Find Your Dream Job with AI · Training Slides
AI Training Series · Session 3 · July 2026

Find Your Dream Job with AI

Rules · Method · Two Full Case Studies · 30 Days of Action

← → or Space to navigate · F fullscreen · 32 slides

Today's Roadmap

Your rival isn't AI —
it's the job-seeker who uses AI well

Session 1 mapped the landscape, Session 2 put the tools in your hands — this session points all of it at the battlefield that matters most: your own career.

01 · New Rules

Entry-level jobs are shrinking, AI skills are commanding a premium, and your résumé's first screener may not be human

02 · The Method

The AI job-search workflow: knowledge base → résumé → portfolio → interviews

03 · Case · Finance

Mei's road into sell-side equity research: a report pipeline

04 · Case · Software

Shuai's road to Agent engineer: the portfolio is the résumé

05 · Red Lines & Mindset

AI amplifies the real you — it doesn't fabricate a fake one

06 · Action

A 30-day checklist, starting tonight

01

The Rules of the Game Have Changed

This is one of the hardest new-grad markets in decades — and the one where ordinary people hold the most leverage. Both are true at once. First, read the table you're playing at.

01 · New Rules · Cold Water First

Ice: entry-level jobs are being eaten by AI

−13%
Employment drop for 22–25-year-olds in AI-exposed occupations, while senior staff in the same roles grew 6–9% — AI is eating the "entry", not the "job"
Stanford Digital Economy Lab, on ADP payroll data covering tens of millions, 2025-08
1/3
Share of employers already using AI to replace entry-level hires instead of recruiting; Goldman Sachs estimates AI trims US employment by ~16,000 jobs a month
GMAC survey 2026-06 · Goldman Sachs 2026-04
12.7M
China's college graduating class of 2026 (up 480K year on year), an all-time high
Ministry of Education, 2025-11-20
One more cut: US tech shed over 150,000 jobs in H1 2026, with AI listed as the No. 1 cause of layoffs for 4 straight months (~48% attributed to AI and automation — the attribution may be inflated, but the direction is not in dispute).

New college graduates in China (×10,000) — your same-age competition grows every single year

90011001300 795 1,270 +475 (×10k) in 10 yrs — up 60% 2017201820192020202120222023202420252026E

Sources: Stanford Digital Economy Lab · Fortune 2026-04 · Ministry of Education annual bulletins / Xinhua 2025-11 · TechTimes 2026-07

01 · New Rules · That Viral Ranking

"The jobs AI eliminates first" — the original list looks like this

Measured (Anthropic 2026-03): the share of each occupation's tasks already being done by AI

Computer programmers
75%
Customer service reps
70%
Data entry clerks
67%
Medical records specialists
67%
Market research analysts
65%
Sales representatives
63%
Financial/investment analysts
57%
Software QA analysts
52%

Method: the share of an occupation's tasks "already being automated by AI" in real Claude usage data — not a forecast, a measurement. Programmers rank first: exactly the reality Mei and Shuai have to face.

The viral version · Microsoft's "AI applicability" Top 10 200K Copilot conversations

① Interpreters & translators ② Historians ③ Writers & authors ④ Service sales representatives ⑤ CNC tool programmers ⑥ Broadcast announcers & radio DJs ⑦ Customer service reps ⑧ Telemarketers ⑨ Political scientists ⑩ Mathematicians
The common thread: language and information processing — pure execution, fully digital, no physical presence required.

In the same study, barely affected

Phlebotomists, massage therapists, roofers, dishwashers, water plant operators — hands-on skill + on-site judgment: AI applicability near zero.

The China picture PKU NSD × Zhaopin

Editors/translators score highest of all occupations on the LLM impact index; customer service/operations postings fell over 2 percentage points in two years, sales/BD over 5 — and the bar keeps quietly rising.

A sedative: Microsoft published a clarification blog stating the data "does not indicate these jobs will be replaced"; Anthropic likewise notes high-exposure occupations show no systematic unemployment yet, though hiring of young workers is slowing. The rankings measure "task overlap" — what gets eliminated isn't the occupation, it's the "pure execution" slice of it. How do you stand on the surviving side? Read on.

