Projects

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 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 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 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 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 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.