Building 7 min read

Your $2,000 day starts the night before: our system keeps you on the tools, not on the phone

Optimised routes overnight, automatic customer notifications, and promises the system keeps or corrects. A scheduling system that protects your daily rate.

A job runs long. You are behind. Three customers are waiting and two of them have taken the morning off work. You are under a sink and you cannot call anyone.

You tap one button. Every affected customer gets an updated time window automatically. The one whose appointment shifted from morning to afternoon is told before they have to wonder. The one who is still on track hears nothing. You are already driving to the next job. You did not make a single call. You did not think about who was promised what. The system handled it.

That is what a perfect day feels like. Not a day where nothing goes wrong. Those do not exist. A day where things go wrong and nobody notices, because the system caught it before it became your problem.


Your Day With the System

You wake up. At six-thirty you get a text with your run for the day: jobs listed in order with addresses and estimated times. One link opens a mobile page. No app. Works in your browser.

That run order is not random. Overnight, the system calculated the actual drive times between every job and produced the route that gets you through your day with the least time on the road. For five jobs between Baldivis, Rockingham, and Secret Harbour, that is the difference between an hour of driving and two hours of driving. Every day. You never think about it.

You drive to the first job. Between jobs, you tap one button: “on my way.” The system sends the customer a message, shows you the next address as a Google Maps link, and marks the previous job complete. That is your entire interaction with the system. One tap between jobs.

Three buttons total. “On my way” for the next job. “Can’t do this job” for cancellations. “Cancel whole day” for when you are crook. Plus a quick-add button for jobs that come in by phone or text, but more on that below.


What Your Customers Get

Two messages. That is the whole experience from their side.

The evening before their job, they get a text: Dave from Dave’s Plumbing is coming tomorrow morning. Not a six-hour window. Morning or afternoon.

When you tap “on my way,” they get a second text. If you are under an hour away: Dave is on his way and will be with you within the hour. If further out: within the next couple of hours. The system picks the wording automatically. You never see the calculation.

They did not download an app. They did not create an account. They did not get a link to track you in real time on a map they never asked for. They got told when you are coming, and then they got told you are on your way. That is all they wanted. That is what gets you the five-star review.


The Jobs You Are Losing at Ten PM

A customer visits your website at ten PM because their hot water just died. They are not going to call; it is too late. They are not going to fill in a contact form and hope someone reads it tomorrow. So they call the next bloke on Google who has a chat window.

With this system, that chat window is on your site. It asks the right questions: what is the problem, where are you, how urgent is this? And books the job right there.

The system knows the difference between an emergency and a job that can wait. No hot water tonight? First available slot tomorrow, routing overridden. Leaking tap that is not getting worse? Batched into an optimised run later in the week so you are not criss-crossing the suburbs. The customer picks their urgency: emergency, urgent, or flexible. And the scheduling adjusts accordingly. No phone tag required.

The system captures the details, creates the job, books a slot in your calendar, and texts the customer a confirmation. Not a vague acknowledgement. A proper confirmation: the date, the window, the address, the job description, the call-out fee, and a clear line explaining that any further work gets quoted on-site before it starts. The customer knows what they are paying to get you through the door. You are protected from being locked into a price before you see the job.

You find out in your morning text. The customer wakes up knowing everything is sorted. That job would have gone to whoever answered the phone first tomorrow morning. Instead, it was booked at ten PM while you were watching telly.


What Happens When the Phone Rings

The phone will not disappear. Some customers will always want to speak to a human: older customers, complex jobs, loyal regulars who have had your number for years.

But you do not need to answer every call. Your voicemail handles most of them: Dave is currently on the road. To book or change an appointment, head to davesplumbing.com.au; you will get a confirmed time straight away. If your job is urgent, we can do same-day servicing through the website. If you need to speak to Dave directly, call back after four or leave a message.

Most callers follow the redirect. They book through the website and get the full experience: confirmation text, evening notice, on-my-way message. A verbal “yeah probably Tuesday arvo” becomes a confirmed booking with professional follow-through.

When you do answer the phone, the repeat customer, the complex job, the anxious caller who needs a human voice, you take the details and tap “add job” on your mobile page. Four fields: name, phone, address, job type. Twenty seconds. The system sends the customer a confirmation text and the job enters the same promise chain as every other booking. Same experience, regardless of how it came in.