Sources: Anthropic "Labor Market Impacts of AI" 2026-03-05 / Euronews 2026-03-14 · Microsoft Research arXiv:2507.07935 (checked line by line against official GitHub data) and clarification blog 2025-08-21 · PKU National School of Development × Zhaopin 2024-09

01 · New Rules · Now the Fire

Fire: people who can use AI are being fought over

+62%
Average salary premium for jobs requiring AI skills worldwide (the 2024 edition said 25% — it more than doubled in two years)
PwC AI Jobs Barometer 2026, analyzing 1B+ job ads across 27 countries
8×
Jobs requiring AI skills grew (69%) at eight times the overall market (9%); AI Engineer ranks No. 1 on LinkedIn's 2026 fastest-growing US jobs
PwC 2026 · LinkedIn/Forbes 2026-01
+74.1%
China's 2025 year-on-year growth in average monthly new AI-related postings (just 8.5% in 2023); AI roles pay about 2.6× ordinary roles
BOSS Zhipin "2026 Talent Trends Report" 2026-01

Job posting growth compared (PwC, 1B+ ads across 27 countries)

Jobs requiring AI skills
+69%
Overall job market
+9%

An 8× speed gap — "tailwind" isn't a metaphor here, it's data.

Read the ice and the fire together: AI hasn't reduced work — it has re-sorted it. "Execution-type" entry jobs are disappearing; "people who can direct AI" are getting more expensive. Your move is not to dodge AI, but to stand on the right side of the dividing line.

Sources: PwC AI Jobs Barometer 2026 official press release · WEF citing LinkedIn data 2026-01 · Xinhua / China News Service 2026-01-23

01 · New Rules · Both Sides of the Table Have Changed

Your résumé's first reader may not be human

The recruiter's AI

61% of employers screen résumés with AI, and 96% of recruiting professionals use AI in at least one step; AI-led first-round interviews rose from 10% to 34% in two years — more and more, the one scoring you across the keyboard is an algorithm.

The candidate's AI

81% of job-seekers already use or plan to use AI in their search; the most common use isn't "ghostwriting" but ATS compatibility checks (64%). Job-seekers who don't use AI are already the minority.

Two corollaries: ① Your résumé must first pass the machine gate — keywords, structure, parseability; artsy layouts cost you points. ② When 81% of candidates use AI, "using AI" is no longer an edge — "using it better than the rest" is — and that's exactly what today teaches.

Sources: TestGorilla 2025 · Resume Now / The Interview Guys 2026 · HireVue 2026 Global AI in Hiring Report · Resume Genius 2026 · Kickresume data

01 · New Rules · In One Sentence
AI levels the gap in "execution skills" —
and widens the gap in "judgment + portfolio + using AI well".
Execution (writing code, building spreadsheets, making decks) keeps getting cheaper with AI; judgment (what to build, is it good, why) and work you can actually show keep getting more expensive. The next five chapters teach you to put every chip on the expensive side.
02

The Method: an AI Job-Search Workflow

Remember Session 1's "advanced workflow" — knowledge base, brief, iterate, review, ship? Your job search is your first real project. Run the exact same playbook.

02 · The Method · Step 1

Knowledge base: make the target industry your home turf

> Here are 100 JDs for "sell-side equity research analyst" I collected (attached).
Help me: 1) extract the 15 most frequent requirements, ranked by frequency;
2) split them into "hard gates" (certificates/degrees) vs "fast-learnable skills";
3) write the output to knowledge-base/jd-analysis.md
✓ Top 15 high-frequency requirements generated:
  #1 Financial modeling (mentioned in 87/100)
  #2 Industry research frameworks (79/100)
  #3 Python / data processing (61/100, up sharply from last year)…

Mine 100 JDs

Don't guess what the job wants — let AI count it. The high-frequency requirements are your study syllabus, and year-over-year comparison even shows where the industry is heading.

Build target-company dossiers

One document per target company: business lines, latest earnings highlights, executives' public remarks, campus-hiring process and past questions — your ammo depot for the night before the interview.

Let the intel update itself

cron + Agent watches your target companies daily (news, filings, recruiting accounts); every change flows into the knowledge base automatically — Session 2's scheduled tasks, working for you for the first time.

02 · The Method · Step 2

Positioning brief: one page on "who I am, where I'm going"

What I have

Courses, projects, internships, skills, certificates — dump it all on the AI and have it re-sort everything in the recruiter's language: which are assets, which are merely experiences.

