AI website chat for small business illustration: a laptop at night showing an example chat where an AI assistant answers a 9:47 pm enquiry and shows Details captured, with a crescent moon outside the window

Here’s a pattern I see in a lot of small businesses. Someone finds your website at 9:30 on a Tuesday night, likes what they see and sends an enquiry. Nobody’s at the desk, so it sits there. By the time you open it at 7am, they’ve also enquired with two other businesses, and one of them got back to them first.

You can’t be on call 24/7, and you shouldn’t have to be. This is a job an AI website chat handles well: answering the common questions, collecting the details and lining up the next step, so the enquiry is warm and ready when you start work. In this post I’ll show you what a good AI website chat should and shouldn’t do, what to feed it, how the handover works next morning, and how to test it before it goes anywhere near a real customer.

What happens to an enquiry that sits until morning

I’m not going to throw a made-up statistic at you here. Just think about how you shop for a service yourself. When you need a plumber, a bookkeeper or a physio, you rarely contact just one. You send a few enquiries, and the business that replies first with something useful has a head start.

After hours is when a lot of people finally get time to sort out their life admin: kids are in bed, work is done, and they’re browsing on the couch. If your website can only offer a contact form and silence until morning, you’re relying on that person still being keen the next day, and still remembering which website was yours.

I covered the daytime side of this in how to reply to every enquiry fast with AI. After-hours chat is the same idea, for the hours when nobody can reply at all.

What an AI website chat should do (and what it shouldn’t)

The biggest mistake I see is giving a chat bot too much freedom. A good AI website chat has a narrow, clear job. Think of it as a friendly front desk person on their first week: helpful, polite, and very clear about what they can and can’t promise.

Jobs to give it

  • Answer common questions using your own information: services, service area, opening hours, how bookings work, what to expect at a first visit.
  • Collect the details you’d ask for anyway: name, contact details, suburb, what they need and how urgent it is.
  • Offer the next step, such as a booking link for a call, or a clear “we’ll be in touch tomorrow morning”.

Jobs to keep away from it

  • Quoting prices it hasn’t been given, or estimating a job it can’t see.
  • Making promises about availability, timeframes, refunds or results.
  • Advice that needs a qualified person: medical, legal, financial or safety questions.
  • Handling complaints beyond acknowledging them and passing them to a human.

Why be this strict? Because what your chat says, you’ve said. There’s a well-known case from Canada, Moffatt v. Air Canada (2024 BCCRT 149), where the airline’s website chatbot told a customer he could apply for a bereavement fare after travelling. That wasn’t the airline’s policy. The British Columbia Civil Resolution Tribunal found the airline responsible for what its chatbot said and ordered it to pay the difference. It’s a Canadian decision, not Australian law, but the lesson travels: if your chat makes it up, customers will hold you to it.

Tell people they’re talking to AI

Don’t dress your chat up as a person. Label it clearly as an AI assistant. The Office of the Australian Information Commissioner’s guidance on privacy and the use of commercially available AI products says businesses should make sure public-facing AI tools, such as chatbots, are clearly identified as such, and that privacy policies explain how AI is used. Being upfront also builds trust. Most people are fine chatting with AI at 10pm as long as they know a real person will follow up.

Feeding it your services, area, hours and FAQs

An AI chat is only as good as the information you give it. If you feed it nothing, it will guess, and guessing is exactly what you don’t want. Before you switch anything on, put together a one-page “knowledge sheet” in plain English.

What goes on the knowledge sheet

  • Services: what you do and, just as important, what you don’t do
  • Service area: the suburbs or regions you cover, and what happens if someone’s outside it
  • Hours: when a human will reply, so the chat can set honest expectations
  • Pricing rules: only what you’re happy to say publicly, such as “call-out fee from $X” or “we quote after a site visit”
  • Your top 10 to 15 questions, with the answers you’d give on the phone
  • Hard rules: “never quote a price not listed here”, “never promise a time”, “if it’s an emergency, give this number”

Not sure what your top questions are? Your inbox and your team already know. My post on building a team FAQ from real customer questions with AI walks through pulling them out of old emails and messages, and that same FAQ becomes the brain of your website chat.

A simple instruction block

Whatever chat tool you use, it will have somewhere to put instructions. Here’s an example you can adapt:

You are the AI assistant on [Business]’s website. You are an AI, and you say so if asked. Answer only using the information below. If you don’t know, say a team member will reply during business hours. Never quote a price, timeframe or availability that isn’t listed. Your goal is to help, then collect the person’s name, phone or email, suburb and what they need. Keep replies short, friendly and in Australian English. If someone mentions an emergency, give them [emergency number] straight away.

The handover: how a person picks it up next morning

An after-hours chat is only half the job. The other half is what happens at 7am. If the details land in an inbox nobody checks until lunchtime, you’ve lost most of the benefit.

Make the summary easy to act on

Set the chat up so every conversation ends with a short summary sent to wherever your team actually looks: email, your CRM or a shared inbox. A good summary has:

  • Name and contact details
  • What they need, in one or two lines
  • Urgency and suburb
  • Any questions the chat couldn’t answer
  • What the customer was told would happen next

Give someone the morning job

Decide who works through overnight enquiries first thing, and by when. Even a simple rule like “every overnight chat gets a personal reply before 9am” makes a huge difference. That reply should come from a human and pick up where the chat left off, so the customer never has to repeat themselves.

If you want the follow-up to happen even when that first reply gets no response, that’s where an Instant Lead Reply and a follow-up routine come in. Both are in my free Steal My AI Agents pack, written as plain-English instructions that work with ChatGPT, Claude, Grokbot or any AI assistant.

Test it like a customer before it goes live

Never switch a chat on without trying to break it first. Spend 30 minutes being your own trickiest customer. Get a team member to have a go too.

Questions to throw at it

  • “How much does it cost?” (Does it stick to your pricing rules?)
  • “Can you come tomorrow at 8am?” (Does it avoid promising a time?)
  • “Do you service [suburb outside your area]?”
  • “Is this safe to fix myself?” (Does it avoid advice it shouldn’t give?)
  • “Am I talking to a real person?”
  • A grumpy complaint about a past job

Every time it gets something wrong, fix the knowledge sheet or the rules, then test again. Keep testing for the first couple of weeks after launch too: read every conversation, note anything odd and tighten it up. It’s also worth checking what customer details the chat tool stores and who can access them. My post on whether AI is safe for small business covers what to look for.

What to do this week

  1. Check your after-hours gap. Look at when your last 20 enquiries arrived and how long each waited for a reply.
  2. Write your knowledge sheet. Services, area, hours, pricing rules, top questions and hard rules, on one page.
  3. Set up the handover. Decide where summaries land and who replies first thing each morning.
  4. Test it hard. Run through the question list above and fix anything it gets wrong.
  5. Review weekly. Read the conversations, add new questions to your FAQ and adjust the rules.

Done well, an AI website chat doesn’t replace you. It keeps the conversation going while you’re off the clock, so you start each morning with warm enquiries instead of cold ones. If you’d rather have one built and looked after for you, that’s exactly what we do at WebsiteChat.

FAQ

Can an AI website chat answer enquiries after hours?

Yes. A well set-up AI website chat can answer common questions, collect the customer’s details and offer the next step at any hour. A person then picks up the conversation during business hours.

Will an AI chat give customers the wrong information?

It can if you leave it to guess. Give it a clear knowledge sheet, tell it to answer only from that information, and set hard rules about prices, timeframes and advice. Then test it and read the conversations regularly.

Should I tell customers they’re chatting with AI?

Yes. Label it clearly as an AI assistant. The OAIC’s guidance on commercially available AI products says public-facing AI tools such as chatbots should be clearly identified, and being upfront builds trust.

Can the chat quote prices or book jobs?

Only within rules you set. It can share pricing you’re happy to publish and offer a booking link, but leave custom quotes, availability promises and anything needing judgement to a person.

Do I need a developer to add AI chat to my website?

Not always. Many chat tools can be set up without code, but the knowledge sheet, rules, handover and testing are what make it work. If you’d rather not do it yourself, a free AI audit is a good place to start.

Stop losing the enquiries that arrive after hours

Grab the free Steal My AI Agents pack: ready-to-use agents for lead replies, follow-ups, reviews, onboarding, inbox triage and a weekly business review. Works with ChatGPT, Claude, Grokbot or any AI assistant. Want help working out where your enquiries are slipping through? Book a free AI audit.

Get the free AI agents pack or book a free AI audit

GoHighLevel AI automation illustration: a simple three-step workflow diagram with Follow-up, Review and Onboard nodes joined by arrows, each labelled AI draft, you approve

A lot of small businesses I talk to are paying for GoHighLevel every month and using a fraction of it. The pipeline is there, the calendars are there, the workflow builder is there. But the follow-up sequences never got written, the review requests go out when someone remembers, and new clients still get a welcome email typed from scratch.

That’s not a software problem. It’s a writing and setup problem, and that’s exactly where AI helps. In this post I’ll walk you through why GHL accounts stay half set up, then three jobs you can hand to AI first: follow-up sequences, review requests after the job, and a client onboarding checklist. Then I’ll show you how to test it all before you switch anything on.

Quick note: I’m independent and not affiliated with or endorsed by HighLevel. GoHighLevel and HighLevel are trademarks of their owner.

Why GoHighLevel accounts stay half set up

GoHighLevel can do a lot. That’s the selling point, and it’s also the problem. When a tool can do everything, someone has to decide what it should do for your business, write the words, build the steps and keep them up to date. In most small businesses, that someone is the owner, and the owner is busy running the business.

Here’s what I usually see when I open up an account:

  • Empty or default workflows. The account was set up by an agency or a course template, and nobody has touched the workflows since.
  • Generic messages. The follow-up texts that do exist were written for “any business”, so they don’t sound like you and customers can tell.
  • Stages nobody uses. The pipeline has stages, but jobs don’t get moved, so any automation tied to those stages never fires.
  • Fear of breaking something. Owners worry that if they switch a workflow on, it’ll spam their customer list. So they leave it off.