You go from answering every call to answering maybe one in four. The calls you do take are the ones where a human conversation genuinely matters. Everything else is handled.


The Promise Principle

This is the part that matters, and the part every other booking tool gets wrong.

The evening notice is not a notification. It is a promise. When a customer receives Dave is coming tomorrow morning, that window is locked. The system will either keep it or explicitly correct it. It will never silently break it.

If a job cancels and the run shifts, the system checks every remaining customer. Did anyone’s window change from morning to afternoon, or the other way around? If yes, they get a correction message immediately, before you have to make a phone call, before the customer has to wonder, before trust erodes. If nothing changed, silence. The system only sends messages that tell people something they do not already know.

Here is how that works in practice. A morning job cancels. You are now running ahead of schedule. Your afternoon customers do not get bumped earlier without being told; new jobs that come in after the evening notices were sent slot into the gap or go to the end of the day. They cannot displace a promise that has already been made. If a job runs long and pushes someone across the morning-afternoon boundary, the correction fires automatically. You do not need to remember who was promised what. The system remembers.

Think about how you handle the same situation today. A job cancels. You are running ahead. The afternoon customer has no idea they could have gone to work this morning. Or a job runs long. The morning customer is sitting at home wondering. You are under the van and cannot call. Nobody gets told anything until you surface and remember.

The system remembers so you do not have to.


Three Buttons, Not Thirty Decisions

“Can’t do this job” is smarter than it looks. You select why: true cancellation or no access. The customer gets a different message depending on the reason. If you cancelled, the message says you will be in touch to rebook. If the customer was not home, the message says you arrived but could not get access. Your action is the same either way. One tap. The system handles the wording.

“Cancel whole day” sends one message to every remaining customer on the run, personalised per job, in one tap. You are not making six phone calls from your bed when you have the flu.

You can also tap “on my way” against any job in the list, not just the next one in sequence. If you decide to swap job two and job three, you tap “on my way” for whichever you are heading to. The system recalculates from there. Free reordering, no admin.


What It Deliberately Does Not Do

No invoicing. No payment processing. No job cards. No quoting tool. No materials tracking.

You handle all of that the way you always have. The system owns the front end: booking, routing, notifications, promises. Everything else stays with you until you decide otherwise.

This is deliberate. Every tradie has been sold a system that promised to do everything, did most of it badly, and created more admin than it saved. This system does one thing well: it books jobs, tells customers when you are coming, and keeps that promise. That is it.

If you want invoicing later, that is V2. If you want automated follow-ups for reviews, that is V2. V1 solves the problem that costs you the most jobs and the most phone time right now.


What It Takes

Setup takes one to two weeks; you can be running automated scheduling and notifications within a fortnight. Scope and pricing are agreed in writing per engagement.

One saved job per month covers the running cost. One customer who books at ten PM instead of calling a competitor at eight AM covers it. One day where you do not have to make six phone calls about timing covers it. Most businesses save several jobs worth of phone time in the first month alone.

The system works independently of your existing website. Your web person adds one or two lines of code and the booking widget is live. We are happy to liaise with them directly; you do not need to be the middleman between two tech people.

The maths is not complicated. The question is whether you want your next good day to happen by luck or by design.


Perth AI Consulting builds booking and automation systems for trades businesses across Australia. Setup in one to two weeks. No app required. Start with a conversation.

Published 8 March 2026

Perth AI Consulting delivers AI opportunity analysis for small and medium businesses. Start with a conversation.

Prepared by Claude, directed and approved by PAC.

More from Thinking

Building 7 min read

Why we let AI run the interviews (and why we never let it pretend to be human)

AI-conducted interviews compress weeks of stakeholder discovery into days, standardise what gets asked, and lower the guard that distorts honest answers.

Adoption 14 min read

How AI capability actually moves through a business

The decisive variable in SME AI adoption is the human absorption sequence, not the tooling. A working framework from observation across WA businesses.

Evaluation 7 min read

AHPRA advertising rules for psychologist websites

Recovery stories, 'specialist', 'clinical psychologist', and endorsement titles are where psychology sites breach the National Law. A practical read-through.

