Stop drowning in CVs.
The bot screens them for you.
I train a bot on what my company does, who my clients are, the culture, and the values I want in a person. Skills matter less to me, so it weighs fit first. It then reads every CV and application I receive, scores each one against my criteria, and builds a shortlist that says clearly why each person is in or out. For the ones who did not make the cut, it pulls their details and replies to them kindly, because people made the effort to apply. I interview only the top two or three, instead of reading thirty CVs and wasting time on poor fits.
Hiring used to mean reading thirty CVs and interviewing the wrong people.
A single open role can pull in dozens of applications, and almost all of them are a no. So you spend hours reading CVs, you miss the small inconsistencies that matter, and you still end up interviewing people who were never a fit. Worse, most of the applicants never hear back at all, which is both unkind and bad for your name. The fix is not to hire faster, it is to pre-screen properly before a single interview. A bot trained on your culture and values does exactly that. Here is who it is for, what goes wrong without it, how it works, and what you get back.
Who it’s for
Anyone who hires and dreads the CV pile. Founders, agency owners, small teams, and anyone staffing a role who wants the right person, not just the most qualified one on paper. It fits you best if you care more about culture and values than a perfect skills checklist, because that is exactly what the bot is trained to weigh.
What goes wrong
Manual screening is slow, tiring, and biased by the tenth CV. You skim, you miss inconsistencies, and you interview people who look good on paper but do not fit the team. Then most applicants get no reply at all. You burn a day reading CVs and still end up with a shortlist built on a tired skim, not a real judgement.
How the machine works
You train the bot on what your company does, your clients, your culture, and your values. It reads every application, scores each one against your criteria, and builds a shortlist that justifies why each person is in or out. It then replies kindly to everyone who did not make the cut. You only interview the top two or three.
What you get back
Hours back on every hire, a shortlist you can trust, and a hiring process that treats applicants like people. The bot is accurate, it can make the occasional mistake, but it spots things you never would. Fewer wasted interviews, better hires, and time saved that compounds across a whole year of hiring.
I was tired of reading CVs and interviewing the wrong people.
Hiring was the part of running a business I quietly dreaded. A single role would bring in thirty or forty applications, and reading them all properly took the better part of a day. By the tenth CV my attention was gone, and I knew I was skimming. The honest truth is that a tired human reading the thirtieth CV is not making a fair decision, and I was making important calls on a tired skim.
What bothered me most was that the reading was not even where my judgement mattered. My judgement is about fit, whether a person shares the values of the team and would do well with my clients. Skills matter less to me than most people think, because skills can be taught and the right attitude usually cannot. The CV reading was just a tax I paid to get to the few people actually worth a conversation. So I asked a simple question. What if a bot did the reading and the first cut, and I only met the people who genuinely fit?
I built a small machine that does the whole pre-screen end to end. First I train it on my own business, what my company does, who my clients are, the culture, and the exact values and attributes I want in a person. Then it ingests every CV and application I receive and scores each one against those criteria. One brief, one bar, one shortlist that the bot builds for me instead of me reading every page myself.
The part that genuinely surprised me is how it justifies every decision. It does not just hand me a shortlist, it tells me why each person made the cut or did not. It spots inconsistencies in a CV, gaps that do not add up, claims that contradict each other, and it flags them in plain language. It even catches things I never would have noticed on my own. It is accurate, and yes it can make the occasional mistake, but it is a far better first reader than a tired human at CV number thirty.
The numbers are modest and easy to check. Say a single hire used to cost me eight hours of reading CVs and five wasted interviews. The bot hands me back most of that, call it six saved hours and four interviews I no longer sit through. At a conservative fifty dollars an hour for my time, that is around three hundred dollars saved on one hire, before counting the interviews. Hire a handful of people across a year and that is a few thousand dollars of my time back, plus better hires who lift the whole team’s output. Saved time and better people both compound.