The good news: the hardest part of all of this is the writing and the thinking, and AI is very good at both. You can get the words and the logic drafted in an afternoon, then put them into GHL piece by piece.

HighLevel has its own AI too

It’s worth knowing what’s already built in. HighLevel’s support portal describes a Workflow AI Builder that turns a plain-language prompt into a workflow you then review and refine, and Conversation AI bots that can collect lead details, answer common questions and help with booking. HighLevel’s own guide says generated workflows need a manual review before you publish them, which is good advice for any AI setup. Features and pricing depend on your plan, so check your account before you rely on them.

Whether you use HighLevel’s built-in AI or an outside assistant like ChatGPT, Claude or Grokbot, the same rule applies: you still need to know what you want it to say and when. That’s what the rest of this post is about.

Job 1: AI-written follow-up sequences

Most quotes and enquiries that go cold weren’t lost. Nobody followed up. A follow-up sequence in GHL fixes that, but only if the messages are good enough that you’re happy for them to go out.

Decide the cadence first

Keep it simple. A day 1, day 3 and day 7 rhythm works for a lot of service businesses: a quick check-in, a helpful nudge, then a polite last message that makes it easy to say no. Write down when the sequence should stop, for example as soon as the person replies, books, or says they’ve gone elsewhere.

Get AI to draft the messages in your voice

Give your AI assistant three or four real messages you’ve sent before, a short description of your business and your service area, and the cadence. Ask it to write each message for SMS and email, short and friendly, with one clear next step. Then edit them until they sound like you. I cover the tone side in more detail in my post on how to follow up leads with AI without being pushy.

Personalise with the fields you already have

GHL lets you insert contact fields into messages. Ask the AI to use the ones you actually fill in, such as first name, service type and suburb. A follow-up that mentions “the bathroom quote in Ashgrove” lands very differently to “your recent enquiry”. (That’s an example, not a real customer.)

Job 2: Review requests after the job

Happy customers rarely leave a review unless you ask, and asking feels awkward. A simple automated request, sent at the right moment, takes the awkwardness out of it.

Trigger it on the win

Tie the request to a clear moment, such as a job being marked complete or an invoice being paid. If your pipeline stages aren’t kept up to date, fix that first, or the request will go out at the wrong time or not at all.

Write a short, personal ask

Ask the AI for a two or three line message that thanks the customer for something specific, then gives them the link. No pressure, no incentives, no long story. Ask for a second version for the reminder a few days later, and stop after that.

Ask everyone, not just the happy ones

Don’t set up a workflow that only sends the review link to people who rate you highly and sends everyone else somewhere else. That’s called review gating and it goes against Google’s review policies. Ask every customer, and handle any complaints that come back as a person, not a bot. My post on getting more Google reviews with AI goes through this step by step.

Job 3: A client onboarding checklist

When a deal is won, the next few days set the tone for the whole relationship. If onboarding happens in your head, things get missed: the access you needed, the forms they never filled in, the kick-off call nobody booked.

Write the checklist once

Tell your AI assistant what happens after someone says yes in your business, even in rough dot points. Ask it to turn that into a clean checklist with three parts: what the client needs to send you, what your team needs to do, and when each step should happen. You only have to do this once.

Turn it into messages and tasks

From that checklist, get the AI to draft the welcome email, a short reminder for anything the client hasn’t sent yet, and the internal tasks for your team. In GHL, these can hang off the “won” stage: the welcome goes out, tasks are created and assigned, and a reminder follows if a form is still missing. For more on this, see how to onboard new clients with AI.

Test everything before you switch it on

This is the step most people skip, and it’s the one that stops the “what if it spams everyone” fear from coming true.

Use a test contact

Create a contact with your own mobile and email, and run them through every workflow. Read every message as if you were the customer. Check the timing, the personalisation fields and the links.

Check the stop rules

Reply to a follow-up as your test contact and make sure the sequence stops. Move the test deal to won and check the follow-up ends and onboarding starts. These are the bits that cause the most embarrassment when they’re wrong.

Start small

Switch on one workflow for new contacts only, not your whole list. Watch it for a week. Look at what went out, what people replied and anything that looked off, then fix the wording or the logic before you add the next one.

Keep a person in the loop for the tricky stuff

Decide what must always go to a human: pricing questions, complaints, anything legal or sensitive. If you’re unsure about the data side, my post on whether AI is safe for small business covers what to check.

What to do this week

  1. Pick one job. Follow-up, reviews or onboarding. Choose the one that costs you the most work today.
  2. Write your rules in plain English. Your services, area, tone, cadence and what always goes to a person.
  3. Get AI to draft the messages. Use your own past messages as examples, then edit until they sound like you.
  4. Build it in GHL and test it on yourself. One workflow, one test contact, every message read end to end.
  5. Switch it on for new contacts only. Review after a week, then add the next job.

If you’d rather start with the instructions already written, the free CRM agent pack for GoHighLevel gives you AI agents for lead replies, follow-ups and pipeline updates. They’re plain-English instructions that work with ChatGPT, Claude, Grokbot or any AI assistant, so there’s nothing to install.

FAQ

Do I need to know how to build workflows to use AI with GoHighLevel?

No. AI can draft the messages and describe the steps in plain English, and HighLevel’s own Workflow AI Builder can turn a prompt into a workflow. You still need to review every step and test it before you switch it on.

Will AI send messages to my customers without me checking?

Only if you set it up that way. Start by testing every workflow on your own contact, switch it on for new contacts only, and keep pricing, complaints and anything sensitive with a person.

Can I only send review requests to happy customers?

No. Filtering out unhappy customers before asking for a review is called review gating and goes against Google’s review policies. Ask every customer and handle complaints personally.

Should I use HighLevel’s built-in AI or ChatGPT, Claude or Grokbot?

Either can work. Many businesses draft messages and checklists in their usual AI assistant, then build them in GHL. Check what your HighLevel plan includes before relying on its built-in AI features.

What’s the best first job to automate in GoHighLevel?

Whichever one loses you the most work today. For many service businesses that’s quote follow-up, because the leads are already in the pipeline and just need a nudge.

Make GoHighLevel finally run itself

Grab the free CRM agent pack: AI agents for lead replies, follow-ups and pipeline updates, with no weekend workflow building. Prefer a hand? Book a free 15-minute AI workflow audit and we’ll find your first quick win.

Get the free CRM agent pack or book a free AI audit

Independent AI agents. Not affiliated with or endorsed by HighLevel.

HubSpot AI agents illustration: a generic CRM pipeline board with New lead, Contacted, Follow-up and Won columns, where the Follow-up column glows with an AI sparkle and AI draft ready labels

If you’re paying for HubSpot every month and still typing notes after every call, chasing quotes from memory and onboarding new clients with a copy-pasted email, you’re not alone. A CRM is only as good as what goes into it, and for most small businesses the bit that goes in is the bit nobody has time for.

The good news is you don’t need a bigger plan or a new system to fix it. You can hand the repetitive writing and chasing to AI agents and keep HubSpot as the place where everything lives. In this post I’ll show you what HubSpot already does well, where the gaps usually are, three jobs to give AI first, where the AI actually sits, and how to keep your data clean while you do it.

Quick note: I’m independent and not affiliated with or endorsed by HubSpot. HubSpot is a trademark of HubSpot, Inc.

What HubSpot does well (and where the gaps are)

HubSpot is very good at being the single source of truth for your contacts, deals and conversations. You can see who enquired, what stage their deal is at, which emails they opened and who on your team is responsible. For a small business, that alone is a big step up from a spreadsheet and a full inbox.

HubSpot also has its own AI now. Its Breeze Assistant page says Breeze Assistant is included with every HubSpot subscription at no extra cost, and its AI agents page describes pre-built agents and an agent builder. Some of those features need a Starter, Professional or Enterprise subscription, and custom agents use HubSpot Credits, so check what your plan includes before you count on them.

So where are the gaps? In my experience they’re rarely about features. They’re about the work around the CRM:

  • Replies are slow. A new enquiry lands in HubSpot, but someone still has to write the first reply, and that person is on the tools or with a client.
  • Follow-up depends on memory. Quotes go out and nobody chases them, because the follow-up tasks pile up faster than anyone clears them.
  • Onboarding is ad hoc. Every new client gets a slightly different welcome, and the details you need from them arrive in dribs and drabs.
  • Records go stale. Notes don’t get logged, deal stages don’t get moved, and the pipeline report stops matching reality.

None of those are HubSpot problems. They’re time problems, and they’re exactly the sort of repetitive, text-heavy jobs AI is good at.

Three jobs to hand to AI first

Don’t try to automate your whole CRM in one go. Pick one of these, get it working, then add the next.

1. The first reply to a new lead

When a lead comes in, an AI agent can read the enquiry and draft a friendly, specific reply based on your services, service area and pricing rules. You check it and send it, or for simple enquiries you let it go out once you trust it. The reply then gets logged against the contact in HubSpot so everyone can see it.

The key is giving the agent good information: what you do and don’t do, the areas you cover, how you price, and when it must hand over to a person. I go into the details in my post on replying to every enquiry fast with AI.

2. Follow-up on quotes and quiet deals

Most deals that go cold weren’t lost. Nobody followed up. An AI agent can look at deals that have sat in the same stage for a few days and draft a short, personal follow-up using the notes on that deal. A simple cadence such as day 1, day 3 and day 7 works for a lot of businesses, and the agent should stop as soon as the person replies or says no.

Because the drafts come from the deal notes, they don’t read like a template. If you want the full approach, see how to follow up leads with AI without being pushy.