What I want

Industry × role × city × bottom lines (pay/overtime/growth). Only once written down do you notice how many "wants" fight each other — make the trade-offs before applying, not at the offer stage.

Gap list

Match "what I have" against the high-frequency JD requirements and have AI produce a gap list plus a catch-up plan ranked by ROI: what can be closed in two weeks (tools, question banks), and what not to chase (gatekeeping certificates).

This is the job-search version of the "goals & constraints spec": feed it first into every later session (résumé edits, mock interviews, cover letters) — the deeper AI knows you, the sharper its help.
02 · The Method · Step 3

Résumé engineering: one résumé per job, robots love it too

> Rewrite my résumé against this JD (résumé and positioning brief are in the project).
Rules: 1) annotate the reason for every change; 2) quantify every result;
3) use the JD's own wording without keyword stuffing; 4) never invent any experience.
✓ 11 changes made. Example:
  Before: "Helped run the student club's social media account"
  After: "Ran the account solo for 8 months, published 32 posts,
        top post 12K reads, followers +40%"
  Reason: JD item 3 asks for "content production skills"; quantified = verifiable

One résumé per job

A generic résumé is an average-score résumé. Have AI re-tune the emphasis and keywords for each JD — 10 minutes per version, a luxury only the AI era makes possible.

Quantify results (STAR)

"Participated / responsible for / assisted" are dead words. For every experience, force yourself to answer: how many, how fast, up by how much — AI is great at pressing, so make it your coach.

⚠️ Red line

Polishing ≠ fabricating: every number must survive a background check; never list what you didn't do. Every sentence AI writes, you must be able to defend through three levels of follow-up questions.

02 · The Method · Step 4 · The Most Important Slide Today

Portfolio > Certificates: the hard currency of the AI era

87%
Share of tech recruiters who look at candidates' GitHub (industry survey figures) — Session 2's "GitHub = the new résumé" is real
SOLTECH and other industry survey roundups
73%
Share of hiring managers who say a strong portfolio beats a perfect résumé (industry survey figures)
Cited from Stack Overflow survey figures
3 > 10
3 well-polished real projects beat 10 toy projects — recruiters read GitHub as a "living work sample"
A common refrain in recruiter interviews
Why is work worth more in the AI era? Because a résumé can be AI-generated, but work can't be faked — it carries timestamps (commit history), process (README, iteration logs), and can be verified on the spot. Certificates prove you "studied"; work proves you "shipped". Each case-study chapter will build one killer project.

Note: the 87%/73% figures come from industry blog survey roundups, not primary academic reports — the magnitude is credible; treat exact values as indicative

02 · The Method · Step 5

Application funnel: manage applications like a sales pipeline

Company / RoleStatusDeadlineNext step
Brokerage · ER internTest passed07-20Interview: prep industry questions
Fund · Research asst.Applied07-18Unread 3 days → find a referral
Bank · Fintech traineeRejected—Have AI post-mortem vs the JD

One table rules them all

Where you applied, current status, deadlines, next action — a spreadsheet, or let an Agent keep it; cron pings you every morning with today's deadlines.

Find the bottleneck with the funnel

Review conversion weekly: application→test low? Fix the résumé; test→interview low? Drill problems; interview→offer low? Practice interviews. The data tells you which stage to repair — no need for blind anxiety.

02 · The Method · Step 6

Mock interviews: an on-call interviewer who shows no mercy

> You are a stern senior interviewer at a brokerage research institute.
Dig into my résumé (in the project) section by section;
after every answer, press me with two follow-ups, and at the end give:
1) per-question feedback 2) my three verbal tics 3) an improvement list
Interviewer: you wrote "independently produced an industry report" —
  what were the data sources? How did you define the scope?
  If I say your valuation is 30% too high, how do you defend it?

Three interview types, drilled separately

Behavioral: STAR deep-dive follow-ups; technical: questions set from the JD; stress: have AI play the "hard-to-please" interviewer — you stay calm in the room because you've met the hard questions before.

Record → AI review

Record live mocks or self-Q&A, transcribe, hand it to AI: verbal tics, broken logic, pacing — Session 2's video-transcription exercise, put to work here.

The information-asymmetry weapon

The night before: have AI use the company knowledge base to write 10 "questions this company is most likely to ask me" — most of your rivals never take this step.

