Only good gigs reach me.
The rest never arrive.
A bot watches the boards for my keyword, reads every gig against my own rules on price, scope, and client, and lets only the well-paid, good-fit contracts through. It even drafts the reply. I stopped losing an hour or more a day to reading job descriptions.
The reading-and-sorting task that quietly eats your whole morning.
Every freelancer knows the grind. You open the boards, search your keyword, and start reading. Most gigs pay too little. Some want you on-site. Others quietly ask you to run the whole marketing strategy on top of the work. You read description after description just to reject most of them. Here is a different way. A bot watches the boards, reads each gig against rules you wrote, and only lets the good-fit, well-paid contracts reach you, with a reply already drafted. Here is who it is for, what goes wrong without it, how it works, and what you get back.
Who automatically filter freelancer contracts is for
Freelancers, consultants, and small agencies who hunt for gigs on job boards and lose real time sorting the good from the bad. Especially useful if you have clear standards on pay, scope, and client type but still read every listing by hand. If finding and qualifying gigs is the part of freelancing you hate most, this is for you.
What goes wrong without automatically filter freelancer contracts
You spend the best hour of your day reading gigs that were never a fit. Low pay, on-site demands, and bloated scope hide three paragraphs into a listing. You either skim and miss good ones, or read everything and burn out. The most valuable task in freelancing is buried under the most boring one.
How the automatically filter freelancer contracts automation works
You write your rules once. The bot watches your chosen boards for your keyword, reads each new gig, and checks it against those rules. Too cheap, it rejects. Wrong scope, it rejects. Good fit, it passes, researches the client, and drafts a reply. You set the standards once, the bot enforces them on every gig forever.
What automatically filter freelancer contracts gives back each month
About an hour to an hour and a half a day handed back, roughly seven to eight hours a week and close to 350 to 400 hours a year. Only good-fit contracts reach your inbox, each with a draft reply waiting. The most draining task in freelancing, done for you, while you do the actual work.
I was spending my best hour reading gigs I would never take.
For a long time my mornings started the same way. Open the boards, search for automation, and start reading. The trouble was never finding gigs. The trouble was that most of them were wrong for me, and I only learned that after reading the whole description. Too cheap. On-site. Asking me to handle the marketing and the positioning on top of the build. I read all of it just to say no to most of it.
That reading is the most valuable hour of a freelancer’s day and the most draining. It is also the easiest to do badly. Skim too fast and you miss a great contract. Read everything and you have no energy left for the actual work. I kept thinking the answer was more discipline, when the real answer was a rule book the machine could follow for me.
So I built a bot that does the reading. It watches the boards for my keyword, reads every new gig, and checks each one against a set of rules I wrote in plain words. If the price is below what I charge, it filters the gig out. If it demands on-site work, it filters it out. If it quietly bundles in the whole marketing strategy, it filters it out. Only the gigs that pass every rule ever reach me.
It does not stop at sorting. For the gigs that pass, the bot researches the client first. How big is the company, when was it founded. If I only want startups, I tell it the company must have been created in the last three years, and it checks. Then it drafts a short reply aimed at getting an interview, using what it learned about the gig and the client. I read the draft, tweak a line, and send.
The best part is the log. For every gig, the bot writes down what it found and why it passed or rejected the job. If I ever disagree with a call, I read the note and adjust that one rule. Sorting gigs by hand used to eat about an hour to an hour and a half a day. The filter hands most of that back, close to seven to eight hours a week. Proof point: the freelance income this protects is the same kind I documented in 28 Income Streams Revealed on YouTube and in my a day in my life breakdown, both checkable, so the time saved here reads as real.
Three moves that turn a noisy job board into a clean inbox of good gigs
What made this work was treating the job board as raw noise, not as a list to read. The signal is buried, and a machine can dig it out faster than you can. The framework hangs on three moves: one rule book that defines a good gig, one gate that reads every listing against it, and one log that explains every call so you can keep tuning.
One rule book that defines a good gig
Before the bot reads anything, you write your rules in plain words. A minimum price or rate. A maximum scope, so a gig that wants the whole marketing strategy on top of the work gets rejected. No on-site work if you only work remote. A client founded in the last three years if you only want startups. These are your standards, written once. The bot does not guess what a good gig is. It enforces exactly the rules you gave it, on every listing, without ever getting tired or sloppy.