3. Onboarding new clients

When a deal moves to won, an AI agent can draft the welcome email, a checklist of what you need from the client, and the first few tasks for your team. It pulls the client’s name, the job and any special notes from the HubSpot record, so each welcome feels personal without you writing it from scratch.

Where the AI actually sits

This is the part that confuses people, so let me keep it simple. There are two common ways to set this up, and you can start with the first and move to the second later.

Option A: AI drafts, you paste into HubSpot

You keep your AI assistant open beside HubSpot. You paste in the enquiry or the deal notes, the assistant drafts the reply or follow-up, you check it and paste it into HubSpot to send or log. It sounds basic, but it’s the fastest way to start, it costs nothing extra, and you stay in full control of every message.

This is how the Steal My AI Agents pack works. Each agent is a set of plain-English instructions you load into ChatGPT, Claude, Grokbot or any AI assistant, so there’s nothing to install.

Option B: AI connected to HubSpot

Once the drafts are reliably good, you can connect the AI to HubSpot so it reads new records and writes notes, tasks or drafts straight back. That might be through HubSpot’s own agents, or an AI assistant that’s been given access to your account. Either way, the same rule applies: start with the agent creating drafts and tasks for a person to approve, and only let it act on its own once you’ve tested it on real examples.

Guardrails that apply either way

  • Decide what the AI may never send without a person checking it, such as pricing, complaints or anything legal.
  • Give it a clear hand-over rule: if it isn’t sure, it flags the record for a human.
  • Only give it access to the data it needs for the job.

If you’re weighing up the data side, my post on whether AI is safe for small business covers what to check.

Keeping your data clean

AI is only as good as the records it reads. If your contacts have no notes and your deal stages are a guess, the drafts will be generic. A few habits make a big difference:

Agree on your deal stages

Write down what each stage means in one line, for example “Quote sent: the quote has been emailed and we’re waiting on a yes or no”. When everyone uses the stages the same way, an agent can safely pick out the deals that need chasing.

Log a short note after every conversation

Even two lines helps: what they want, what you promised, and the next step. You can dictate a rough note and have AI tidy it into a clean summary before it goes into HubSpot. I cover this in how to keep your CRM up to date with AI.

Use the fields you already have

Service type, suburb and lead source are usually enough for an agent to personalise a message. Fill those in consistently before you add more custom fields.

Review weekly

Spend ten minutes a week looking at what the agent drafted and what actually went out. Fix the instructions when something’s off. That small habit is what turns a clever experiment into something your team relies on.

What to do this week

  1. Pick one job. First reply, follow-up or onboarding. Choose the one that costs you the most time or the most lost work.
  2. Write down your rules. Services, areas, pricing basics, tone, and what must always go to a person.
  3. Run it in your AI assistant for a week. Paste in real enquiries or deal notes, check every draft, and log what you send in HubSpot.
  4. Tidy the records it relies on. Agree on your deal stages and start logging short notes.
  5. Decide on the next step. If the drafts are consistently good, look at connecting the AI to HubSpot or adding the next job.

If you’d like the instructions already written, the free CRM agent pack for HubSpot gives you agents for lead replies, follow-ups and keeping records complete on the plan you already have.

FAQ

Do I need a higher HubSpot plan to use AI agents?

Not to get started. You can run AI agents in your own AI assistant and paste the results into HubSpot on any plan. HubSpot’s own agents and agent builder have their own plan and credit requirements, so check HubSpot’s pricing pages for your account.

Will AI send messages to my customers without me knowing?

Only if you set it up that way. Start with the AI creating drafts that a person checks and sends. Once you trust it on simple messages, you can decide which ones, if any, it may send on its own.

Is it safe to paste customer details into an AI assistant?

Use a business account with data controls switched on, share only what the job needs, and check the provider’s privacy settings. Avoid pasting sensitive information such as health or financial details unless your setup is approved for it.

Should I switch CRMs to get better AI?

Usually not. Switching costs time and money, and the gaps are rarely the CRM itself. Adding AI to the work around HubSpot, such as replies, follow-ups and notes, is normally the quicker win.

What’s the best first job to give AI in HubSpot?

Whichever one loses you the most work today. For many small businesses that’s following up quotes, because the deals are already in the pipeline and just need a nudge.

Get more out of HubSpot without upgrading

Grab the free CRM agent pack: AI agents for lead replies, follow-ups and complete records that work with the HubSpot plan you already have. Prefer a hand? Book a free 15-minute AI workflow audit and we’ll find your first quick win.

Get the free CRM agent pack or book a free AI audit

Independent AI agents. Not affiliated with or endorsed by HubSpot.

Dark blue gradient graphic with the headline Hand over work before holidays beside a mock holiday handover card listing coverage dates, open work owners and when to call, marked Checked

Every year it’s the same story. The Christmas break is a couple of weeks away, everyone’s flat out trying to finish jobs, and the handover gets squeezed into the last afternoon before you lock up. Then on 2 January someone’s ringing you at the beach because nobody knows where the supplier quote is, which customer was promised a callback, or what the password is for the booking system.

In this post I’ll show you how to hand over work before holidays with AI. You do a quick brain dump, let your assistant turn it into a clear handover with a coverage checklist and a who-owns-what list, then you check it and send it. It works with ChatGPT, Claude, Grokbot or any AI assistant you already use, and it takes an hour or two instead of a frantic afternoon.

Why holiday handovers go wrong

Most small business handovers don’t fail because people don’t care. They fail because the important stuff lives in your head, and writing it down feels like a job for later. The common problems:

  • The handover is written at the last minute, so it’s rushed and patchy
  • It lists tasks but not the context: who the customer is, what was promised, what “done” looks like
  • Nobody is clearly named as owner, so two people do the same thing or nobody does it
  • It doesn’t say what to do when something goes wrong, so the default is “call the boss”
  • Logins and access are left out, or worse, pasted into an email

AI won’t magically know what’s going on in your business. What it’s very good at is taking a messy dump of everything you’ve said and turning it into a tidy, consistent document that someone else can actually follow. You supply the facts. It supplies the structure.

What a good holiday handover includes

Before you open your AI assistant, it helps to know what you’re aiming for. A useful handover has five parts:

  1. Dates and coverage: who’s away when, who’s covering, and when the business is closed, open or on reduced hours
  2. Open work: every job, quote or customer conversation that’s still live, with where it’s up to and the next step
  3. Who owns what: one named person for each item, plus a backup
  4. What can wait: things that don’t need touching until you’re back, so nobody wastes time on them
  5. When to call: the short list of situations that are genuinely worth interrupting your holiday for, and how to reach you

If your handover covers those five things clearly, the person covering can make good decisions without guessing.

How to hand over work before holidays with AI

Step 1: Do a brain dump, not a document

Don’t try to write the handover yourself. Instead, spend fifteen or twenty minutes getting everything out of your head in whatever form is fastest. You can type rough notes, use voice dictation on your phone while you drive, or talk through your week out loud and paste in the transcript.

Go through the places work hides:

  • Your inbox, especially anything flagged or waiting on a reply
  • Your calendar for the weeks you’re away and the first week back
  • Open quotes, jobs and invoices in your job management or accounting software
  • Promises you’ve made on the phone (“I’ll get back to you after Christmas”)
  • Recurring tasks: payroll, BAS reminders, supplier orders, social posts, backups

Don’t worry about order or spelling. Messy is fine. The goal is to get it all out so nothing lives only in your head.

Step 2: Ask AI to turn it into a structured handover

Paste your brain dump into your AI assistant with a clear prompt. Something like this:

I’m going on holiday from [date] to [date]. [Name] is covering for me. Below are my rough notes about open work. Turn them into a handover document with these sections: dates and coverage, open work (one item per row with customer or project, where it’s up to, next step, due date and owner), recurring tasks during the break, things that can wait until I’m back, and when to call me. Use plain Australian English. Don’t add anything that isn’t in my notes. If something is unclear or missing, list it as a question at the end instead of guessing.

That last instruction matters. You want the AI to flag gaps, not fill them with confident guesses. A handover with a made-up due date is worse than one with a question mark.

Step 3: Build the coverage checklist

Next, ask for a simple coverage checklist for the whole break. For example:

Using the handover above, create a day-by-day coverage checklist for the break. For each working day, list who’s on, what needs checking (inbox, phones, website enquiries, bookings) and any task due that day. Mark the public holidays and days we’re closed.

You’ll get a one-page view of the break that anyone can follow. Check the dates against your own calendar and your state’s public holidays, because AI can get those wrong. It’s your job to confirm them, not the assistant’s.

Step 4: Make the who-owns-what list

Ownership is where handovers usually fall apart, so give it its own list. Ask the AI to pull every item from the handover into a short table: the task, the owner, the backup, and how the owner will know it’s done. If there’s only one person covering, that’s fine. The table still makes it obvious when one person has been handed too much.

Look down the list and ask yourself one honest question: if this person is sick on day two, does anyone else know what to do? If the answer is no, add a backup or move the task to “can wait”.

Step 5: Write the “when to call me” rules

This is the bit that protects your holiday. Ask the AI to help you draft a short list of situations worth interrupting you for, and a longer list of situations the person covering can handle on their own. You might decide:

  • Call me: a safety issue, a major customer complaint, anything involving a large payment or contract
  • Message me, no rush: a new enquiry that looks big, a supplier problem that can wait a day
  • Handle it yourself: routine questions, rebooking, small refunds within an agreed limit

Those categories are only examples. You set the rules and the limits. The AI just helps you write them clearly so there’s no grey area.

Step 6: Draft the customer and supplier messages

While you’ve got the context loaded, get the AI to draft the messages you’ll need: your out-of-office reply, a holiday hours note for your website and Google Business Profile, a short email to key customers with open jobs, and a reminder to suppliers about your closure dates. Read each one before it goes anywhere. You’re sending these under your name, so they need to sound like you and be accurate.