02 · The Method · Step 7

Negotiating the offer: don't walk the last mile unarmed

Check the market first

Have AI compile the role's salary band (platform data, peer disclosures, per-capita pay in annual reports), and negotiate with a range in hand instead of being anchored to HR's first number.

Rehearse the negotiation

Have AI play HR for three rounds: "our pay bands are standardized", "new grads have no room to negotiate" — a comeback for every script, and the cost of blowing up paid in rehearsal.

Multi-offer decision matrix

Pay, growth, platform, city, overtime — have AI build the scoring matrix, with weights you set yourself (back to the positioning brief). AI supplies structure; the human makes the choice.

The method in one line, seven steps: knowledge base to scout the field → positioning brief to lock the target → résumé to pass the machine gate → work to win the human gate → funnel to track progress → mock interviews to build nerve → data as armor when talking money. Now watch two majors run the full play.
03

Case One: Mei, Finance

Finance major, junior year. Target: sell-side equity research / investment banking. The traditional path (internship referrals + certificate stacking) keeps getting more crowded — so Mei picks a different road: let the work do the talking.

03 · Case: Finance · The Battlefield First

The industry is changing — so is the ticket in

Wall Street has already changed

Goldman CEO Solomon: "AI can draft 95% of an S-1 in minutes — work that used to take a six-person team two weeks; the value now lies in the last 5%." Goldman's AI assistant covers all staff; JPMorgan's LLM Suite is rolled out to 250,000 employees. The junior analyst's grunt work is precisely the 95% being eaten.

Chinese brokerages are changing now

24 brokerages are deploying LLMs: CICC's "Dianjing", Guotai Junan's "Junhong Lingxi", China Securities claims +40% research productivity. Campus hiring is pivoting too: Huatai's fintech track, CITIC's "Xin-Pi Program", East Money's management trainees explicitly require LLM tech + Python — while traditional IBD and research-desk openings keep shrinking.

Mei's read: rather than queue on a shrinking old track, prove she already is the "AI-native new-model researcher" — the direction job requirements are moving is the direction to differentiate.

Sources: Fortune 2025-01-17 (Solomon's own words) · American Banker · The Digital Banker · Cailian Press · 21jingji 2026-03-15 (campus-hiring requirement examples)

03 · Case: Finance · Weeks 1–2

Mei's foundation: a self-updating research knowledge base

# Two cron jobs on Mei's server:
30 15 * * 1-5  ~/fetch-market.sh
# ↑ after each close, pull quotes + sector news into the base
0 8 * * *  claude -p "Read yesterday's data and write a one-page
  morning brief: the 3 major indexes, moves in the consumer names
  I track, 3 headlines and their impact" >> ~/briefs/$(date +%F).md
# ↑ every day at 8:00, the brief shows up on her phone

Pick one industry, go deep

Don't chase the whole market; pick an industry you have a feel for (Mei chose consumer). The base holds: leaders' financials, industry data sources, and the analytical frameworks from published sell-side reports.

Session 1's exercises, fully assembled

Exercise 1 (data infrastructure) + Exercise 2 (investment analysis) bolted together are exactly this system — what was homework then is a job-hunting weapon now.

Two weeks later

Talking shop with classmates, Mei quotes the latest numbers cold — not because her memory is great, but because her system reads the market for her every day.

03 · Case: Finance · Weeks 3–4 · The Killer Project

The killer project: a report pipeline she can demo live

① Data

The pipeline auto-pulls the target company's financials and industry data

② Analysis

AI runs financial analysis + comparable-company valuation on a sell-side framework

③ Draft

Charts + prose auto-generate a first draft; Mei owns the views and revisions

④ Publish

Pipeline code on GitHub, final reports on WeChat / Zhihu

Output: 1 deep dive + 1 weekly tracker

One 30-page deep-dive report as the anchor, then a 2-page tracking brief every week — a continuously updated body of work proves systematic ability better than a one-off magnum opus.

Why this opens doors

Asked "can you use AI?", other candidates say "I use ChatGPT". Mei hands over a link: "Here's my pipeline — data as of this morning." In that moment, she's no longer in the same category as the rest.