One gate that reads every listing
The bot watches your boards for your keyword and checks for new gigs on a schedule. For each one it reads the full description, just like you would, and runs it through the rule book. If the gig fails any rule, it never reaches you. If it passes, the bot researches the client, confirms the company fits your rules, and drafts a reply aimed at landing an interview. One gate, applied the same way to every gig, so nothing slips through and nothing good gets buried.
One log that explains every call
For every gig, the bot writes a short note on what it found and which rule it passed or failed. The filter is never a black box. If a good contract gets rejected, you read the note, see the exact reason, and adjust that one rule. Over a week or two you tune the rule book until almost nothing good slips past. This is where the machine earns your trust. You can audit any decision in seconds and the filter gets sharper the more you read it.
Once those three moves are in place, the boards keep churning out noise and your inbox only ever shows good gigs, each with a reply already written. One rule book, one gate, one log, and the worst task in freelancing is off your plate.
Before the gatekeeper
- An hour or more a day spent reading gigs you would never take
- Low pay and bad scope hidden three paragraphs into a listing
- Skim too fast and miss a good one, read it all and burn out
- Client research skipped, so you reply to firms you would never join
- The blank-page moment every time a gig finally looks right
After the gatekeeper
- The bot reads every gig against your rules, you read almost none
- Low pay, on-site, and bloated scope rejected before you see them
- Only good-fit, well-paid contracts ever reach your inbox
- Client size and age checked, so every gig that lands actually fits
- ~7-8 hours a week back, with a draft reply already waiting
Prompt 1: write the rule book that defines a good gig
Before the bot reads a single listing, your rules have to be clear. Price, scope, client type, location, all written in plain words. Use this prompt to turn your standards into a rule book the bot can apply to every gig.
Gig rule book builder
Act as a freelance business advisor. I want to write a clear set of rules that decides whether a freelance gig is worth my time, so a bot can apply them to every listing it reads. My field and the keyword I search is: [paste, e.g. automation]. My minimum acceptable price or rate is: [paste]. Work I will not do is: [e.g. on-site, full marketing strategy, ongoing positioning]. The kind of client I want is: [e.g. startups founded in the last 3 years, remote-friendly]. Red flags that mean instant reject are: [paste 3 to 5]. Produce a rule book as a numbered list of pass-or-fail checks, each written in one plain sentence the bot can apply to any gig. Group them as price rules, scope rules, client rules, and location rules. For each rule, add a one-line note on what to look for in the listing text. End with a short list of soft signals that should be flagged for my attention rather than auto-rejected.
The rule book is the spine of the whole filter. Write it once, in your own words. Every gig the bot reads is judged against this one list, so spend real care getting it right.
Prompt 2: read one gig and decide pass or reject
This is the core check the bot runs on every listing. It reads a gig, scores it against your rule book, and returns a clear pass or reject with a reason. Use this prompt to test your rules on a real listing before you wire it up.
Single gig judge
Act as my gig filter. You will read one freelance listing and decide if it passes my rules. Be strict. When a gig fails any pass-or-fail rule, reject it. My rule book: [paste the full rule book from Prompt 1]. The gig listing: [paste the full description, price, and any client details]. Work through the rule book one rule at a time. For each rule, state whether the gig passes or fails and quote the line from the listing that decided it. Then give a final verdict of PASS or REJECT. If REJECT, name the single most important reason in one sentence. If PASS, list the two strongest reasons this gig is a good fit, which I can use later in my reply.
Run this on five or six real listings before you trust the filter. Reading the bot’s reasoning against your own gut is how you tune the rule book until it matches your judgement.
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 filters like this one?
I teach the same mechanics that make this gig gatekeeper work inside Automations Made Easy. 1,000+ students have used these mechanics to save two hours a day and take back the most draining part of their week. No coding required.
Week one: a quiet inbox and a little voice asking if it broke.
Most people get nervous in the first week because the inbox suddenly goes quiet. No flood of listings, no morning of reading, just a handful of gigs that actually fit. That quiet is the point. It does not mean the bot stopped working. It means the bot is rejecting the noise it used to make you read, and only the good gigs are getting through.
Week one looks like this. You write the rule book and point the bot at your boards with your keyword. It starts reading every new gig and checking it against your rules. Most get rejected and logged. A few pass, get the client researched, and arrive in your inbox with a draft reply attached. You open the log a couple of times, see the bot reject a gig you would also have rejected, and start to trust it.
The point of the first week is not the number of gigs. It is to prove the loop closes: the bot reads, your rules decide, the noise gets filtered, the good gigs arrive with a draft, and the log explains every call so you can tune anything that feels off.