Step 7: Check it, then walk the person through it

AI gets you a strong first draft, but it doesn’t know what it doesn’t know. Read the whole handover with the person covering, ideally a few days before you leave rather than on the last afternoon. Go through the questions the AI flagged, fix anything wrong and let them ask their own questions. Twenty minutes of walking through it together beats a perfect document nobody has read.

A note on passwords and private information

Don’t paste passwords, banking details or sensitive customer information into an AI chat, and don’t put them in the handover document either. Instead, note in the handover where access lives, for example “booking system login is in the shared password manager”, and set up that access before you leave. If you don’t use a password manager yet, the holiday break is a good reason to start.

Also check your AI tool’s privacy settings and your own business rules before pasting customer details. Where you can, use first names or job numbers instead of full customer details in your brain dump.

Turn it into a template you reuse

Once you’ve done this once, save the prompts and the final handover as a template. Next time someone goes on leave, whether it’s Christmas, school holidays or a sick week, you start from the template instead of a blank page. You can even set it up as a simple AI agent: a saved set of instructions your assistant follows every time you paste in a brain dump, so the handover always comes out in the same format.

Frequently asked questions

How long does this take?

For most small businesses, the brain dump takes fifteen to thirty minutes, and turning it into a handover with AI takes another half an hour or so, plus time to check it. Allow longer the first time while you work out your prompts.

Which AI assistant should I use?

Any of the main ones will do the job: ChatGPT, Claude, Grokbot or another assistant you’re comfortable with. Clear notes and a good prompt matter far more than the tool.

What if I’m a sole trader with nobody to hand over to?

The same process still helps. Use it to write a clear “what happens while I’m away” plan: your out-of-office message, which enquiries can wait, and a list of what to pick up first when you’re back. Your future self is the person you’re handing over to.

Can AI work out what’s open by reading my inbox?

Some assistants can connect to email and calendars, which can help you find things you’ve forgotten. Treat what it finds as a starting list to check, not the final word, and only connect tools you’re comfortable giving access to.

Should I send the handover by email?

Put it somewhere shared that the person covering can find easily, like a shared drive or your team’s usual workspace, and send them the link. That way you can update one copy if something changes before you leave.

What should never go in the handover?

Passwords, full banking details and sensitive customer information. Say where access lives instead, and make sure the person covering can get in before you go.

Want a calmer break this year?

If you’d like help working out which parts of your business only run when you’re there, and which jobs AI can take off your plate, book an AI audit and we’ll go through it together. Or, if you’d rather start yourself, grab the AI agents pack. It works with ChatGPT, Claude, Grokbot or any AI assistant, and you can have your first agent running this week.

Dark blue gradient graphic with headline Build a team FAQ with AI beside a mock Team FAQ card grouping customer questions under Pricing, Timing and After-sales with an Approved badge

You already know the questions. “How much does it cost?” “Do you service my area?” “How long does it take?” “What happens if something goes wrong?” Your team answers them every week by email, by phone and in website chat. The trouble is, everyone answers them a little differently, and the good answers live in someone’s sent folder instead of somewhere the whole team can find them.

In this post I’ll show you how to build a team FAQ from real customer questions with AI. You collect the questions customers actually ask, let your assistant group them and draft answers, then you approve every answer before anyone uses it. It works with ChatGPT, Claude, Grokbot or any AI assistant you already use, and you can have a first version done in an afternoon.

Why most FAQs don’t help

Plenty of small businesses have an FAQ page. Very few have one that matches what customers really ask. The usual problems:

  • It was written once, at launch, from guesses about what people might ask
  • It answers questions nobody asks and skips the ones that land in the inbox daily
  • Staff don’t use it, so they rewrite the same reply from scratch each time
  • Answers drift out of date when prices, service areas or policies change

The fix is to flip the order. Start with the real questions, then write the answers. AI is very good at the boring middle part: sorting a pile of messy messages into clear groups and drafting a first answer for each. You’re good at the part that matters most, which is making sure every answer is true.

What a useful team FAQ looks like

A team FAQ isn’t just a public web page. It’s the shared set of approved answers your team pulls from when replying to customers. Each entry should have:

  1. The question, written the way customers actually phrase it
  2. A short approved answer, two to four sentences in plain English
  3. A longer version, if the topic needs detail or steps
  4. An owner, the person who checks it stays accurate
  5. A “last checked” date, so you know when it might be stale

Some entries can go straight onto your website. Others, like how you handle refunds case by case, stay internal. Decide that per question, not all at once.

How to build a team FAQ from real customer questions with AI

Step 1: Collect the questions customers actually ask

Pick a window, say the last 60 to 90 days, and pull questions from the places customers reach you:

  • Your enquiry inbox and general email
  • Website chat transcripts and contact form submissions
  • Social media DMs and comments
  • Notes from phone calls, if your team jots them down
  • Questions that come up on sales calls (related: prep for a sales call with AI)

You don’t need the whole conversation. Copy just the customer’s question into a document, one per line. Remove names, phone numbers, addresses and anything else personal as you go. If a question appears ten times, keep a few copies, because frequency is useful information.

Step 2: Ask AI to group the questions

Open your assistant and paste the list with a prompt like this:

“Below is a list of real questions customers have asked my small Australian business, one per line, with personal details removed. Group them into themes (for example pricing, timing, service area, process, after-sales). For each theme, list the distinct questions in plain customer wording, merge near-duplicates, and show roughly how many times each came up in this list. Don’t add questions that aren’t in the list. Use Australian English.”

Read the groups. Merge anything that’s really the same question and split anything that’s two questions stuck together. This list is now your FAQ outline, ordered by what comes up most.

Step 3: Give AI the facts, then ask for draft answers

This is where most people go wrong. If you just ask AI to “answer these questions”, it will make up prices, timeframes and policies that sound plausible. Instead, give it your real facts first: your price list or ranges, service areas, standard turnaround, warranty and refund terms, and how you like to talk to customers. Then:

“Using only the business facts I’ve provided above, write a draft answer for each question in the FAQ outline. Give a short answer (2–4 sentences) and, where helpful, a longer version with steps. Plain Australian English, friendly and direct. If my facts don’t cover a question, write NEEDS ANSWER instead of guessing. Never invent prices, timeframes, guarantees, stats or customer results.”

The “NEEDS ANSWER” rule is the most important line in the prompt. Every gap it flags is a question your team has been answering inconsistently, and that’s worth knowing.

Step 4: Approve every answer

Go through the drafts one by one. For each answer, check:

  • Is every fact right, including prices, areas and timeframes?
  • Does it promise anything you don’t actually guarantee?
  • Does it sound like your business, not a brochure?
  • Is there anything that should stay internal rather than go on the website?

Fill in the NEEDS ANSWER gaps yourself, or ask the person in your team who knows. Then mark each entry approved, with an owner and today’s date. Anything not approved doesn’t get used. That’s the rule that keeps the FAQ trustworthy.

Step 5: Put it where your team will use it

An FAQ that sits in a forgotten folder is no better than none. Store the approved version somewhere your team already works: a shared doc, your help desk’s saved replies, or your CRM’s templates. Publish the customer-safe entries on your website too. If you write process documents for the team, the same approach works there (see write SOPs with AI).

A fuller prompt you can save

Once you’ve done this once, save a reusable prompt for adding new questions as they come in:

“Role: FAQ assistant for a small Australian business. Inputs: our approved FAQ, our business facts, and a list of new customer questions. Tasks: 1) Match each new question to an existing FAQ entry if one already answers it. 2) For genuinely new questions, draft a short and long answer using only our facts. 3) Flag any existing answer that seems to conflict with the facts or looks out of date. Rules: plain Australian English; never invent prices, timeframes, guarantees, stats, quotes or results; write NEEDS ANSWER where our facts don’t cover it; flag any personal information in the input so I can remove it.”

Prompts for common FAQ jobs

  • Turn an FAQ into email replies: “Using this approved FAQ answer, write a short reply to this customer’s email. Keep the facts exactly as approved. Don’t add new promises.”
  • Find gaps: “Compare this month’s customer questions with our FAQ. List questions we don’t cover yet, ordered by how often they came up.”
  • Spot stale answers: “Here are our updated prices and policies. List every FAQ answer that no longer matches and suggest the fix.”
  • Write the website version: “From the approved FAQ entries marked public, write a website FAQ section with clear headings. Keep answers short and keep every fact as approved.”
  • Train a new starter: “Turn our FAQ into a 15-question quiz with answers, so a new team member can check they know our standard replies.”

What to leave out of the AI chat

Customer messages are full of personal information. Before you paste anything:

  • Strip names, emails, phone numbers and addresses from every question
  • Remove order numbers, account details and payment information
  • Leave out health, financial or other sensitive details customers mentioned
  • Only paste the question itself, not the whole thread

For Australian businesses, the Office of the Australian Information Commissioner (OAIC) has practical guidance on using AI tools with personal information: OAIC guidance on privacy and commercially available AI products. It’s worth a read before this becomes a team habit.

Keep the FAQ alive

The first version is the hard part. Keeping it useful takes about 20 minutes a month:

  1. Once a month, collect new customer questions from the inbox and chat
  2. Run them through your saved FAQ prompt to find matches and gaps
  3. Approve new answers and update anything flagged as out of date
  4. Whenever prices or policies change, update the FAQ the same day
  5. Ask your team which questions they still answer from scratch, and add those

Over time, the questions that keep coming up tell you something. If everyone asks the same thing before buying, that answer probably belongs on your website, your quote template or your sales page, not just in the FAQ.

Frequently asked questions

How many questions do I need to start?

Thirty to fifty real questions is plenty for a first version. You’ll usually find they boil down to ten or fifteen distinct topics. Start small and add as new questions arrive.

Which AI assistant should I use?

Any of the main ones will do: ChatGPT, Claude, Grokbot or another assistant you’re comfortable with. The real questions, your facts and your approval matter far more than the tool.