Honest labeling: the report's front page states "data and first draft generated by my own AI pipeline; views and revisions are mine" — that line isn't a disclaimer, it's a statement of capability.
03 · Case: Finance · Weeks 5–6

What to write on the résumé, how to answer in the room

Résumé wording (before / after)

❌ "Proficient with AI tools; strong interest in industry research"
✅ "Built an automated research pipeline (data ingestion → financial analysis → report generation) covering 12 consumer companies; 90 daily market briefs; deep-dive report read XX times" — every number clicks through and verifies.

Technical-round AI sparring list

How the three financial statements tie together, defending DCF assumptions under attack, the evidence behind an industry-cycle call — have AI grill you three levels deep in the target brokerage's style; then use the company knowledge base to predict questions: recent report views, the chief analyst's public calls.

Mei's highlight in the interview wasn't reciting concepts. Pressed on valuation, she said: "Move this assumption one point in my model and the target price moves 8% — which is why I made sensitivity analysis a default output of the pipeline." That's the line the interviewer remembered.
04

Case Two: Shuai, Software

CS major, junior year. Target: AI application / Agent engineer. Junior programmer jobs are shrinking, but he's aiming at the fastest-expanding slice — using work to prove he's already inside the door.

04 · Case: Software · The Battlefield First

The coldest winter, the hottest track

−20%
Employment drop for software developers aged 22–25 from the 2022 peak; new-grad software postings down 28% — traditional junior coders are the hardest hit
Stanford 2025-08 · industry hiring-market reports 2026
1,205 / 2,559
Of ByteDance's 2026 campus-hiring roles, nearly half are AI-related; "AI Agent Application Engineer" is a brand-new job title; AI roles top 60% of Alibaba's campus openings
Securities Times · Yicai 2026
4M
McKinsey's projected 2030 gap in China's AI talent (demand: 6M) — the winter is structural, and so are the tropics
McKinsey, cited in 2026 campus-hiring coverage
The JD has already been rewritten. A typical 2026 junior role asks for: "familiarity with AI-assisted development workflows, the ability to review and verify AI-generated code, and fluency in at least two AI coding tools". 84% of developers already use AI coding routinely (Stack Overflow survey figures). What Shuai must prove isn't "I can write code" — it's "I can write code with AI in harness".

Sources: Stanford Digital Economy Lab · Final Round AI 2026 · Securities Times · Yicai · daily.dev 2026

04 · Case: Software · Weeks 1–2

Shuai's GitHub: three real projects, not ten toys

Project 1 · Already built

The Hermes deployed in Session 2 plus his own accumulated skill packs (dorm-repair bot, timetable reminders) — organized into a standalone repo, with a README covering architecture and pitfalls. The tools you've used are themselves project material.

Project 2 · From the exercises

Session 1's Exercise-1 data pipeline, upgraded into a full project: scraping + cleaning + API + a one-page dashboard, with unit tests and CI — showing engineering discipline, not just features.

Project 3 · Contributed

1–2 merged PRs to open-source projects he actually uses (OpenClaw / the Hermes ecosystem) — even doc fixes count. Recognition from a stranger maintainer beats ten thousand lines of self-praise.

Standard kit for every repo: a proper README (what it is / how to run it / screenshots), a clean commit history (in the AI era it's the recording of your work process), and one green CI check. Everything Session 2 taught is cashing out here.
04 · Case: Software · Weeks 3–4 · The Killer Project

The killer project: an Agent app from zero to production

# Shuai's project: the "Job-Funnel Agent" — built on his own pain point
# Features: application-deadline alerts / status tracking / pre-interview
#       auto-summary of the company knowledge base, pushed to Telegram
$ git log --oneline | head -4
e7a12f9 Add pre-interview company brief push (with tests)
b3c90d1 Fix deadline timezone bug, add regression test
a1f4e20 Wire up Telegram notifications
9d02c11 Initial version: funnel data model + CRUD
# Ran the full Session 1 Chapter 08 workflow:
# knowledge base → brief → code with tests → commit → review → ship

Why this topic

It solves his own real pain point (he really is job-hunting), so the requirements, iterations, and retrospectives are all real — one look and the interviewer knows it's no template project.

Demo-able in the interview

He opens Telegram on his phone: "These are the three deadlines it flagged for me this morning." Then the architecture diagram and the tech choices — demo + architecture + trade-offs, the interview triple strike.

Compounding for free

The Agent is itself helping him land a job — the project and the search accelerate each other. That's topic selection at its finest.