Adoption 6 min read

Customer service AI has finally grown up

Chatbots and AI receptionists earned their bad reputation. What changed, why the trick is in the data, and how the mature version answers every call without replacing anyone.

Evaluation 6 min read

Who can use the titles 'Dr', 'Specialist', and 'Surgeon'?

AHPRA restricts 'specialist' and 'surgeon' to specific registrations, and 'Dr' has its own rule. What health practice websites can and cannot claim.

Adoption 5 min read

Your best people hate writing reports

The operators you promote are brilliant at the work and allergic to reporting. A scheduled AI call interviews them, drafts the briefing, and they approve it. No ego, no politics, no blank page.

Building 6 min read

Your website isn't just for humans anymore

How to build a chatbot that keeps itself up to date, can't leak client information, and won't answer beyond what you've published. The answer was sitting in plain sight.

Evaluation 7 min read

Can you show Google reviews on your health practice website?

AHPRA bans clinical testimonials, even true ones, but service reviews are fine. What that means for the Google reviews widget on your practice site.

Evaluation 7 min read

What AHPRA's advertising rules mean for your website

Your practice website is advertising under the National Law. What AHPRA's rules prohibit, who is responsible, and how to check your own site.

Evaluation 8 min read

Is it safe to paste client data into ChatGPT?

What ChatGPT, Claude, and Copilot promise about your data, what the Privacy Act requires, and the honest answer for professionals handling client files.

Evaluation 6 min read

What a good AI audit actually delivers

The audit report named one recommendation specific enough to check. What the Build engagement that followed looked like, shown through one real engagement, generalised.

Evaluation 7 min read

AI and video, Mid-2026: the models can watch now, not just listen

AI could always transcribe video. It can now read the frames as well, and every hour of footage a business owns becomes something it can question.

Technical 5 min read

Why the privacy case against cloud AI memory isn't paranoia

An AI knowledge base concentrates everything sensitive a business holds. Dated 2026 incidents show what cloud custody means once legal process gets involved.

Technical 5 min read

Your AI knowledge base is an attack surface

A knowledge base an AI agent can read and write is a productivity tool, and dated 2026 incidents show it is also somewhere an attacker can plant instructions.

Adoption 5 min read

The real asset in an AI knowledge base isn't the notes

In every AI-maintained knowledge base, one file carries the owner's judgement and compounds. The wiki pages are the least valuable part.

Evaluation 5 min read

The missing measurement in the AI second-brain boom

Every claim about AI knowledge bases saving time is self-reported. The one controlled experiment measured token economics, not benefit.

Building 11 min read

From evidence base to delivery: a production AI methodology

How we delivered 34 evidence-anchored AI briefings to a WA peer-advisory chapter: fact-checked literature review, multi-agent verification, one method.

Technical 9 min read

The six functions of a working AI system

A working AI system is six functions doing six jobs. When all six connect, hallucinations get caught, outputs hold steady, and models become swappable.

Technical 7 min read

Supervised autonomy: the middle path for AI architecture

Between drafts you approve and agents you hope about sits the middle path: an envelope of authorised routine work, supervised, audited, and yours to widen.

Evaluation 5 min read

The state of applied AI in Mid-2026

Our literature review of applied AI in mid-2026: ten capability categories, three fact-check passes, written for operational leaders.

Evaluation 8 min read

AI in building inspections, Mid-2026

AI defect detection is strong on obvious defects and weak on the subtle ones where liability lives. Which capabilities fit inspection work in 2026.

Evaluation 8 min read

AI in property valuation, Mid-2026

AVMs are reliable enough for triage, not for the final word on contested property. What has shifted in valuation work by mid-2026, and what has not.

Evaluation 8 min read

AI in family law, Mid-2026

Federal Court practice note GPN-AI makes AI verification a professional obligation. What the courts now require, and what the evidence says about legal AI.

Technical 9 min read

How to design a PHI redaction system for clinical AI

PHI redaction is part of a clinical AI tool's architecture, not a feature you add. What the literature says it should look like, and how we built it.

Building 9 min read

How we built on-device de-identification so AI never sees real names

Most AI privacy is a policy. Ours is architecture: an NER model runs in the browser and strips names before anything leaves the device.