Can AI just write the FAQ without my input?

It can write something, but it will guess at your prices, policies and timeframes. That’s how a wrong answer ends up in front of a customer. Give it your facts, and approve every answer before it’s used.

Should the team FAQ and the website FAQ be the same?

Mostly, but not completely. Keep one approved source and mark each entry public or internal. Things like case-by-case refund handling or escalation steps usually stay internal.

How do I stop answers going out of date?

Give each entry an owner and a “last checked” date, and update the FAQ whenever prices or policies change. A quick monthly review catches the rest.

Can I use the FAQ to power a website chatbot?

Yes, an approved FAQ is a good starting point for a website chat assistant, because it gives the bot real answers to work from. Keep a person in the loop for anything the FAQ doesn’t cover.

Want help turning your inbox into answers?

If you’d like help working out which customer questions are worth answering once and reusing, and which other admin AI can take off your plate, book an AI audit and we’ll go through it together. Or, if you’d rather start yourself, grab the AI agents pack. It works with ChatGPT, Claude, Grokbot or any AI assistant, and you can have your first agent running this week.

Dark blue gradient card with headline Prep for a sales call with AI beside a mock Prep checklist showing Research, Agenda and Objections with a Checked badge

Most sales calls don’t fall apart because you don’t know your product. They fall apart because you walked in cold. You skimmed the lead form on the way to the Zoom link, forgot what they said three weeks ago, and spent the first ten minutes reconstructing context instead of listening. The prospect notices. You feel it too.

In this post I’ll show you a simple way to prep for a sales call with AI. You take the notes you already have — the form fill, the last email, a LinkedIn bio, a past call summary — and ask your assistant to draft a research brief, an agenda and likely objections. You check every line. You stay in control of what you send and what you say. It works with ChatGPT, Claude, Grokbot or any AI assistant you already use.

Why sales call prep gets skipped

In a small business, the person on the call is often also the person who wrote the quote, answered the inbox and ran the last delivery. Prep gets squeezed. Common shortcuts:

  • Open the CRM two minutes before the call and hope the last note is useful
  • Re-read the original enquiry and nothing else
  • Wing it because “we’ve spoken before”
  • Skip prep entirely when the calendar is packed

None of that is laziness. It’s load. The fix isn’t a longer prep ritual — it’s a short, repeatable one that turns scattered notes into something you can actually use in five minutes.

What “good” prep looks like

Before a sales or discovery call, you want one page (or less) that covers four things:

  1. Who they are — company, role, what they do, why they reached out
  2. What we already know — past emails, quotes, open issues, promises made
  3. Agenda — three to five topics you’ll cover, in order
  4. Likely objections — price, timing, fit, internal buy-in — with plain-English responses you can adapt

If you have that, you walk in calm. You listen better because you’re not hunting for context mid-call. AI is good at assembling this shape from messy input. You are good at checking that nothing was invented and that the tone matches how you actually talk.

How to prep for a sales call with AI

Step 1: Gather what you already have

Don’t start researching the whole internet. Start with public or first-party notes you already own:

Paste only what you need. Strip passwords, private account numbers and anything personal that isn’t required for the call. The goal is a clean brief, not a data dump.

Step 2: Ask for a research brief — not a novel

Open ChatGPT, Claude, Grokbot or whichever assistant you use, and paste your notes with a prompt like this:

“You’re helping me prep for a sales / discovery call for my small Australian business. Below are notes I already have about the prospect (enquiry, emails, CRM notes, public bio). Produce a one-page prep brief with: 1) Who they are (2–4 sentences), 2) What we already know / promised, 3) Open questions I still need answered on the call, 4) Suggested agenda (3–5 items), 5) Likely objections with a short plain-English response I can adapt. Use Australian English. Do not invent company facts, stats, testimonials or results I didn’t provide. If something is missing, mark it as Unknown. End with a 5-bullet ‘walk-in checklist’.”

That “Unknown” rule matters. A tidy brief full of guesses is worse than a short brief with honest gaps.

Step 3: Check every claim before you rely on it

AI will happily fill holes. Read the draft and check:

  • Did it invent a company size, revenue figure or industry claim?
  • Did it turn a maybe into a promise you supposedly made?
  • Are the objections grounded in what they actually said, or generic filler?
  • Is anything confidential that shouldn’t sit in this chat?

Fix those, then ask: “Update the brief with my corrections. Keep the same five sections. Don’t add new facts.”

Step 4: Lock the agenda and objection notes

Copy the agenda into your calendar invite notes or a sticky you keep beside the screen. Keep objection responses as bullet prompts, not scripts — you want to sound like yourself, not a brochure. If a quote is likely to come next, have your numbers ready; for faster quoting after the call, see write quotes faster with AI.

Step 5: After the call, close the loop the same day

Prep is half the job. Within an hour of hanging up, dump a short voice note or bullets into your assistant: what they said, what you promised, next step with date. Update the CRM. Send the follow-up while the call is still warm — related reading: follow up leads with AI.

“From these post-call notes, list: pain points confirmed, what I promised to send, next step with owner and date, and anything still unclear before I quote. Don’t invent numbers or commitments.”

A fuller prompt you can save

Once you’ve done this a few times, save a reusable prep prompt so you’re not rewriting it every call:

“Role: sales-call prep assistant for a small Australian business. Input: enquiry, emails, CRM notes and any public bio I provide. Output only: Who they are | What we already know / promised | Open questions for the call | Agenda (3–5 items) | Likely objections with short adaptable responses | Walk-in checklist (5 bullets). Rules: plain Australian English; never invent company facts, stats, quotes, testimonials or results; mark missing facts as Unknown; flag anything that looks like personal or sensitive data so I can remove it before sharing. Ask me up to three clarifying questions only if a promised next step or decision-maker is genuinely ambiguous.”

Paste that once at the top of a chat, then drop each prospect’s notes underneath. Same structure every time means your prep stays short and scannable.

Prompts for common call types

  • First discovery call: “From this enquiry and email thread, draft who they are, what problem they named, open questions, a 4-item agenda, and three likely objections. Mark unknowns. Don’t invent budget.”
  • Quote review call: “Using the quote notes and their last email, list what they liked, what they pushed back on, open questions, and a short agenda focused on deciding next steps. Don’t invent discounts.”
  • Renewal / upsell chat: “From CRM notes and recent support emails, summarise current relationship, open issues, what we’ve delivered that they valued (only from my notes), and likely concerns about renewing.”
  • Partner / referral intro: “From the referrer’s note and the prospect’s public bio, draft a short who-they-are, why they were referred, open questions, and a light agenda. Don’t invent the referral reason.”
  • Re-engage cold lead: “From the old enquiry and last contact date, summarise what they asked for then, what might have changed (Unknown if not said), and a short re-intro agenda. Don’t invent why they went quiet.”

What to leave out of the AI chat

Sales notes often include things that shouldn’t go into a general AI tool. Before you paste:

  • Strip passwords, one-time codes and private account details
  • Remove home addresses, health notes, payroll or bank details you don’t need for the brief
  • Don’t paste full contracts just to extract “next meeting Tuesday”
  • Use initials or project codes when a full name isn’t required

For Australian businesses, the Office of the Australian Information Commissioner (OAIC) publishes practical guidance on using commercially available AI products with personal information — worth a read before you make this a team habit: OAIC guidance on privacy and commercially available AI products. When in doubt, keep the AI input to business context and leave sensitive detail in your own systems.

Make prep a habit, not a scramble

The workflow only pays off if you do it every time. A simple rule that works for most owners:

  1. Block five to ten minutes before every sales or discovery call
  2. Paste what you already have into your saved prep prompt
  3. Check the brief — especially Unknowns and objections — then walk in
  4. After the call, capture notes and send the follow-up the same day
  5. Once a week, skim open next-steps in your CRM or task list and chase what’s still hanging

If the same objections keep showing up, that’s useful product feedback — not just sales noise. Capture them and review in your weekly ops pass.

Frequently asked questions

Do I need to scrape the prospect’s whole website?

No. Start with what you already have. A public About page or LinkedIn bio you’ve already opened is enough. More data isn’t better if it invents a story you then believe.

Which AI assistant should I use?

Any of the main ones will do — ChatGPT, Claude, Grokbot or another assistant you’re already comfortable with. The prompt and your check matter more than the brand.

What if I have almost no notes on the prospect?

Say so in the prompt and ask for an agenda and open questions only. Mark company facts as Unknown. A short honest brief beats a long invented one.

Should I read the AI script word-for-word on the call?

No. Use the agenda and objection bullets as prompts. Talk like yourself. Scripts sound like scripts.

Is it okay to paste client names into the AI tool?

Be careful. For many tools, treat anything you paste as data you wouldn’t mind a third party processing. Use initials or project codes when you can, strip personal details, and follow the OAIC guidance linked above. When the notes are sensitive, keep the AI step on a tool your business has reviewed.

Can my team use the same prep prompt?

Yes — and they should. Save the fuller prompt in a shared doc so every call brief looks the same. Consistency makes handovers easier and stops prep quality depending on who is free that hour.

Want this running as a repeatable habit?

If you’d like help mapping which calls are worth prepping this way, and which other admin AI can take off your plate, book an AI audit and we’ll walk through it together. Or, if you’d rather start yourself, grab the AI agents pack. It works with ChatGPT, Claude, Grokbot or any AI assistant, and you can have your first agent running this week.

Dark blue gradient card with headline Turn meeting notes into actions with AI beside a mock wrap-up showing Decisions, Actions and Open questions with a Checked badge

After almost every meeting I sit in with small business owners, the same thing happens. Someone closes the laptop, everyone nods, and the notes sit in a phone, a scrap of paper or a half-finished Google Doc. Decisions were made. Jobs were handed out. Deadlines were mentioned. A week later, half of it has slipped. Not because anyone is lazy — because the notes never turned into a clear action list.