04 · Case: Software · Weeks 5–6

Algorithms & system design: AI as sparring partner, not hired gun

The right way to grind problems

Stuck? Don't peek at the answer — have AI give hints, not solutions ("only hint at the data-structure direction"); once solved, have it generate variant problems to test whether you understood or memorized.

System design simulation

Have AI play interviewer: "design a timetable-reminder system", pressing step by step on concurrency, storage, degradation — Shuai's Agent project is ready-made material, turning recital into a conversation about his own architecture.

⚠️ One hard red line

No proxies in online assessments. Big-tech anti-cheat keeps upgrading, and one blacklist flag follows you far beyond a single company — use AI to raise your real level, not to fake one.

Asked in an interview "how would you solve this with AI?", the right answer isn't embarrassment — it's showing the workflow: "I'd have it enumerate the edge cases first, write the core logic myself, then have it review — exactly like every commit in my GitHub."
04 · Case: Software · Wrapping Up

"An engineer who directs AI" — how to write it without sounding hollow

Résumé wording (before / after)

❌ "Familiar with ChatGPT, Claude and other AI tools"
✅ "Independently delivered a Job-Funnel Agent via an AI-pairing + test-driven workflow (Python/FastAPI, 34 commits, 85% test coverage), plus 2 merged PRs to the open-source project Hermes" — tools are worthless; what you deliver with the tools is what's worth money.

Interview narrative (three sentences)

What I wrote (core logic and architecture decisions), what AI wrote (boilerplate and first-draft test cases), and how I made sure AI's code was right (review + tests + staged rollout) — those three sentences are the model answer to "can review and verify AI-generated code" in 2026 JDs.

The shared core of both cases: Mei and Shuai aren't selling "I can use AI" — they're selling "I built something with AI" — something verifiable, demonstrable, and able to survive cross-examination.
05

Red Lines & Mindset

AI adds leverage to your job search — and leverage amplifies both your equity and your losses. Three red lines to hold the floor, one mindset to hold the direction.

05 · Red Lines & Mindset · Do Not Cross

Three red lines — cross one, lose everything

① No résumé fraud

AI makes inventing stories easy — and makes background checks easy too. Numbers, titles, dates: one lookup and you're caught — and flagged candidates land on industry-shared blacklists.

② No proxies in tests or interviews

AI proxy-taking = cheating, and anti-cheat systems (camera behavior analysis, code fingerprinting) are upgrading with AI too. You'd be competing with AI at cheating. You can't win.

③ Full candor when asked

"How much of this work was AI?" — the model answer is to open the workflow and walk through it. Owning your usage is a plus; concealing it is an instant veto.

Interviewers can smell "AI flavor" now: ornate but hollow adjectives, projects with no details, collapse after two follow-ups. AI content you haven't digested scores worse than using no AI at all.
05 · Red Lines & Mindset · One Mindset
AI is an amplifier:
if you have work, it amplifies the work;
if all you have is blankness, it amplifies the blankness.
So the order cannot be reversed: first use AI to make something real (however small), then use AI to package and spread it. A portfolio is a compounding asset — Session 1 said "GitHub = the new résumé"; by now you should see it isn't the résumé's attachment. It is the résumé.
06

The 30-Day Action Checklist

Week 1 · Foundation

□ Build the knowledge base: mine 50–100 target JDs
□ Write the positioning brief (one page)
□ Gap list + catch-up plan
□ Get the cron intel station running

Week 2 · Ammunition

□ Start the killer project (report pipeline / Agent app)
□ Résumé v1 + three rounds of AI polish
□ Tidy the GitHub repos + READMEs

Week 3 · Open Fire

□ Application funnel live; apply to 3–5 a day
□ One AI mock interview per day
□ Ship v1 of the killer project

Week 4 · Iterate

□ Post-mortem on funnel data: fix the weakest stage
□ Update the project weekly
□ Salary research + negotiation rehearsal

This checklist is itself a project — drive it with Session 1 Chapter 08's workflow: git commit your job-search repo every night, update your own CLAUDE.md every week. The job search is your first real delivery.

One Last Slide

Opportunity doesn't go first to the prepared —
it goes first to those who've already built something.

Session 1 said AI gave ordinary people wings. Now you know: wings aren't for waiting on the wind — start the Week 1 checklist tonight.

GitHub