Projects

You're going to build a real web app for one thing you wish existed, and put it live on the internet where actual people can use it. The skill is scope: deciding the ONE job it does well, cutting everything else, then shipping it and fixing what breaks when a real person tries it. That's the core of software engineering, turning an idea into a working thing and deciding what not to build, and doing one tells you fast whether shipping a live product is your kind of work.

You're going to build a bot that lives in a real Discord server and does one useful thing: a study buddy in your class server, a converter in a hobby server, a mood-check in your friend group. You'll get it replying fast, give it an AI brain, then decide what it should refuse to do, and the payoff is that it runs on its own and real people come to rely on it. That's what software engineers actually ship, a service that works without you watching it, and doing one tells you fast whether building things people depend on is your kind of work.

You're going to build a Chrome extension that fixes something on the web that annoys you every day (a cluttered feed, endless threads, a site that buries what you need) and get it running in real browsers. The skill is subtraction: testing on the real sites, then cutting it to the one behavior actually worth keeping and making that solid. That's real software engineering, shipping code that runs in other people's browsers and doing one thing well, and doing one tells you fast whether building tools that run in the wild is your kind of work.

You're going to build an iOS Shortcut that does one annoying repetitive task for you, with AI wired in, and get a few friends to actually install and run it. The skill is the instinct for what's worth automating: spotting a thing you do over and over and going 'I could make that disappear.' That's how automation engineers think, seeing workflows where other people see chores, and doing one tells you fast whether that instinct is yours.

You're going to build a single-feature web product, give it a landing page, and get one real person to actually use it. The skill is building for a real user: watching someone use your thing, then cutting everything that isn't what they needed. That's the founder instinct, finding someone with a problem and making them exactly what solves it, and doing one tells you fast whether building something people want is your kind of work.

You're going to make a 60 to 90 second film: write a treatment, generate the shots from it, then cut everything that doesn't earn its place until you've got something tight. The work is mostly the edit: pacing it so a stranger doesn't drift, killing shots even when you love them, deciding what stays. That's the real craft of filmmaking, the part that survives every tool change, and doing one of these tells you fast whether the cut is your thing.

You're going to make an original 2 to 3 minute track, design its cover, and share it. The skill is the choosing: generating a dozen versions and being able to say why one of them is the one and the others aren't. That's the ear of a music producer, the call about what a track actually needs, and doing one of these shows you fast whether trusting your taste like that is your kind of work.

You're going to make a real 15 to 25 minute podcast episode: research it, record it, cut it tight, and publish it on Spotify. The skill is the edit: explaining one thing cleanly to a stranger, then listening back and cutting the filler and rambling until every minute earns its place. That's the craft at the core of content creation, the part that makes something a stranger will actually finish, and doing one tells you fast whether that's your kind of work.

Generate a hundred AI images, then prove you've got the eye to pick the twelve that belong together. You'll lock one signature look and art-direct a series so tight a stranger can tell at a glance it's all one body of work. Making images is easy now; the taste to choose the right twelve is the whole skill, and it's yours.

Write a short comic and let AI draw it: 4 to 6 pages where the story and the characters are yours and AI renders the panels. The fun, maddening part: keeping one character's face consistent across every panel, and making the beats actually land. AI can draw all day; it can't make a character feel like a person or a story stick the landing. That's on you, and it's the part worth doing.

You're going to make a 15 to 30 second animated piece: a loop, a micro-story, or a transition. Working in seconds forces something hard: every frame has to carry something (story, motion, meaning) or it goes. That's motion direction, the eye animators build for what to keep and what to cut, and doing one of these tells you fast whether thinking in motion is your kind of work.

You're going to take a multi-step task you do every week and build an AI automation that runs it for you on your real data: group-chat summaries, turning one post into five, a morning calendar-prep digest. The skill is workflow automation: chaining steps across your apps and making the AI step in the middle hold up when messy real data hits it. That's a core piece of what AI application builders ship, processes that run reliably on their own, and doing one tells you fast whether building those systems is your kind of work.

You're going to build an AI that answers questions using only your own notes, links, and documents, and that you can trust because every answer shows you the source it came from. The skill is grounding: getting an AI to answer reliably from a specific body of knowledge and verifying it against the sources instead of taking its word. That's RAG, one of the most in-demand things AI application builders do (every company wants an AI that knows their own stuff), and doing one tells you fast whether building trustworthy knowledge tools is your kind of work.

You're going to build an AI agent that reads your incoming email, sorts it into categories, and drafts replies for the ones that need them. The skill is agent design: deciding the categories, then drawing the line on what the agent handles on its own versus what it must flag for you. That's the textbook first AI agent and a core thing AI application builders ship, and doing one tells you fast whether designing what an agent is allowed to do is your kind of work.

