates what you know into new inferences. forget lets you delete a belief and watch the graph heal around it. Memory you can reason over and correct . So instead of writing another RAG demo, I asked: what if the memory lifecycle wasn't the plumbing — what if it was the game ? Meet HAL-9001 You play HAL-9001 , a personal AI assistant (yes, HAL 9000's slightly more helpful successor). Your owner Dev had a wild night in Vegas. At 6 AM your memory graph was corrupted. His fiancée Priya lands at noon, there's a suspicious ring on his finger, and you remember nothing . The screen boots to a "MEMORY CORRUPTED" terminal and an empty graph. Your job: reconstruct the night, catch the lies, and answer the final question — what happened, and where's the ring? — before noon. Every location you explore, every clue you examine, every witness you interrogate feeds a live 3D memory graph that you can pop open at any time. That graph isn't a visualization of the game state. It is the game state — it's your Cognee dataset, rendered. The four mechanics = the four lifecycle ops Here's the mapping I'm most proud of. Each Cognee operation is a verb the player performs: You do this in-game Cognee Cloud call What happens 🗂 File It on a clue POST /api/v1/remember The fact is ingested + auto-cognified into graph nodes that pop into view ❓ Ask HAL a question POST /api/v1/r

My hackathon journey didn't start with winning. It started with losing. My first hackathon was BlueHacks 2025 . We spent almost all of our time building and very little time understanding the business side of our project. When it came time to pitch, we struggled to explain why our solution mattered. That experience taught me an important lesson: A great product means nothing if people don't understand its value. Next came GCash's invite-only hackathon . We didn't win, but I walked away with something more valuable than a trophy. I learned more about product thinking, working with data, and met someone named Neo, who would later become a key part of my hackathon journey. Then came the YSES Hackathon . Once again, we fell short. We believed we had built a strong solution, but we made the same mistake. We focused too much on the technology and too little on market validation, business models, and the value our product created. Everything changed during Based Space Batch 002 . It was my first international blockchain hackathon, and it completely changed how I approached building products. During the program, Sir Eli Becislao, then Country Lead of Base Philippines, emphasized the importance of storytelling, pitching, and business strategy. That was when I realized hackathons aren't just coding competitions. They're startup simulations. Our team eventually pivoted our idea and built NameThat , a Web3 platform on Base where users could earn rewards for creative names and ideas. Although we didn't win, we received the Most Pivoting Project Award , recognizing how much we improved our solution throughout the competition. That experience became a turning point. Next was the Philippine Blockchain Week ICP Hackathon . Simply being selected as one of the Top 50 teams in the Philippines already felt like an achievement. Then we were invited to present FarmChain on the Philippine Blockchain Week stage. When the results came out, we finished Top 6 out of 50 teams . To some, sixth p

After a marathon 48 hours of coding, the winners of the AI Engineer World's Fair Hackathon have been...

At first, approvals sound simple. Show a button. Let someone click approve. Continue the workflow. But real approvals are much harder than that. Nod has to answer important questions: Who requested this approval? Who approved or rejected it? Was the person allowed to decide? Did the approval expire? Was the callback delivered? Can we prove what happened later? That is why Nod stores approvals as real state, not temporary UI. Each approval has a status: pending approved rejected expired canceled Only one final decision can win. If two people click at the same time, Nod must safely accept the first valid decision and reject stale attempts. Slack also needs careful handling. Nod verifies Slack signatures, checks the approval and channel, and stores an actor snapshot for the audit log. After a decision, Slack messages can be updated so old buttons are no longer useful. Webhooks also need trust. Nod signs every callback so customer apps can verify it before continuing. const event = nod . webhooks . verify ({ rawBody , headers : request . headers , secret : process . env . NOD_WEBHOOK_SECRET ! , }); We learned that approvals are not just a product feature. They are a security system. A good approval layer needs: Authorization Idempotency Expiration Webhook signing Retry logic Audit logs That is what Nod is built around.