Proof point: I have broken down how I run my businesses on autopilot and the time these systems give me back on YouTube, in a day in my life running automated businesses and the wider picture in my 28 income streams breakdown, so the conservative numbers on this page are checkable.
Three moves that turn a CV pile into a shortlist you can trust
What made this work was separating the two halves of hiring that everyone glues together. There is the judgement, deciding who actually fits your team, and there is the labour, reading every page and chasing every applicant. Most people do both by hand and burn out on the second half, then rush the first. The framework here keeps your judgement in the loop and hands the labour to a bot.
Train the bot on your culture and values
The whole loop starts with training. Instead of giving the bot a generic skills checklist, you teach it your business, what you do, who your clients are, the culture, and the exact values and attributes you want in a person. This is the part that makes the screening yours, because the bot now judges by your bar, not a stock template. Skills matter, but fit matters more, and the bot weighs fit the way you would. Get this brief right once and every shortlist after it reflects your real standards. Without this, you are back to keyword matching, which is exactly the lazy screening that lets the wrong people through.
Let it read and score every applicant
Once trained, the bot ingests every CV and application and reads each one in full, with the same care on the thirtieth as on the first. It scores each person against your criteria and, crucially, it justifies the score in plain language, why this person is a strong fit or why they are not. It spots inconsistencies, unexplained gaps, and claims that contradict each other, and it flags them. This is where the bot beats a tired human, because it never skims and never gets bored. The reader is perfect and patient, so the first cut is fair to everyone in the pile.
Answer everyone, interview only the few
The last move is the one almost every company skips, and it is the one that matters for your name. For everyone who did not make the cut, the bot pulls their details and sends a kind, personal reply, because people made the effort to apply and the least you can do is answer. Then it hands you a justified shortlist of the top two or three, and those are the only people you meet. You spend your interview time on real fits, the rejected applicants leave with respect for you, and you never sit through a wasted interview again.
Once those three moves are in place, hiring stops being a dreaded day of reading and starts behaving like a small machine that hands you the right people. Training the bot is the seed. Reading and scoring every applicant fairly is the engine. Answering everyone and interviewing only the few is the part that gives you your time and your reputation back at once.
Before the bot
- Half a day reading thirty CVs, attention gone by number ten
- Missed inconsistencies and gaps that a tired skim glides past
- Interviewed five people who were never a fit for the team
- Most applicants heard nothing back, which looked bad on me
- Judged on skills on paper, not on real fit with my values
After the bot
- Bot reads every application in full, none skimmed or skipped
- Scores each one against my culture and values, not a checklist
- Justifies why each person is in or out, in plain language
- Replies kindly to everyone who did not make the cut
- I interview only the top two or three real fits
Prompt 1: turn your company into a screening brief
Before the bot can judge anyone, it needs to know your business the way you do. The biggest mistake is feeding it a generic job description and a skills list. Use this prompt to turn what your company actually is into a screening brief built on culture and values.
Company and values brief builder
Act as a hiring strategist. I am building an automatic CV screener that judges applicants on fit with my company, not just skills on paper. What my company does: [describe it in two or three sentences]. Who my clients are: [describe them]. The culture of my team: [describe how you work and what you value]. The attributes I want in a person: [list the values and traits that matter most to you]. Turn this into a clear screening brief the bot can use to judge every applicant. Define what a strong fit looks like, what a weak fit looks like, the red flags that should count against someone, and how much weight to give values versus skills. Keep it plain and specific, so the bot judges by my bar and not a generic template.
The output of this prompt is the brief the screener reads on every applicant forever. Get this right once and every shortlist after it reflects your real standards instead of a keyword match.
Prompt 2: score one applicant and justify the call
The score is only useful if it comes with a reason you can trust. To do that, the bot scores against your brief and explains itself in plain language. Use this prompt as the scoring step the bot runs on every single CV in the pile.