You're going to build a workflow where you talk, an AI turns what you said into the right structured thing (a task in your list, a note in your notes, a clean meeting summary), and it lands where you actually work. The skill is intent-extraction: getting the AI to capture what you MEANT, not just the words, and tuning it when it misreads you. That's a growing slice of what AI application builders do, and doing one tells you fast whether turning messy human input into reliable output is your kind of work.

You're going to pick a topic you care about, find a real angle, research it (verifying every source yourself), and publish a 1,500 word piece that actually argues something. The skill is building an argument you can defend: finding what the sources actually support, writing it in your own voice, and cutting any claim you can't back up. That's the core of journalism, having a real point and proving it rather than just summarizing, and doing one tells you fast whether that kind of thinking is your kind of work.

You're going to pick a real question with a real answer (how much your school district spends on athletics versus arts, why a local landmark closed, what your city actually does with recycling) and answer it with primary documents, not opinion. The skill is reasoning from evidence: figuring out what the records actually prove versus what you assumed going in, and claiming only what you can defend. That's what investigative journalism actually is, proving something true with evidence, and doing one tells you fast whether chasing the real answer is your kind of work.

You're going to write and publish a short story (~5,000 words) or a collection of 8 to 12 poems, using AI as an editor without ever letting it write a line for you. The skill is voice: keeping the writing unmistakably yours while using AI to sharpen it, and rejecting every suggestion that flattens you into generic 'good writing.' That's the thing only you can do as a writer, the part AI can't supply, and doing one tells you fast whether finding your voice is your kind of work.

You're going to launch a newsletter on a niche you care about, ship issue one fast, then keep shipping until you've got three real issues out to real subscribers. The skill is editorial identity and cadence: building a point of view recognizable enough that people open it, and shipping on schedule even before there's any applause. That's the discipline at the heart of being a creator, the thing that compounds where one-off posts don't, and doing one tells you fast whether shipping on a schedule is your kind of work.

You're going to turn a one-page brief into a full brand identity: a logo, a color palette, typography, and three mockups for a real or made-up business. The skill is coherence: picking ONE direction out of the options and making everything hold together as a single identity, then defending why that direction fits the brief. That's what brand designers actually do, decide what belongs and what doesn't, and doing one tells you fast whether shaping a visual identity is your kind of work.

You're going to design a reusable Notion template that other people can duplicate and actually run their lives with: a student planner, a college-essay tracker, an internship-application CRM. The skill is systems-design: deciding what to standardize, what to leave open for the user to fill in, and what to cut, then getting real people to adopt it. That's the durable, systems side of design, and doing one tells you fast whether designing things other people build on is your kind of work.

You're going to build and run a 6 to 9 post Instagram series on a niche, with a visual language consistent enough that a stranger recognizes it as one set. The skill is consistency with a point of view: keeping a recognizable identity across every post without getting repetitive, which builds trust faster than any single viral hit. That's the real engine of content creation, the cadence real creators run on, and doing one tells you fast whether running a series is your kind of work.

You're going to take a business idea, build a landing page, put it in front of real people, and read the signal: is there real demand, or should you kill it? The skill is reading that signal honestly, making the pursue-or-drop call without talking yourself into the answer you wanted. That's a founder superpower, finding out early whether an idea has real demand before you pour months into building it, and doing one shows you whether making that honest call is your kind of work.

You're going to find a real local business, figure out their actual annoyance, build them an AI tool for it, and get them to use it for two weeks. The skill is customer empathy: building for what they actually needed, not the cool version in your head, and learning the difference when you watch them use it. That's the instinct that separates founders who build things people pay for from ones who build demos, and doing one tells you fast whether reading a real customer is your kind of work.

You're going to start a tiny business and make one real sale: pick a product, put up a live listing today, launch it, and get a stranger to actually pay you. The skill is action bias: shipping a real, live thing fast and then doing the unglamorous work of getting someone to buy, instead of planning forever. That's the founder trait that's hardest to teach, and doing one tells you fast whether the ship-and-sell rush is your kind of work.

You're going to take a real question you care about, find a public dataset that can answer it, and publish a piece that argues a finding with real charts. The skill is analytical judgment: deciding what the data actually supports versus what you hoped to find, and not over-claiming when it's close. That's the real work of a data analyst, the call about what's true and what isn't, and doing one tells you fast whether digging for an honest answer is your kind of work.