From there the maths is simple. Sorting gigs by hand used to eat about an hour to an hour and a half a day. The filter hands most of that back, roughly seven to eight hours a week and close to 350 to 400 hours a year. That is time you spend on paid work, on rest, or on finding bigger clients, instead of reading listings you were always going to reject.
All of this runs while you do the actual work, sleep, or take a holiday. The bot does not get bored, does not skim, and does not skip the boring listings the way a tired human does. The rule book holds your standards, the gate applies them to every gig, and the log keeps the whole thing honest.
Prompt 3: research the client behind a gig that passed
A gig passing your rules is only half the picture. You still want to know who is behind it. Use this prompt on any gig that passed, so the bot pulls together what it can find on the client before you reply.
Client background researcher
Act as a research assistant for a freelancer deciding whether to pursue a gig. A listing has passed my filter and I want a quick read on the client before I reply. The gig and any client details in the listing: [paste]. The client name or company, if known: [paste]. My rule about clients is: [e.g. I only want startups founded in the last 3 years]. Find and summarise what you can about this client: company size, roughly when it was founded, what it does, and any signal about how it works with freelancers. State clearly whether the client meets my client rule. Flag anything that would make me hesitate, such as a much larger company than I usually serve or a vague brief. Keep it to a short, scannable brief I can read in under a minute.
This is the check that stops you replying to clients you would never actually want to work with. It runs only on gigs that already passed the rules, so it never wastes effort on the rejects.
Prompt 4: draft a reply that gets the interview
The slow part of a good gig is the blank page. Use this prompt to turn a passed gig and its client research into a short, specific reply aimed at landing an interview. You read it, tweak a line, and send.
Interview-getting reply writer
Act as a direct, confident freelancer writing a short reply to a gig that fits me well. The goal is to get an interview, not to write a long proposal. The gig listing: [paste]. What the bot found on the client: [paste the brief from Prompt 3]. The two strongest reasons this gig fits me: [paste from Prompt 2]. My name and one line on what I do: [paste]. Write a reply of 120 words or fewer. Open with one specific line that shows I actually read the listing. Name one concrete way I would approach the work. Reference one relevant thing about the client. End with a clear, low-pressure ask for a short call. Keep the tone human and direct. Do not use filler, do not flatter, and do not invent experience I did not give you.
The draft is a starting point, never the final word. The blank-page moment is gone, the specifics are already in place, and you stay in full control of what actually gets sent.
How to build automatically filter freelancer contracts, step by step
Write the rule book and pick your keyword
Open a clean note file. Write your keyword, the one you already search for on the boards. Then run the rule book prompt to lock your rules on price, scope, client, and location in one place. This rule book is the spine of the whole filter. Write it before the bot reads a single listing. Vague rules let bad gigs through, so spend real care making each rule a clear pass-or-fail check the bot can apply to any gig.
Point the bot at your boards and set the watch
Give the bot the boards you already use and the keyword you already search. Set it to check for new gigs on a schedule, say every hour or twice a day. This is a one-time setup. The bot now visits the boards, pulls the new listings that match your keyword, and queues them up for reading. You never open the boards yourself again unless you want to. The watching that used to start your morning now happens in the background.
Let the bot read each gig against your rules
For every gig in the queue, the bot reads the full description and runs it through the rule book, one rule at a time. Price below your rate, it rejects. Scope bundles in the whole marketing strategy, it rejects. On-site required, it rejects. A gig only passes if it clears every pass-or-fail rule. This is the heavy reading you used to do by hand, now done in seconds per gig, the same way every time, without skimming or fatigue.
Research the client on every gig that passed
When a gig clears every rule, the bot looks up the client before it reaches you. Company size, roughly when it was founded, what it does, how it tends to work with freelancers. If your rule says startups only, the bot checks the company was created in the last three years and rejects it if not. This is the research you would do yourself before replying, done up front, so the gigs that land in your inbox are not just well-paid but attached to clients you actually want.
Get the gig in your inbox with a draft reply
The gigs that pass every rule and clear the client check arrive in your inbox, each with a short reply already drafted. The draft is built from what the bot learned about the gig and the client, so it reads specific, not generic. You open it, see why it passed in one line, tweak the reply if you want, and send. The blank-page moment is gone. The only time you spend is the few seconds it takes to approve and send a message that was already written for you.
Read the log and tune the rule book
Every decision the bot makes goes into a log in plain words. What it found, which rule decided the gig, and whether it passed or rejected. Read the log a few times in the first weeks. If a good contract got rejected, you see the exact rule that caught it and loosen it. If junk slips through, you tighten a rule. Over a week or two the filter sharpens until it matches your judgement almost exactly. This is the loop that makes the machine yours.