In this post I’ll show you a simple way to turn meeting notes into actions with AI. You dump the rough notes or transcript in, the AI pulls out decisions, owners, deadlines and open questions, you check the list, and you send a short action summary. It works with ChatGPT, Claude, Grokbot or any AI assistant you already use. You stay in charge of what goes out.

Why meeting notes die on the vine

Most small businesses don’t have a dedicated note-taker. The person running the meeting is also trying to think, talk and write. So the notes end up as:

  • Bullet points with no owners (“follow up quote”)
  • Half-sentences only the writer understands
  • A long transcript nobody will re-read
  • Nothing at all — “we’ll remember”

When the next meeting rolls around, people spend the first ten minutes reconstructing what was agreed last time. That’s wasted time you can get back with a short, repeatable habit.

What “good” looks like after a meeting

A useful meeting wrap-up is one page or less. It has four parts:

  1. Decisions — what we agreed, in plain English
  2. Actions — who does what, by when
  3. Open questions — things we still need to answer
  4. Parking lot — ideas raised that aren’t for this week

If your wrap-up has those four, anyone who missed the meeting can catch up in two minutes. That’s the bar. AI is good at building this shape from messy input. You are good at checking that the names, dates and wording match what actually happened.

How to turn meeting notes into actions with AI

Step 1: Capture something — anything

You don’t need a perfect transcript. Pick one capture method and stick to it:

  • Handwritten or typed bullets during the meeting
  • Voice notes you dictate into your phone right after
  • A meeting transcript from your video call tool (if you already have one)
  • A rough email you send yourself with “stuff we said”

The messier the capture, the more useful the AI step. Don’t polish first. Get it out of your head while it’s still fresh — ideally within an hour of the meeting ending.

Step 2: Paste it into your AI assistant with a clear ask

Open ChatGPT, Claude, Grokbot or whichever assistant you use, and paste your notes with a prompt like this:

“You’re helping me turn rough meeting notes into a clear action list for my small business. Below are my messy notes / transcript from a meeting about [topic]. Extract and organise into four sections: 1) Decisions (what we agreed), 2) Actions (owner, task, deadline — if a deadline wasn’t said, mark Deadline: not set), 3) Open questions, 4) Parking lot. Use plain Australian English. Don’t invent owners, dates or decisions I didn’t mention. If something is unclear, put it under Open questions instead of guessing. End with a short ‘send-ready’ summary I can paste into email or chat.”

That last instruction matters. You want something you can send, not a long report.

Step 3: Check every line before anyone else sees it

AI is fast at sorting. It is also happy to invent a tidy story when your notes are vague. Read the draft and check:

  • Are the owners right? (Not “the team” — a real name)
  • Are the deadlines real, or did the AI fill one in?
  • Did it turn a maybe into a decision?
  • Is anything confidential that shouldn’t leave this chat?

Fix those, then ask: “Update the list with my corrections and keep the same four sections.”

Step 4: Send a short action list the same day

Copy the send-ready summary into email, Slack, Teams or your project tool. Keep it short. Something like:

“Quick wrap from today’s meeting. Decisions: … Actions: Sam — send revised quote by Friday; Alex — update CRM notes today. Open: do we want to include the March option? Ping me if I’ve got an owner or date wrong.”

Sending it the same day is the whole game. A perfect list next week is less useful than a good-enough list today.

Step 5: Drop actions into wherever you already track work

If you use a CRM, a shared task board or a simple spreadsheet, move each action there with the owner and date. If you don’t have a tracker yet, the action email itself is fine for a while. The point is that actions leave the notes and land somewhere people look. Related reading: keep your CRM up to date with AI and run a weekly business review with AI.

A fuller prompt you can save

Once you’ve done this a few times, save a reusable prompt so you’re not rewriting it every meeting:

“Role: meeting wrap-up assistant for a small Australian business. Input: rough notes or transcript. Output only: Decisions | Actions (Owner — Task — Deadline) | Open questions | Parking lot | Send-ready summary (under 150 words). Rules: plain Australian English; never invent owners, deadlines or decisions; mark missing deadlines as ‘not set’; flag anything that sounds like personal or sensitive data so I can remove it before sharing. Ask me up to three clarifying questions only if a decision or owner is genuinely ambiguous.”

Paste that once at the top of a chat, then drop each meeting’s notes underneath. Same structure every time means people know what to expect.

Prompts for common meeting types

  • Sales / discovery call: “From these notes, list: prospect pain points, what we promised to send, next step with owner and date, and anything we still need to confirm before quoting.”
  • Internal ops meeting: “Turn these notes into actions only. Drop discussion. One line per action: Owner — Task — Deadline. Flag anything with no owner.”
  • Client project check-in: “Extract decisions that change scope, budget or timeline. List client asks separately from our internal actions.”
  • Hiring / interview debrief: “Summarise strengths, concerns and agreed next step. Do not invent ratings. Keep candidate personal details out of the send-ready summary.”
  • Board or advisor catch-up: “List decisions and open questions only. Keep the send-ready summary under 100 words.”

What to leave out of the AI chat

Meeting notes often include things that shouldn’t go into a general AI tool. Before you paste:

  • Strip passwords, one-time codes and private account details
  • Remove or blur personal information you don’t need for the action list (home addresses, health notes, payroll figures)
  • Don’t paste full contracts or bank details just to extract “send the invoice”

For Australian businesses, the Office of the Australian Information Commissioner (OAIC) publishes practical guidance on using commercially available AI products with personal information — worth a read before you make this a team habit: OAIC guidance on privacy and commercially available AI products. When in doubt, keep the AI input to decisions and tasks, and leave sensitive detail in your own systems.

Make it a habit, not a one-off

The workflow only pays off if you do it every time. A simple rule that works for most owners:

  1. End every meeting with two minutes of capture (bullets or a voice note)
  2. Run the AI wrap-up before you open the next app
  3. Send the action list before you leave the desk (or the car park)
  4. Once a week, skim last week’s actions in your weekly review and chase what’s still open

If the same kind of meeting keeps producing the same open questions, that’s a process gap — the kind you can turn into a short SOP later. See how to write SOPs with AI.

Frequently asked questions

Do I need a fancy meeting transcription tool?

No. Rough bullets or a voice note after the meeting are enough. A transcript helps if you already have one, but it’s not required. The AI step works on messy input.

Which AI assistant should I use?

Any of the main ones will do — ChatGPT, Claude, Grokbot or another assistant you’re already comfortable with. The prompt and your check matter more than the brand.

What if nobody was assigned an owner in the meeting?

Don’t let the AI invent one. Put those items under Open questions or mark Owner: not set, then decide before you send. A list with honest gaps is better than a tidy list with the wrong names.

How long should the send-ready summary be?

Under about 150 words. If people need the full detail, they can ask. The wrap-up’s job is to make the next steps obvious.

Is it okay to paste client names into the AI tool?

Be careful. For many tools, treat anything you paste as data you wouldn’t mind a third party processing. Use initials or project codes when you can, strip personal details, and follow the OAIC guidance linked above. When the notes are sensitive, keep the AI step on your own device or a tool your business has reviewed.

Can my team use the same prompt?

Yes — and they should. Save the fuller prompt in a shared doc so every wrap-up looks the same. Consistency makes it easier to scan and harder for actions to hide.

Want this running as a repeatable habit?

If you’d like help mapping which meetings are worth wrapping this way, and which other admin AI can take off your plate, book an AI audit and we’ll walk through it together. Or, if you’d rather start yourself, grab the AI agents pack. It works with ChatGPT, Claude, Grokbot or any AI assistant, and you can have your first agent running this week.

Illustration of a one-page SOP document card with numbered sections and an Approved owner check, next to the headline Write your SOPs with AI

In most small businesses I work with, the way things get done lives in one person’s head. Usually the owner’s. How to quote a job, how to set up a new customer, what to check before an order goes out, which supplier to ring when something breaks. It all works fine until that person is sick, on holidays, or trying to hire someone new. Then everything slows down, and the same questions get asked over and over.

The fix is simple and boring: write it down. The problem is that nobody has time to sit down and write a stack of process documents. That’s exactly where AI helps. In this post I’ll show you how to write standard operating procedures (SOPs) with AI, step by step, using ChatGPT, Claude, Grokbot or any AI assistant you already have. You do the talking. The AI does the typing and tidying. You stay in charge of what goes in.

What an SOP actually is (and why small businesses skip them)

An SOP is just a short, written set of steps for a task you do regularly. It answers three questions: what is this task, who does it, and how do we do it properly every time. It doesn’t need to be a 40-page manual. For most small businesses, a one-page checklist per task is plenty.

When I ask owners why they don’t have them, I hear the same reasons:

  • It takes too long. Writing a clear process from a blank page can take an hour or more, and there’s always something more urgent.
  • It’s hard to explain what you do on autopilot. You’ve done the task so many times you skip steps without noticing.
  • They go out of date. You write one, the process changes, and nobody updates it.
  • Nobody reads them. Long, wordy documents get ignored.

AI deals with the first two really well, and makes the last two much easier to fix.

Why AI is good at this job

Writing an SOP is mostly turning messy, spoken knowledge into clear, ordered steps. That’s one of the things AI assistants do best. You can talk through a task the way you’d explain it to a new staff member, rambling and out of order, and the AI can turn it into a clean checklist in seconds. It can also ask you questions to fill the gaps you didn’t notice you left.

What it can’t do is know how your business works. It doesn’t know your systems, your customers or the shortcuts that cause problems. So the rule is the same as every other AI job I recommend: the AI drafts, you check. Every SOP should be read and approved by the person who actually does the task before anyone relies on it.

How to write SOPs with AI, step by step

Step 1: Pick the first three tasks

Don’t try to document the whole business. Start with three tasks that meet at least one of these:

  • You get asked how to do it more than once a month.
  • Mistakes in it cost you money or upset customers.
  • Only one person knows how to do it.