Applicant scorer with justification
Act as a careful first-round screener using my screening brief. I will give you the brief and one applicant's CV and application. My screening brief: [paste it]. The applicant's CV and application: [paste it]. Score this applicant from 0 to 100 on fit with my brief. Then justify the score in plain language: the two or three strongest reasons they fit, the two or three reasons they may not, and any inconsistencies, unexplained gaps, or claims that contradict each other. Flag anything that looks off, even small things a tired reader would miss. End with a clear in or out recommendation and one line on why.
Run this on every applicant and the bot builds a scored, justified pile instead of a pile of pages. You read the reasons, not the CVs, and you can see exactly why each call was made.
The 3-minute overview of how this works
Before the build steps, watch this short overview. It’s the exact video from the Automations Made Easy page, and it walks through the mechanics behind machines like this one. 1,000+ students have used these mechanics to save two hours a day, with zero coding.
Want to learn the mechanics behind quiet, time-saving automations?
I teach the same mechanics that power this CV screener inside Automations Made Easy. 1,000+ students have used these mechanics to save two hours a day and take the dull work off their plate. No coding required.
Week one: one hire, screened without you reading a CV.
Most people think hiring automation means cold, robotic screening. It is the opposite. The bot does the tiring reading so your judgement gets the time it deserves. In week one you train the bot on your business, point it at your first batch of applications, and watch it hand you a justified shortlist while every applicant gets a reply. You read reasons, not CVs.
Week one looks like this. On Monday you write the brief, what your company does, your clients, your culture, and the values you want, and the bot turns it into a screening standard. The applications come in, and instead of reading thirty CVs you let the bot read them. By Friday it hands you a shortlist of the top two or three, each with a clear reason they are in, plus the inconsistencies it caught. Everyone who did not make the cut has already had a kind reply. You spend your week’s hiring time on two real conversations, not thirty pages.
The point of the first week is not the money. The point is to confirm the bot judges by your bar, that the reasons it gives match how you actually think, and that the replies to the rest sound like you. Once that is locked, every hire after it is the same machine running on its own.
From there the maths is simple and conservative. Say each hire used to cost eight hours of reading and a stack of wasted interviews, and the bot gives back six of those hours. At fifty dollars an hour that is three hundred dollars of your time per hire, before the interviews you skip. Hire a handful of people across a year and that is a few thousand dollars of your time back, plus better hires who lift the team’s output for years. Saved hours and better people both compound.
All of this runs while you work on something else. The bot reads, scores, justifies, shortlists, and answers the rest. You step in only for the two or three conversations that actually decide the hire, and you walk into each one already knowing why this person is in front of you.
Prompt 3: build the justified shortlist
Once every applicant is scored, the bot assembles the few worth your time into a shortlist that shows the reasoning, not just the names. Use this prompt as the shortlist step the bot runs once all applicants are scored.
Justified shortlist assembler
Act as my hiring assistant. Below are all the scored applicants for one role, each with a score, the reasons for and against, and any flags. The scored applicants: [paste the scored list]. How many to shortlist: [usually two or three]. Build me a shortlist of the top fits. For each shortlisted person, give a short summary of why they made the cut, what to probe in the interview, and any flag to confirm. Then give me a short list of the strongest near misses with one line each on why they did not quite make it, in case I want to reconsider. Keep it tight and decision-ready.
The output is a shortlist you can act on in minutes, with the reasoning attached. You walk into interviews already knowing who you are meeting and exactly what to ask each of them.
Prompt 4: write the kind reply to those who did not make it
The applicants who did not make the cut still made the effort, and answering them is the right thing to do. Use this prompt to draft a warm, personal rejection the bot can send to each one, so nobody is left in silence.
Kind rejection writer
Act as a thoughtful hiring manager writing to an applicant who did not make the shortlist. I want to answer everyone who applied, because they made the effort and silence is unkind. The applicant's name: [name]. The role they applied for: [role]. One genuine, specific thing worth acknowledging from their application: [detail]. Write a short, warm, honest reply that thanks them for applying, acknowledges that one specific thing so it does not feel like a form letter, lets them know they were not selected this time, and wishes them well. Keep it human and respectful, no corporate filler, no false promises. First person, plain English.