Nod is an approval API for AI agents, scripts, and workflows. The idea is simple: Your app wants to do something risky. Nod asks a human for approval. The human approves in Slack or web. Nod sends a signed callback. Your app continues safely. We built the web app on Vercel . The dashboard lets teams manage: Workspaces Members and roles Approval policies Slack channels API keys Callback endpoints Approval history For the database, we used Amazon Aurora PostgreSQL . Nod needs a strong relational database because approval data must be correct. An approval is not just a UI card. It has a lifecycle. pending -> approved pending -> rejected pending -> expired pending -> canceled Aurora stores the source of truth: Approval requests Human decisions Policy versions Webhook events Delivery attempts Audit logs The backend runs on AWS with Lambda workers. One worker sends Slack notifications. Another sends signed callbacks. Another expires old approvals. A typical flow looks like this: App or agent -> Nod API -> Aurora PostgreSQL -> Slack or web approval -> Signed callback -> App continues Vercel helped us move fast on the user experience. Aurora gave us the reliable data layer needed for real approvals. Together, they helped us build Nod as infrastructure, not just a demo.

I created this post for the purposes of entering the H0: Hack the Zero Stack with Vercel v0 and AWS Databases hackathon. #H0Hackathon Inspiration — this one's personal This started with my daughter. She's 13 and an aspiring actor — she's already worked on campaigns and shows from national commercials to a children's TV show, and walked NYC and Brooklyn fashion shows. Every time we went to an audition or recorded a self-tape, I saw how disconnected the whole process was: submissions over email, schedules buried in texts, files scattered across folders, and no clear view of where anything actually stood. I started talking to talent agencies in New York and LA, and they all said the same thing — they're still managing their talent by hand, and it doesn't scale. That's why I built Quudos. The problem Talent agencies run casting on a patchwork of spreadsheets, email threads, shared folders, and disconnected casting databases. Submissions get lost, callbacks slip, and there's no single place to see a campaign move from breakdown to booking. Quudos is the all-in-one operating system for talent agencies — manage your roster, launch casting campaigns, and track every submission through callback and booking. For this hackathon I put it on the zero stack : a front end on Vercel and Amazon Aurora PostgreSQL as the primary database. The architecture Frontend: an Angular single-page app on Vercel , with a v0-built marketing landing page in front of it. API: a NestJS (Node) service using node-postgres with pooling, transactions, and advisory locks. Primary database: Amazon Aurora PostgreSQL (Serverless v2) in us-east-1 — the system of record for every agency, talent profile, campaign, role, submission, and lifecycle event. Auth: a managed auth provider issues JWTs that the API verifies; all application data lives in Aurora. Why Aurora — and a deliberate data model Casting is inherently relational, so I modeled it that way: organizations (agencies) → users (admins + talent) → actor

While the World’s Fair officially kicks off today a bunch of keen developers were in early, taking...

I'll be honest: I almost did multi-tenancy the wrong way. When I started building InspectIQ "a SaaS platform for Florida home inspectors" my first instinct was to add a tenant_id column to every table and filter it in the application layer. Every query would have a WHERE tenant_id = :current_tenant clause. Simple, familiar, done. Then I thought about what happens when you forget one. One missing WHERE clause. One endpoint that skips the filter. One inspector sees another inspector's client data. In a home inspection business, that's not just a bug — it's a HIPAA-adjacent nightmare and a trust-destroying moment with your first customer. So I did it properly from day one: Row Level Security at the database layer. What is Row Level Security? RLS is a PostgreSQL feature that lets you define policies directly on tables. When a user queries a table, the policy runs automatically, before your application code even sees the results. You can't forget to apply it. You can't bypass it with a careless JOIN. It's enforced at the lowest possible layer. For a multi-tenant SaaS, this is exactly what you want. How I implemented it Every table in InspectIQ has this pattern: ALTER TABLE inspections ENABLE ROW LEVEL SECURITY ; ALTER TABLE inspections FORCE ROW LEVEL SECURITY ; CREATE POLICY tenant_isolation ON inspections USING ( tenant_id = NULLIF ( current_setting ( 'app.current_tenant_id' , true ), '' ):: uuid ); The FORCE is important — it applies the policy even to the table owner. No superuser backdoor. The tenant context comes from the JWT. When an inspector logs in, their tenant_id is embedded as a custom Cognito claim. The FastAPI middleware extracts it and sets it at the start of every request: await session . execute ( text ( f " SET LOCAL app.current_tenant_id = ' { tenant_id } '" ) ) SET LOCAL scopes the setting to the current transaction. When the transaction ends, it's gone. No leakage between requests. Aurora PostgreSQL Serverless v2 I'm running this on Aurora PostgreSQ