Common first picks are setting up a new customer, sending a quote, processing a refund, opening or closing the shop, and end-of-month admin.

Step 2: Talk it through, don’t write it

This is the bit that saves the most time. Open your AI assistant’s voice mode, or use the dictation on your phone, and just explain the task out loud as if you were training someone on their first day. Don’t worry about order or polish. Mention the tools you use, what can go wrong and what “done” looks like.

Another option is to record yourself (or a staff member) doing the task while narrating, then paste the transcript in. Either way, you’re capturing what’s really done, not what you think is done.

Step 3: Ask the AI to turn it into an SOP

Paste your notes or transcript in with a prompt like this:

“You’re helping me write a standard operating procedure for my small business. Below is my rough explanation of how we [task]. Turn it into a one-page SOP with: a purpose line, who does it, what you need before starting, numbered steps (one action per step), common mistakes to avoid, and how to know it’s done. Use plain Australian English. Don’t add steps I didn’t mention. Instead, list any gaps or questions at the end.”

That last line matters. You don’t want the AI inventing steps that sound sensible but aren’t how you work. Asking it to list gaps instead keeps it honest.

Step 4: Answer the gaps

The AI will usually come back with a handful of questions. “What happens if the customer doesn’t have an ABN?” “Who approves refunds over a certain amount?” These are the steps you do on autopilot. Answer them, and ask it to update the draft.

Step 5: Test it on someone else

Give the draft to someone who doesn’t normally do the task and watch them follow it. Wherever they get stuck or ask a question, the SOP needs fixing. Tell the AI what happened and get it to tweak the wording. This test is the most important step, and it’s the one people skip.

Step 6: Store it where people will find it

An SOP nobody can find is useless. Put them all in one shared folder, a shared drive or your team chat, with clear names like “SOP: Sending a quote”. Add the date and the owner of each one at the top.

Prompts you can copy

Here are a few more prompts that work well once you’ve got the basics going:

  • Turn an SOP into a checklist: “Turn this SOP into a short tick-box checklist someone can print and use on the job.”
  • Make it easier to read: “Rewrite this so a new staff member on their first week can follow it. Short sentences, no jargon.”
  • Update an old one: “Here’s our current SOP and here’s what’s changed. Update it and list exactly what you changed so I can check it.”
  • Build a training quiz: “Write five quick questions to check someone understands this SOP.”
  • Find what’s missing: “Here’s a list of the SOPs we have. Based on a business like mine, what common tasks are we missing?”

Keep your SOPs safe and accurate

A few things to watch:

  • Don’t paste in private information. Leave out customer names, passwords, bank details and anything personal. Use placeholders like [customer name]. The Office of the Australian Information Commissioner has clear guidance on privacy and the use of commercially available AI products that’s worth a read before you start.
  • Safety steps need a proper check. If a task involves any risk to people, such as tools, chemicals, vehicles or working at heights, AI can help with the wording but it isn’t a substitute for doing your hazard checks properly. Safe Work Australia explains how to identify, assess and control hazards.
  • Someone owns every SOP. Put a name on it. That person checks it’s still right every few months.
  • The AI doesn’t get the final say. If the SOP and how the job is really done don’t match, fix the SOP. Don’t just trust the document.

Where SOPs pay off fastest

The biggest win I see is with new staff. Instead of shadowing you for two weeks, a new hire can work through a folder of clear one-page SOPs and come to you with specific questions. business.gov.au has a helpful guide on how to onboard new employees, and good SOPs make almost every part of that easier.

The second win is with AI itself. Once a task is written down clearly, it’s much easier to hand parts of it to an AI agent. A good SOP is basically the instructions an agent needs. That’s why, when I set up AI agents for a business, writing down the process is always the first step. If you’ve already read my post on onboarding new clients with AI, you’ll notice the same pattern: get the steps clear, then let AI help with the repetitive parts.

A simple plan for this week

  1. Pick three tasks that get asked about the most.
  2. Spend ten minutes talking each one through out loud.
  3. Use the prompt above to turn each into a one-page SOP.
  4. Answer the gaps the AI lists.
  5. Test each one on someone who doesn’t usually do it.
  6. Save them in one shared folder with a name and date on each.

That’s maybe two hours of work for three SOPs you’ll use for years. Then add one more each week.

Frequently asked questions

Can AI write SOPs for my business without my input?

It can write a generic one, but it won’t match how you actually work. The useful SOPs come from your explanation of the task. The AI’s job is to organise and tidy it, not make it up.

Which AI assistant is best for writing SOPs?

Any of the main ones will do the job, including ChatGPT, Claude and Grokbot. Use the one you’re most comfortable with. The prompt and your input matter far more than the tool.

How long should an SOP be?

For most small business tasks, one page. If it’s longer than that, it’s probably two tasks and should be split.

How often should I update my SOPs?

Whenever the process changes, and give each one a quick check every few months. AI makes updates fast: paste in the old version, explain what changed, and ask it to list its edits so you can check them.

Is it safe to put business processes into an AI tool?

General process steps are usually fine, but leave out personal information, passwords and anything confidential. Check your AI tool’s privacy settings and read the OAIC guidance linked above.

Want help getting your processes out of your head?

If you’d like to see which of your processes are worth writing down first, and which ones AI could take off your plate, book an AI audit and we’ll map it out together. Or, if you’d rather get started yourself, grab the AI agents pack. It works with ChatGPT, Claude, Grokbot or any AI assistant, and you can have your first agent running this week.

Illustration of an overdue invoice card with a four-stage reminder sequence from heads-up to final notice and a Paid status, next to the headline Chase unpaid invoices with AI

Most small business owners I talk to are great at doing the work and not so great at chasing the money for it. The job is finished, the invoice has gone out, and then it just sits there. You mean to send a reminder, but it feels awkward, you’re busy with the next job, and before you know it the invoice is weeks overdue and your cash flow is feeling it.

Chasing unpaid invoices is one of those jobs that’s perfect for AI. It’s repetitive, it’s mostly writing, and the hard part is getting the tone right, firm without being rude. In this post I’ll show you how to chase unpaid invoices with AI, step by step, using ChatGPT, Claude, Grokbot or any AI assistant you already have. You stay in charge of who gets chased and when. The AI just takes the awkward writing off your plate.

Why invoices slip through the cracks

When I look at how a business handles overdue invoices, the problem is rarely that the owner doesn’t care. It’s usually one of these:

  • Nobody owns it. Following up on payments is “everyone’s job”, which means it’s nobody’s job.
  • It feels awkward. You’ve got a good relationship with the customer and you don’t want to sound pushy.
  • Every reminder starts from a blank page. So it gets put off until there’s time to write it properly.
  • There’s no clear sequence. One customer gets three reminders, another gets none, depending on how busy the week was.

Every one of those is fixable with a simple system and a bit of help from AI.

What AI should and shouldn’t do when chasing payments

Money conversations need care, so it’s worth being clear about the line before you start.

Let AI handle

  • Drafting friendly reminders, firmer follow-ups and final notices in your voice
  • Adjusting the tone for a long-term customer versus a one-off job
  • Summarising your overdue list into “who to chase today”
  • Writing a short phone script for when an email isn’t enough

Keep with you

  • Checking the amounts, dates and invoice numbers against your accounting software
  • Deciding when to offer a payment plan, pause work or escalate
  • Anything that involves legal action or a debt collector
  • The final read-through before anything is sent

The AI drafts. You check and send. Nothing goes to a customer without you seeing it first.

Step 1: Get your payment terms clear

Reminders work best when your terms were clear from the start. If your invoices don’t already show the due date, how to pay and what happens when payment is late, fix that first. The Australian Government’s business.gov.au payments and invoicing guide is a good plain-English place to check what to include on an invoice and how to set your terms.

You can ask your AI assistant to help tidy the wording too. Paste in your current terms and ask: “Rewrite these payment terms so they’re short, clear and friendly for a small business customer. Don’t change any amounts, dates or conditions.”

Step 2: Write your reminder brief once

The secret to getting good results from AI is giving it a clear brief. Write this once, save it somewhere handy, and reuse it every time. Here’s a starting point you can copy and adjust:

You help me write payment reminders for my business, [business name]. We [what you do]. My tone is friendly, direct and professional. Australian English. Keep emails short, under 120 words. Always include the invoice number, amount, original due date and how to pay, exactly as I give them to you. Never change or invent any numbers. Never threaten legal action unless I specifically ask. End with a simple next step for the customer.

That last line matters. A reminder that says “please pay” gets ignored. A reminder that says “you can pay by bank transfer to the details below, or reply if there’s a problem with the invoice” gets a response.

Step 3: Build a simple reminder sequence

Instead of deciding what to do with each invoice from scratch, set up a sequence and ask your AI to draft each stage. A simple one I suggest to clients looks like this:

A few days before the due date: the friendly heads-up

Not a chase at all, just a helpful nudge. “Just a quick reminder that invoice 1042 is due on Friday.” Plenty of late payments are simply forgotten, and this catches them early.

Just after the due date: the polite reminder

Assume it’s an oversight. Restate the details, make paying easy, and invite them to reply if something’s wrong with the invoice.

A couple of weeks overdue: the firmer follow-up

Still polite, but clearer. Mention the earlier reminder, ask for a payment date, and offer to talk if they’re having trouble.

Well overdue: the phone call and final notice

At this point, pick up the phone. Ask your AI for a short call script so you know what you’ll say, then follow up with a final written notice that sets out the next step. If it gets to this stage, it’s worth reading the guidance from the Australian Small Business and Family Enterprise Ombudsman on dealing with late payment and disputes before you decide what to do next.

Your timings will depend on your industry and your terms, so set them to suit you. What matters is that every customer gets the same fair treatment, and nothing relies on you remembering.