Wire this into the screener and every rejected applicant gets a real reply, automatically. It costs you nothing, it protects your name, and it treats people the way you would want to be treated.
The exact build, step by step
Train the bot on your company, culture and values
Start by teaching the bot who you are. You give it what your company does, who your clients are, how your team works, and the exact values and attributes you want in a person. This is the brief that turns generic screening into your screening. You decide how much weight goes to fit versus skills, and for most teams fit wins, because skills can be taught and the right attitude usually cannot. Do this once and the bot now judges every applicant by your bar instead of a stock checklist, which is the whole reason the shortlist ends up being people you actually want to meet.
Feed it every CV and application you receive
Next, the bot ingests every CV and application for the role, all of them, in one pass. There is no triage by you, no skimming, no setting some aside for later and forgetting them. The bot reads the thirtieth application with the same care as the first, which is something a tired human simply cannot do. This is the step that removes the bottleneck, because the reading was always the expensive part. Thirty CVs or three hundred, the bot reads every page in full, so no good applicant slips through because you ran out of attention.
Score each applicant against your criteria
Now the bot judges. It scores each applicant against the brief you set and gives a clear number plus a plain-language reason for it. It names the strengths, names the concerns, and flags inconsistencies, unexplained gaps, and claims that do not add up. This is where it beats a human reader, because it catches the small things a tired skim glides past, and it sometimes catches things you never would have. The score is never a black box. Every number comes with a why, so you trust the call and can overrule it when you disagree.
Build the justified shortlist, in or out
With every applicant scored, the bot assembles the shortlist. It does not just rank names, it shows you who made the cut and exactly why, and who did not and exactly why. For the people who are in, it tells you what to probe in the interview. For the people who are out, it gives the honest reason in a line. You get a decision-ready shortlist of the top two or three, plus the strongest near misses in case you want a second look. The whole pile becomes a short, reasoned list you can act on in minutes.
Auto-reply kindly to everyone who did not make it
Here is the step almost every company skips. For every applicant who did not make the cut, the bot pulls their name and contact details and sends a kind, personal reply. People made the effort to apply, and the least we can do is answer, yet so many applications go unanswered and I think that is wrong. The reply is warm and specific, not a cold form letter, so the person leaves with respect for you instead of resentment. It costs you nothing, it happens automatically, and it quietly protects your name with every applicant you turn down.
Interview only the top two or three
Final piece. You step in for the part that actually needs you, the conversations. Instead of interviewing thirty people and wasting time on poor fits, you meet only the top two or three the bot shortlisted, and you walk into each one already knowing why they are there and what to ask. This is where the time saving lands. The dull reading is gone, the wasted interviews are gone, and your attention goes only to the real decisions. Each hire saves you a stack of hours, and across a year of hiring those hours and better hires add up to real money.
Bot trained
You teach it your company, clients, culture, and values once, and it judges every applicant by your bar.
Read and scored
It reads every CV in full and scores each one against your criteria, with a plain reason for the number.
Shortlist built
It hands you the top two or three with a clear why in and why out, plus the inconsistencies it caught.
Rest answered
Everyone who did not make the cut gets a kind, personal reply, and you interview only the few who fit.
Build this CV screener inside the same playbook 1,000+ students use
Automations Made Easy teaches the mechanics behind time-saving bots like this one. Step by step, no code, plain English. Save two hours a day and hand the dull reading to a bot that judges by your bar.
The six months after I switched it on
Here is the shape of my time saved over the first six months after I turned the screener on, counted in dollars of my own time at a conservative fifty an hour. It is modest in the early months when I hired less, and climbs as more roles ran through the bot, because that is how the saving actually compounds.
Monthly value of time saved by the CV screener, at $50 an hour
Three things matter on this chart. The line climbs as more roles run through the bot, not in a spike. The value is time saved on reading and wasted interviews, not a magic revenue number. And every one of those months happens while the bot does the reading, the scoring, and the replies for you, so your time goes only to the hires that count.
