Summary: AI on a real project

Three people are about to read about you, and no two will read the same way. A recruiter opens your resume with dozens more waiting and may give it less than a minute, and the document was quite possibly filtered through screening software before any human saw it. A hiring manager reads your cover letter slowly, hunting for evidence that you understand the actual work. A former coworker glances at a two-line note and decides on the spot whether to answer. One person, one true story, three readers with three different goals. Most job seekers write one document and send it everywhere, which is why most applications read as if written for no one. This lesson runs everything from lessons 2 through 4 on that problem, end to end, from first draft to final handshake.

Core ideas

• The lesson adapts the case-study session that closes the using-AI-well unit of the Harvard Kennedy School course this track is built on: everything the unit taught, run end to end on a single communications campaign. The session ends by inviting you to take the method to a situation “closer to what you do in your day-to-day life,” and this lesson accepts: a job search, with a small-nonprofit detour near the end.
• The whole method fits in three questions, asked before any piece goes to the machine. Who will read this? Where will they read it? What should happen because they read it? Audience, platform, goal. It sounds almost too simple to matter. It is the whole method.
• On the job search: the resume bullet faces a recruiter, lives in a skim, and its goal is survival to the next round, so it stays short, factual, dense with the posting’s own vocabulary. The cover letter faces the hiring manager, gets an actual read, and must earn an interview, so it can breathe. The outreach note goes to someone who already knows you and asks for fifteen minutes, nothing more. The facts never change. The shape changes every time, on purpose.
• The task passes lesson 4’s first filter loudly: it needs personalization, there is a body of text to draw from (old resumes, notes on past wins, the posting itself), it rewards creative variation, and your strongest bullet is demonstration data. The course runs this same scoring on its own project and reaches the same verdict. This is the machine’s kind of work.
• The handoff starts warm: the assistant you built in lesson 3’s practice already holds your resume and standing instructions, so you go straight to task, instructions, context, exactly as lesson 2 drilled.
• When you do not know what context the machine needs, turn the question around. The session’s teacher, unsure what to feed the tool, stated the goal and added, “please ask me what you need to know to do this task well.” Back came clarifying questions the teacher admitted to never having considered, and answering them made the drafts markedly better. One sentence buys the interview.
• Then iterate, because a first draft is a proposal, not a verdict. Read each draft the way its reader will, say what is off, and let it revise. Speed is what you handed over. Judgment stayed home.
• Lesson 4’s second filter decides which pieces stay yours. Drafting: the machine’s, all of it. But every claim about you that survives into a final document gets your check, line by line, against what actually happened. Left unwatched, the machine will quietly promote you: helped with becomes led, familiar with becomes expert in. It is not lying. It is predicting. You are the only fact-checker your own life has, so never let it invent an accomplishment.
• Privacy rides along. Your story is yours to share; your current employer’s is not. Swap confidential figures for shapes you have the right to share: grew, halved, doubled. Lesson 4’s question settles every paste: am I comfortable with this information leaving my hands under this tool’s rules?
• Rehearsal is the session’s most surprising move. One prompt sets it up: act as the interviewer for this role, do not write the whole exchange as a script, ask one question, then stop and wait for my answer. Because the assistant holds your resume and the posting, its questions aim at your actual seams: the gap, the missing tool, the career change you have never practiced explaining.
• The role-play takes direction. The session notes you can tell the tool to play its part more aggressively or less, tuning the exchange into the preparation you want: a friendly screening call on the first night, a skeptical, pressing panel the night before the real thing. When an answer comes out weak, say so and run it again. Rehearse the follow-up, not just the opener.
• Be honest about what rehearsal is, because the course is. Its own classroom split: some students found the simulation genuinely capable, others said a live spoken performance is mostly voice and presence and a text exchange sits a long way from that. The session’s teacher sides with caution: this is far from the real event, and nobody is proposing to remove the humans from your preparation. The machine coach is available at midnight and never tires of your seventh attempt. Use it as a complement: let it find the questions you have no answer for while discovering them costs nothing, and keep one live mock interview with a human who can hear you.
• The method travels because nothing in it knew it was about a job search. A three-person food pantry runs it identically: one true story, three readers (a foundation officer scoring a grant against a rubric, neighbors scrolling a community page, a store owner weighing a shelf sponsorship), audience, platform, goal named before every piece, consent before anyone else’s story goes in, and a skeptical program-officer persona the night before the funder meeting.
• The session sorts uses of AI along a spectrum: some sit comfortably (preparing, rehearsing, drafting from your own material), some leave some people uneasy, and some most people would find hard to defend. The bright line is brighter than it first looks: after reading, does this person believe anything false about you? Polishing true sentences leaves every fact standing. Fabrication plants a false belief, and application materials are promises the interview collects on. Fabricate a line and you have scheduled your own exposure, in the one room the machine cannot enter with you.
• Two habits keep you on the right side. Patrol the drafts for inflation you did not ask for, and strike anything you could not defend under a follow-up question. And default to daylight: if an employer asks whether or how you used AI, answer plainly. If the thought of a reader knowing how a piece was made makes you flinch, the flinch is your answer about the piece.

What changes for you

The method is not about job hunting. One project, many readers, judgment at every handoff, rehearsal before the stakes: that skeleton fits a grant, a pitch, a proposal, a hard announcement. Rehearsal may be the most underused skill in this track; most people only ask the machine to produce things, and asking it to push back, in persona, before a moment that counts, is where the confidence comes from. And one question keeps every use defensible: would this still work if the reader knew how it was made? The practice runs the whole method in Clawless on your own project. The next lesson opens the track’s second movement, from how do I use this well to what it means for your world, starting with the kinds of risk this technology carries and the levers for managing them.