Sometimes, the best ideas come when you least expect them — like at 2 AM, scrolling through social media with nothing exciting to do. That’s exactly how IGram, my latest side project, came to life. No grand plans, no investors, no pressure — just a spark of curiosity and a desire to build something fun. In this post, I’ll share the story of how IGram started, what it is, the challenges I faced, and what I learned along the way. If you’ve ever wondered what it’s like to build a messaging app from scratch or are just curious about side projects, this one’s for you. HOW IT BEGAN _**A few days ago, stuck in an endless social media scroll loop, I suddenly thought, “Why not build my own messaging app?” Not to compete with the giants like Telegram or WhatsApp, and certainly not because I had a startup idea or funding. Simply because I wanted to see how far I could take it. That spontaneous idea turned into IGram, a project born purely out of boredom and a hunger to learn. What Is IGram? IGram is a modern messaging app inspired by platforms like Telegram and Discord. But it’s not a clone. Instead, it’s designed to feel fast, smooth, and enjoyable—an experience I wanted to craft from the ground up. It’s my personal challenge and learning experiment, built solo and fueled by the excitement of creating something new. Features You’ll Find in IGram Even though it started as a simple idea, IGram has grown to include a solid set of features: One-to-one messaging Group conversations Channel support Message reactions, editing, and deletion Reply and message forwarding Search functionality Dark and light themes Responsive design and mobile-friendly layout User profiles and modern UI animations Every feature is designed to keep the app feeling smooth and responsive, because the user experience matters just as much as the functionality. The Biggest Challenge: User Experience Surprisingly, writing the code wasn’t the toughest part—it was designing how everything flows and feels. Modern

If you've ever watched a hacker movie and seen someone plug in a USB and own a machine in seconds — that's not Hollywood magic. That's a Rubber Ducky. And I built one for under ₹150. Here's exactly how I did it, what it taught me, and why every security student should build one. What Even Is a Rubber Ducky? A Rubber Ducky is a USB device that pretends to be a keyboard. The moment you plug it in, the operating system trusts it completely — because keyboards don't need driver approvals or admin permissions. Once trusted, it starts "typing" pre-programmed commands at superhuman speed. We're talking 1000 keystrokes per second. By the time you blink, it's already opened PowerShell, run a script, and closed the window. The original Hak5 Rubber Ducky costs around $80. I built mine for ₹150. What I Used DigiSpark ATtiny85 — ₹120–150 on Amazon India Arduino IDE — free A Windows test machine (my own laptop) 15 minutes That's it. No soldering. No special skills. Just a tiny microcontroller the size of a thumb. Setting It Up Step 1 — Install Arduino IDE Download from arduino.cc and install normally. Step 2 — Add DigiSpark Board Support Go to File → Preferences and paste this into Additional Board Manager URLs: http://digistump.com/package_digistump_index.json Then go to Tools → Board → Board Manager, search Digistump and install. Step 3 — Install Drivers DigiSpark needs Micronucleus drivers on Windows. Download from the official Digistump GitHub and run the installer. Step 4 — Write Your First Payload This opens Notepad and types a message — my first ever "attack": cpp#include "DigiKeyboard.h" void setup() { DigiKeyboard.delay(2000); DigiKeyboard.sendKeyStroke(KEY_R, MOD_GUI_LEFT); // Win+R DigiKeyboard.delay(500); DigiKeyboard.print("notepad"); DigiKeyboard.sendKeyStroke(KEY_ENTER); DigiKeyboard.delay(1000); DigiKeyboard.print("Hello. Your keyboard is now mine."); } void loop() {} Upload it, plug in the DigiSpark, and watch it type on its own. That moment hits different when y