What other students built
I teach the simple skills behind machines like this in Automations Made Easy. Students who built their own version sent back what changed in their first month.
“I used to lose a full day to every open role. Now the bot hands me three names with reasons, and I interview three people instead of thirty. It even caught a CV gap I would have read straight past.”
“Training it on our values instead of a skills list changed everything. The shortlist is finally people who actually fit the team, not just the most polished CVs in the pile.”
“The reply to rejected applicants is the part I did not expect to love. Every person who applies now hears back kindly, and a few have thanked me for it. That never happened before.”
“It is accurate and it is honest about its reasons, so I trust it and overrule it when I disagree. The hours it has given me back across a year of hiring are real money.”
What’s inside Automations Made Easy
AME isn’t a library of pre-built automations. Every business is slightly different. What’s reusable across all of them is the underlying mechanics: how to set up little machines that listen, write, and follow up while you sleep, and how to wire the pieces together without writing code.
The program walks you through six modules: The Right Tools (the cost-effective, no-code stack I actually use), Task Selection Mastery (which automations are worth building first), Design Secrets (mapping an automation before you build it), Zero to Hero (complete beginner to confident automator), Real-World Application (we build a full automation together, end to end), and Monetization Mastery (turn the skill into a side-business).
It also includes done-for-you templates you import in two clicks, over-the-shoulder training videos, and the same playbook 1,000+ students have used to save two hours a day. No coding required. If you can copy and paste, you can build this.
The automatic CV screener: common questions
Pulled from what readers and Automations Made Easy students ask most.
Do I need to be a developer to set this up?
No. The screening is an AI workflow you set up once: you write a brief about your company and values, the scoring and justification are prompts the bot follows on every CV, and the replies are a template the bot personalises. You point it at your applications, set your bar, and let it run. The skills you need are knowing what a good fit looks like for your team and shaping the brief, which is exactly what Automations Made Easy teaches.
Will it judge on real fit, or just match keywords on a CV?
It judges on fit, because you train it on your culture and the values you want, not a keyword list. The bot reads each application against that brief, weighs fit ahead of skills if that is what you tell it, and justifies every call in plain language. That is the whole point, it screens the way you would on your best day, instead of the lazy keyword matching that lets the wrong people through.
Can it really spot inconsistencies I would miss?
Yes, and this surprises people most. Because the bot reads every CV in full with the same care, it catches gaps that do not add up, claims that contradict each other, and small red flags a tired human glides past at CV number thirty. It flags them in plain language so you can confirm them in the interview. It is a far better first reader than an exhausted human, and it sometimes catches things you genuinely never would have.
Is it accurate, or will it reject good people by mistake?
It is accurate, and it can make the occasional mistake, just like a human screener can. The difference is that every decision comes with a reason, so nothing is a black box. You can read the why, overrule it when you disagree, and ask it to surface the strongest near misses for a second look. You stay the final judge, the bot just does the heavy reading and hands you a reasoned starting point.
Why bother replying to applicants who did not make the cut?
Because people made the effort to apply, and the least we can do is answer. So many applications go unanswered, and I think that is wrong, both for the person and for your name. The bot pulls each rejected applicant’s details and sends a warm, personal reply automatically, so nobody is left in silence. It costs you nothing once it is wired in, and it quietly builds goodwill with every person you turn down.
More Money Makers like this one
Built from the same handful of mechanics. Each one captures, converts, or earns money that would have walked out the door.
Run this CV screener yourself, or learn the mechanics inside Automations Made Easy.
If you want to learn the mechanics behind hiring automations like this and build your own at home, Automations Made Easy is the playbook. Step by step, no code, plain English. If you want to talk through your own brief, which values to weigh, and how to wire the replies for your specific business first, I take a small number of consulting clients each month.
€497 one-time · Lifetime access · 1,000+ students