You're going to build an AI assistant that helps people understand health information from trusted sources like the CDC and NIH, and that knows what to refuse: it never diagnoses, never gives medical advice, and routes anything serious to a real clinician. The skill is safety-boundary design: deciding what a high-stakes tool must never do, then proving it holds on the dangerous cases. That's the scarcest thing AI application builders do as AI moves into health and other high-stakes fields, and doing one tells you fast whether building tools that fail safe is your kind of work.

You're going to pick a real public company, read its latest 10-K, and write a buy, hold, or sell memo with a bull case, a bear case, and a recommendation you can defend. The skill is the analytical judgment under finance: reading a company closely enough to form a view, then holding it up against the strongest argument that you're wrong. That underlies equity research, strategy, and finance broadly, and doing one tells you fast whether forming and defending a call is your kind of work.

You're going to write a real Product Requirements Document for a feature you care about, then have AI play three people who tear into it from their own angles: an engineer, a designer, an exec. You decide which objections to take and which to push back on, then revise. That's the actual product-manager muscle, deciding what to build and defending the call when smart people disagree, and doing one tells you fast whether owning that kind of decision is your kind of work.

You're going to pick a real local issue (zoning, school funding, a proposed ordinance, public transit), research the actual law around it, and write a brief proposing a specific change with citations, then email it to a local official. The skill is building a position the evidence supports and answering the strongest argument against it, instead of just having an opinion. That's the core of policy and legal reasoning, and doing one tells you fast whether arguing from evidence is your kind of work.

You're going to build a real AI assistant for one narrow job, write the instructions that make it nail that job every time, and ship it to 10 real people who actually use it. The surprise is what's hard: not the tech, but scoping the problem tightly enough that the AI gets it right every time, which is the core skill of building with AI. This is the lightest way in to a whole career, and doing one tells you fast whether shaping a tool around a real problem is your kind of work.

You're going to build one tiny game (a single mechanic, like a one-button jumper) and then do the actual job of a game designer: tune it until it feels good. The skill is game feel: noticing why one jump feels satisfying and another feels like mush, then changing gravity, timing, a little screen-shake, a sound until 'meh' becomes 'one more try.' That's the heart of game design, the judgment about what's fun, and doing one tells you fast whether chasing that feeling is your kind of work.

You're going to build an AI app that does a real job for a real user, then make it reliable enough that they can actually depend on it. The skill is eval-hardening: writing a test set of normal and adversarial cases, finding where the AI breaks, deciding what 'reliable enough' means for your user, and fixing the worst failures. That's what AI engineers actually spend their time on and the part of the work that's becoming a real career, and doing one tells you fast whether making an unpredictable system trustworthy is your kind of work.

Ever gotten an email that felt *off*? Catching that feeling and proving it is the actual day job for a huge slice of cybersecurity. You'll triage a batch of suspicious emails the way a brand-new security analyst does on day one: pull apart the hidden headers, check the links and senders against threat databases (without ever clicking them), and make the call: is this a real attack, something sketchy worth escalating, or a harmless false alarm? You'll walk away with a reusable "is this phishing?" checklist and a written investigation, the exact kind of thing that gets a beginner noticed. One honest heads-up: this is *defensive* security, catching attacks, not the movie-hacker stuff (breaking in). That's not the boring version. It's where most real cyber jobs actually are.

You're going to work a realistic but completely made-up patient case end to end: take a history from an AI playing the patient, build a ranked list of what it could be, pick the one test that would settle it, and make the call. The skill is diagnostic reasoning under uncertainty: figuring out what's most likely, what would change your mind, and what to do right now, when you can't be sure. That's what a doctor's mind actually does, and doing one tells you fast whether reasoning toward a call without certainty is your kind of work. Important: these are fictional practice cases for learning to reason, never medical advice and never for diagnosing a real person.

You're going to take a real screen that frustrates people (a confusing checkout, a cluttered app, a signup that makes you give up), diagnose what's actually failing the user, and redesign it to fix THAT. The skill is product judgment: deciding what 'good' means for a real user's problem, committing to a tradeoff (faster checkout might mean fewer options on screen), and defending every change by how it helps, including the boring loading, empty, and error states most designs skip. That's the durable side of design, the part that's about decisions not decoration, and doing one tells you fast whether solving user problems is your kind of work.

You're going to write a creative brief, shoot a photo series to it on your phone, then do the part photographers say they're really paid for: cut the technically-fine shots that don't serve the brief and sequence the keepers into a story. The skill is editorial selection: deciding which images, in which order, carry the idea, so a stranger can see the intent at a glance. That's what separates a photographer from someone who takes nice photos, and doing one tells you fast whether the selection is your kind of work.