Technical 7 min read

Your agency's clients are about to ask why this costs so much

A solo consultant built in three weeks what your agency quoted twelve for. The client doesn't know why yet. The agencies that survive change what they sell.

Adoption 6 min read

What do you love doing? What do you hate doing?

Ask people what they love doing and what they hate doing, then show them AI is coming for the second list. Why the reframe works, and how it fails.

Technical 7 min read

Why I don't use n8n (and what I do instead)

n8n demos well. But a compelling demo and a reliable production system are different things, and the distance between them is where businesses get hurt.

Technical 10 min read

Your codebase was not built for AI. That's the actual problem.

Amazon's mandatory meeting about AI breaking production is an architecture story: codebases built for human maintainers only, now maintained by AI.

Adoption 4 min read

Your team has AI licences. You don't have an AI system.

Fifteen people, fifteen separate AI accounts, no shared context. The problem isn't the tool; it's the architecture around it. Here's the fix.

Evaluation 4 min read

The fastest way for an executive to get across AI

AI moves faster than any executive can track. One focused conversation, one written report, and a decision you can act on: your time stays on the business.

Building 6 min read

Your IT department will take 18 months. You need this working by next quarter.

Senior leaders know what they need built; the gap is time. A prototype gets the tool working now and hands IT a validated blueprint for later.

Adoption 4 min read

What if you had perfect memory across every client?

Every practice captures more than it can recall. AI gives practitioners perfect memory across every client, so preparation becomes thinking time.

Building 8 min read

We built an AI invoice verifier. Here's where it hits a wall.

We built an AI invoice verifier and watched a fake beat a real invoice. Why document analysis alone cannot stop fraud, and the five layers that can.

Building 5 min read

How to build an AI chatbot that doesn't lie to your customers

Woolworths scripted its AI to talk about its mother. The business fix is honesty; the technical fix is architecture that prevents fabrication by design.

Technical 9 min read

Why AI safety features are load-bearing architecture, not political decoration

The 'woke AI' label came from real failures, but they were engineering failures, not safety failures. The difference matters wherever errors have consequences.

Adoption 3 min read

Woolworths' AI told a customer it had a mother. That's a problem.

Woolworths' AI assistant Olive was scripted to talk about its mother and uncle. When callers realised, trust broke instantly. The fix is honesty.

Evaluation 5 min read

Google is no longer the only way your customers find you

Customers now find businesses through ChatGPT, Perplexity, and Gemini. The sites AI cites are structured differently to the sites Google ranks.

Evaluation 4 min read

Two types of AI audit: and how to know which one you need

Where do we start with AI? It depends on whether you need to find the opportunities or reclaim the time. Two audits, two perspectives, one goal.

Evaluation 4 min read

The personal workflow analysis: what watching a real workday reveals about automation

People describe the work they value, not the work that eats their time. Recording a real workday reveals the automation opportunities interviews miss.

Evaluation 4 min read

AI audit that starts with your business

An operations-first AI audit starts with how your business actually runs, and only recommends AI where the evidence says it will work.

Building 6 min read

What production AI teaches you that demos never will

The gap between a demo and a working system is where the useful lessons live. Architecture, framing, privacy, adoption: the patterns repeat every time.

Adoption 6 min read

The psychology of why your team won't use AI

You buy the tool, run the demo, and three months later nobody is using it. Five predictable psychological barriers, each with a strategy that works.

Technical 4 min read

Stop telling AI what NOT to do (and what to say instead)

Instructions built on prohibitions make AI cautious and generic. Describing what you want instead transforms the output, and the reason comes from psychology.

Building 5 min read

How we turned generic AI into a specialist: and what that means for your business

Mediocre AI output is rarely the model's fault. Three structural changes that turn the same model from generic to specialist-grade.

Evaluation 5 min read

Your business has 9 customer touchpoints. AI can fix the 6 you're dropping.

You pay to get customers to your door, then lose them to missed follow-up. AI can handle the six touchpoints most businesses drop.

Technical 5 min read

What happens to your data when you press 'Send' on an AI tool

Businesses send customer data to AI tools without knowing what happens during processing. The spectrum of AI privacy is wider than you think.