Rules locked
One rule book of pass-or-fail checks on price, scope, client, and location, written in your own words.
Boards watched
The bot checks your boards for your keyword on a schedule and queues every new gig for reading.
Gigs read and filtered
Each gig is checked rule by rule, the client is researched, and only good-fit contracts pass the gate.
Inbox and log
Good gigs arrive with a draft reply, and the log explains every call so you keep tuning the rules.
Build this gig gatekeeper inside the same playbook 1,000+ students use
Automations Made Easy teaches the mechanics behind filters like this one. Step by step, no code, plain English. Take back the most draining hour of your freelance day without spending a cent on tools you do not need.
The six months after I switched it on
Here is the shape of the first six months after I turned the gig gatekeeper on. The hours handed back climb as I tune the rule book, then steady once the filter matches my judgement and almost nothing good slips through.
Hours handed back per week, after switching on
Three things matter on this chart. The line settles around seven to eight hours back a week and stays there. The hours come straight off the reading task I hated most. And every one of those weeks happens without me opening a job board, without missing good gigs, and without spending a cent on extra tools.
What other students built with automatically filter freelancer contracts
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 was reading forty listings a morning to find two worth replying to. Now the two worth replying to are the only ones I see, with the reply already written. I got my mornings back in a weekend.”
“The client research is what sold me. It rejected a gig from a huge agency I would have hated, before I wasted an hour writing a proposal. The log told me exactly why.”
“I set one rule, no on-site, and that alone cut my reading in half. The draft replies feel like me because I gave it my past messages. I just read and send.”
“I turned the same filter onto the applications I get for my small team. It sorts CVs against my hiring rules the same way it sorts gigs. One machine, two problems gone.”
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 watch, read, and decide 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 gig gatekeeper: common questions
Pulled from what readers and Automations Made Easy students ask most.
What stops the bot from filtering out a good gig by mistake?
Every decision is written to a log in plain English. For each gig the bot records what it found and which rule it passed or failed. If you spot a good contract that got filtered out, you read the note, see exactly why, and adjust that one rule. The filter is never a black box. It is a set of rules you wrote, applied consistently, with a reason attached to every single decision. Over a week or two of reading the log you tune the rules until almost nothing good slips through.
Which freelance boards can the bot watch?
Any board that lets you search by keyword and read the listings. The bot watches your chosen boards for a keyword like automation, checks for new gigs on a schedule, and reads each one. It works the same way you would, just faster and without getting bored. You point it at the boards you already use and give it the keyword you already search, and it does the reading and sorting you used to do by hand every morning.
What rules can I set for a gig to pass?
Anything you can describe in words. A minimum price or rate. A maximum scope, so a gig that asks for the whole marketing strategy on top of the work gets rejected. No on-site requirement if you only work remote. A client founded in the last three years if you only want startups. You write the rules in plain language and the bot applies them to every gig. The rules are yours, so the filter matches exactly what you will and will not take on.
Does it really draft a reply for me?
Yes. When a gig passes all your rules, the bot drafts a short reply aimed at getting an interview. It pulls in what it learned about the gig and the client so the message feels specific, not generic. You read it, tweak a line if you want, and send. The draft is a starting point that saves you the blank-page moment. You stay in control of what actually goes out, but the slow part is already done for you.
Can the same filter sort job applicants or CVs?
Yes, the logic is identical. Instead of reading job posts against your rules, the bot reads incoming applications or CVs against your hiring criteria. It checks each one, passes the ones that fit, rejects the rest, and logs why for every candidate. If you ever hire or take on subcontractors, the same machine that filters your gigs filters your applicants. One pattern, two jobs, both off your plate.
How much time does this actually save?
Sorting gigs by hand used to eat about an hour to an hour and a half of my day. The filter hands most of that back. That is roughly seven to eight hours a week and close to 350 to 400 hours a year. More than the hours, it removes the most draining task in freelancing, the endless reading of descriptions to decide if a gig is worth a reply. Only good-fit, well-paid contracts reach me now, with a draft already waiting.
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.
Build this gig gatekeeper yourself, or learn the mechanics inside Automations Made Easy.
If you want to learn the mechanics behind filters 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 the rules and the boards that would work for your specific freelance niche first, I take a small number of consulting clients each month.
€497 one-time · Lifetime access · 1,000+ students
