How can I sell, deliver, and build the email categorization system from zero?
Well, you'd find people with high email throughputs-industries where they get tons of email. Start there; everyone gets lots of email, so there's interest across industries. I've talked to big companies that say their inbox is a bottleneck; solving it by even 10% can grow the whole business by 10%. So don't make your whole business the inbox, but here's how to improve it: get three niches of people who'd benefit from easier email management, then run daily outreach-maybe ten templated Loom videos a day, using Upwork, automation, and email as keywords. Apply to jobs discussing email systems; when you solve their problem, you can quickly upsell an email categorization system (mostly templated by now). First, build lead flow; then, once you have leads, build a templated list of categories by doing the first project for a client-don't aim for perfection; just understand the flow: new email comes in, categorization AI splits it into categories (invoices, Q&A, leads, etc.). For a specific business type, categories will be consistent. Create a module (e.g., in Make or n8n) that does the categorization-use the built-in categorization node if available. Then define an action, like moving emails to a specific label and marking them red (or whatever you prefer). Once you have the template, deliver it: sign the client, kickoff call, get access to their email (they may share credentials or use 2FA), set up a mail/webhook to forward incoming emails to your Make scenario, run the template, and you're set. The TFA may expire weekly, but the mail hook keeps working. Run the system for a week, then review changes with the client and collect payment-e.g., 50% upfront, 50% after delivery. I like this because it shows the delivery process, not just 'do this'.
Josh's approach is perfect if you're not yet in the automation industry, don't have an automation business, or aren't freelancing; your only goal should be to go from zero to one as quickly as possible. Most people in Josh's situation try to jump from zero to a hundred right away, but the strategies for going from 0 to 1 are different from those needed to scale to 100. Josh is looking for a minimum viable strategy—similar to a minimum viable product—to avoid stagnation and quit, because he values feedback loops. This is the way I approach any business model in the 2020s, given how fast everything moves. Regarding your question about minimum tools and whether to focus on Upwork until you earn money: it depends on your financial situation. The quickest path from zero to one, in my experience, is to spam three methods: Upwork applications, cold emails, and community engagement. I call it spamming like a video game because, while quality matters, the law of large numbers ensures results if you send enough outreach. For Upwork, send many applications using a customized Loom video approach—record a short video saying, 'Hey, how's it going? I just saw your post for XYZ; let me show you exactly how I'd solve this.' Highlight your relevant experience (X, Y, Z) and past results. Even if you're new to Upwork, this personalized touch boosts your chances. For cold emails, use one of my offer formulas or cold email templates, then find an audience, split‑test two or three audiences, and gauge reply rates—especially positive replies. You can personalize with AI if you wish; my Nix cold email templates are available via the four‑step cold email copying system. For communities, identify groups and niches you're interested in (e.g., videography, dental clinic managers). Post hyper‑relevant content that provides value without selling immediately. For example, in a dental clinic manager community, share a strategy like 'end‑of‑insurance reactivation' that leaves voicemails about unused benefits. By consistently giving value over time, you become an authority and can start charging for your services. These three outreach methods—Upwork, cold emails, and community posting—constitute the minimum viable strategy for landing your first client.
He advises framing the email‑categorization tool as a revenue‑ or savings‑focused offer rather than an academic feature. Quantify the benefit—for example, saving a founder 30 minutes a day equals 15 hours a month; at a $400‑per‑hour founder rate that’s $6,000 of saved time. Position it as a total inbox manager, AI VA, or email assistant that directly ties to booking meetings or other revenue‑generating activities. Then package that quantified value into a simple, email‑friendly pitch that highlights the time‑ or money‑saving outcome.
Yeah, so for big builds, don't just do it all in one shot; avoid big all-encompassing systems because scope creep usually leads to a situation where you haven't clearly defined what you’ll do for the client, which is impossible to specify ahead of time, causing the client to expect something you didn’t agree to for payment, breeding resentment and harming the relationship. Instead, start with a small starter project that’s tightly scoped and agreed upon by both sides, then vibe each other out to learn what the client likes and demonstrate your aptitude—this lets you pitch more later and gives you insight into their business before committing to a massive scope. If you’re doing this for a company and need to send 10,000 depersonalized emails, think logically: using Make, first you get the leads (one op), then you iterate through the leads (n ops), generate icebreakers (another n ops), and optionally upload to Instantly (another n ops) or bulk‑upload to Google Sheets (effectively one op). Roughly, that’s about three n ops, or two n ops if you use the bulk‑upload shortcut. For 10,000 records that works out to roughly 20,000 operations, give or take. As for the Make plan, the $34‑per‑month Core plan gives you 40,000 ops, plenty of headroom; you don’t need the Pro plan unless you want better error handling, in which case the Pro plan is $62. You can start with Core and upgrade later, paying only the difference. On a personal note, I’m about twenty minutes into this video and feeling locked in; I’ve gotten more done today than in the past week because I’ve committed to stop daily posting on my main channel. My growth has slowed—my first‑24‑hour view‑to‑subscriber ratio dropped from about 15% (≈15,000 views on 100k subs) to around 5% (≈5,000 views). Comments suggest this is because my niche‑specific content has saturated its audience, and broadening the topic would attract less‑interested viewers. Elrico noted that my recent videos repeat earlier material, which may also be hurting growth, and suggested exploring other tools besides Make, like voice agents and live builds. Parker joked about throwing me on while cooking to start a riot over quitting daily, and shared ideas such as adding an automation bucket for publicly traded codes to save Coinbase money, using customer‑support headcount as an input for percentage assessments, and targeting big logos to pull in the right audience. My daily updates channel now has about 5,600 subscribers, while the main channel sits at 110,750. I’m checking follower‑count tools like Trend Hero, though I’m not sure about the daily‑limit metric. Reflecting on all this feedback, I’ve decided to stop posting daily and instead pursue a multifaceted strategy: focus on what makes me unique—my calm, low‑production‑value, high‑signal‑to‑noise conversational content—and develop a new, less‑replicable format. With my team, we’ve decided to pursue the “complete and utter uncopyable thing”: building a business with this stuff in front of everybody, doing it extraordinarily well by spending time generating leads, selling them, securing proposals, onboarding clients, fulfilling projects, and growing the company. Nobody else can replicate that live business‑building demonstration. My earlier live video of starting and selling an AI service in ten hours went viral precisely because it proved I can generate leads on camera; it’s a litmus test for knowing how to do this.
Both approaches have value, so you should do them simultaneously. If you’re planning to send 30‑40 emails a day, aim for 30 rather than 40 to stay sustainable. Start with a manageable number—20 emails per day for the first week, then increase to 30. Build systems that let you work faster: split your daily volume between two types of outreach. Send about half of the emails (15) with deep personalization and the other half (15) with a custom asset, like a sample or a strategy document. Create two or three reusable custom‑asset templates so you can quickly generate them for each prospect, and also develop two or three deep‑personalized email templates where you can swap in variables. This hybrid approach lets you showcase value up front while still tailoring each message, increasing the chances of landing a call and eventually a client.