Step 4: Draft each reminder in under a minute

Once your brief and sequence are set, chasing an invoice looks like this:

  1. Open your AI assistant and paste in your saved brief.
  2. Add the details: customer name, invoice number, amount, due date, which stage of the sequence they’re at, and anything relevant (“long-term client, always pays eventually” or “first job with us”).
  3. Ask for the draft.
  4. Check every number against your accounting software, tweak anything that doesn’t sound like you, and send it.

For example: “Stage 2 reminder. Customer: Sarah at Coastal Cafe. Invoice 1042, $1,850, due 28 October. Regular customer, very friendly. Pay by bank transfer, details on the invoice.”

You’ll get a short, warm reminder that’s ready to go after a quick check. What used to take fifteen minutes of putting it off now takes one.

Step 5: Make it a weekly habit

The businesses that get paid on time aren’t the ones with the fanciest software. They’re the ones that check their overdue list every week, without fail. Pick a time, say Monday morning, and spend ten minutes on it.

Export or copy your overdue invoice list from your accounting software, paste it into your AI assistant and ask: “Sort this list by how overdue each invoice is, and tell me which stage of my reminder sequence each customer is at.” Then work through the drafts one by one.

Before you paste anything in, think about privacy. Only share what’s needed to draft the message, and check your AI tool’s settings around how your data is stored and used. If you’re working with customer details, the OAIC’s guidance on using commercially available AI products is worth a read.

If you want to look at the bigger picture, I’ve written about running a weekly business review with AI, and your overdue invoices fit neatly into that routine. The Australian Government also has practical tips on managing cash flow.

Tips for getting the tone right

  • Assume good intent at first. Most late payers aren’t dodging you. They’ve forgotten, or the invoice went to the wrong person.
  • Make paying easy. Every reminder should include exactly how to pay. The fewer steps, the faster the money arrives.
  • Be specific. “Could you let me know when this will be paid?” gets a better response than “Please pay ASAP.”
  • Keep it short. Long, emotional emails get skimmed. Ask the AI to keep it brief.
  • Stay calm on paper. If you’re frustrated, let the AI write the first draft. It won’t be annoyed, and you can add firmness where it’s needed.

Turning it into an AI agent

Once you’ve used this for a few weeks, you’ll notice it’s the same steps every time. That’s the point where it makes sense to turn it into a simple AI agent: a saved set of instructions that knows your terms, your sequence and your tone, so you just hand it the overdue list and it gives you every draft at once.

That’s exactly what our AI agents pack is built for. It gives you ready-made agents for everyday small business jobs like this, and it works with ChatGPT, Claude, Grokbot or any AI assistant. No new software to learn, and you still approve everything before it goes out.

Frequently asked questions

Is it okay to use AI to write payment reminders?

Yes, as long as you check every message before it’s sent. The AI drafts the wording. You confirm the amounts, dates and tone, and you decide when to send.

Will the reminders sound like a robot wrote them?

Not if you give it a good brief. Tell it your tone, give it a couple of examples of emails you’ve written, and edit the first few drafts. It quickly starts to sound like you.

Can AI send the reminders automatically?

It can be set up to, but I recommend starting with drafts you review and send yourself. Money conversations are personal, and you’ll want to keep a human eye on them, especially at the firmer stages.

What should I do if a customer still won’t pay?

Call them, then send a clear final notice. If that doesn’t work, get proper advice before taking further steps. The Australian Small Business and Family Enterprise Ombudsman is a good place to start.

Do I need special software for this?

No. Your existing accounting software and any AI assistant are enough to get started today.

Want help getting paid faster?

If you’d like to see where AI could save you the most time, from chasing invoices to quotes to admin, book an AI audit and we’ll map it out together. Or, if you’d rather get started yourself, grab the AI agents pack and have your first agent running this week.

Illustration of a tidy quote document with scope, inclusions, exclusions and assumptions filled in and a highlighted space for your price, next to the headline Write quotes faster with AI

Quotes win jobs. But for most small business owners I talk to, writing them is the job nobody wants to do. You’ve just finished a site visit or a discovery call, you know exactly what the customer needs, and then the quote sits in your head for three days because you’re flat out. By the time it lands in their inbox, they’ve often gone with whoever got back to them first.

The good news is that this is one of the easiest places to start using AI in your business. You don’t need new software, you don’t need to change how you price, and you stay in control of every number. In this post I’ll walk you through how to write quotes faster with AI, step by step, using ChatGPT, Claude, Grokbot or any AI assistant you already have.

Why quotes take so long (and why speed matters)

When I look at how a business actually produces a quote, the slow part is almost never the pricing. It’s everything around it:

  • Turning rough notes into clear scope. Your notes say “bathroom, retile, check plumbing, maybe vanity”. The customer needs to read what’s included and what isn’t.
  • Starting from a blank page. Even with a template, you end up rewriting the intro, the inclusions and the terms every single time.
  • Getting the tone right. You want it to sound professional and friendly, not like a legal document.
  • Remembering the follow-up. Once it’s sent, it’s easy to forget to check in.

Every one of those is a writing task, and writing is exactly what AI assistants are good at. The pricing and judgement stay with you. The words come together much faster.

What AI should and shouldn’t do in your quotes

Before you start, it’s worth being clear about the line. I recommend this split to every business I work with:

Let AI handle

  • Turning your notes or a call transcript into a clean scope of work
  • Writing a short, personal intro that shows you listened
  • Listing inclusions, exclusions and assumptions so there are fewer surprises later
  • Drafting the cover email and a polite follow-up

Keep with you

  • Every price, rate and total. Never let an AI make up a number.
  • Your terms, warranties and anything with legal weight
  • The final read-through before it goes to the customer

Think of the AI as a fast, tidy assistant who drafts the quote while you check it. Nothing goes out until you’ve read it.

Step 1: Capture the job while it’s fresh

The quality of the quote depends on what you give the AI. Straight after the site visit or call, spend two minutes getting the details down. That can be:

  • A voice memo on your phone, transcribed with your phone’s built-in dictation
  • A few dot points typed in the car
  • The transcript or notes from a video call

Don’t worry about making it neat. Include what the customer asked for, anything you noticed, what they care about most (price, timing, quality), and anything you’re not sure about yet. Messy is fine. The AI’s job is to tidy it.

Step 2: Give the AI your quote structure once

The trick to consistent quotes is giving the AI the same structure every time. Here’s a brief you can copy and save:

You help me write quotes for my business, [business name], which does [what you do] in [area]. Using my notes below, write a quote draft with these sections: a two-sentence personal intro that references what the customer told me; a scope of work as clear dot points; what’s included; what’s not included; assumptions I’m making; next steps to accept. Use plain Australian English and a friendly, professional tone. Do not add any prices, rates, dates or guarantees. Leave [PRICE] where a price goes. If anything in my notes is unclear, list your questions at the end instead of guessing.

My notes: [paste notes]

That last instruction matters. Telling the AI to ask questions rather than guess is what keeps the draft accurate.

Step 3: Add your pricing yourself

Once the draft comes back, read through the scope and fill in the prices from your own price list or costing sheet. This is also a good moment to sanity check the scope. If the AI has listed something you didn’t mean to include, take it out. If its questions at the end point to a gap, sort it out with the customer before you send.

If you quote the same kinds of jobs often, you can paste your standard price list into the brief and ask the AI to suggest which line items apply. Just treat that as a suggestion and check every figure against your own numbers.

Step 4: Write the cover email and the follow-up

A good quote deserves a good email. Ask the AI:

Write a short email to [customer name] sending this quote. Thank them for their time, mention the one thing they said mattered most to them, and tell them how to accept or ask questions. Under 120 words. Then write a friendly follow-up email I can send in three days if I haven’t heard back, which isn’t pushy and gives them an easy way to say no.

Save the follow-up as a draft and set a reminder in your calendar or CRM. That one habit alone tends to win back quotes that would otherwise go quiet. If you want more on this, I wrote a full guide on how to follow up leads with AI without being pushy.

Step 5: Build a quote library over time

Every quote you send teaches you something. Keep the ones that won the job in a folder. After a few weeks you’ll have a small library of real examples, and you can paste one into your brief and say “match the style and level of detail of this quote”. Your drafts will start sounding more like you, and you’ll need fewer edits each time.

A quick example

Here’s how this might look for a painter. The notes from the site visit say:

“Sarah, 3 bed weatherboard, exterior only, some flaking on north side, wants it done before Christmas, worried about mess with dog, colour already picked.”

From that, the AI can produce an intro that mentions finishing before Christmas and keeping the yard safe for the dog, a scope that covers prep and repair of the flaking boards, inclusions like protecting garden beds, exclusions like interior work, and an assumption that the colour is already chosen. You add the price and the start date, read it through, and send. What used to be a job for Sunday night becomes a ten-minute task in the van.

When to move from copy and paste to an AI agent

Copy and paste is the right place to start. It’s free, it’s safe and you learn what good looks like. Once you’re doing it every day, it might be time for an AI agent that does more of the legwork for you, such as pulling the notes from your call recordings, filling in your quote template and preparing the follow-up for you to approve.

That’s the idea behind my AI agents pack. They’re ready-made agents for jobs like replying to enquiries, following up leads and keeping your records up to date, and they work with ChatGPT, Claude, Grokbot or any AI assistant. You stay in control and approve anything that goes to a customer.

A note on privacy

Quotes often include customer names, addresses and details about their home or business. Before you paste that into any AI tool, check the tool’s privacy and data settings, and only share what you need to. Many tools let you turn off using your chats for training. If you’re unsure, leave out the customer’s surname and address in the draft and add them in at the end.

Frequently asked questions

Can AI work out my prices for me?

I don’t recommend it. AI can suggest which line items from your own price list might apply, but every number should come from you. An AI that guesses a price can cost you the job or your margin.

Which AI tool is best for writing quotes?

Any of the main assistants will do the job well, including ChatGPT, Claude and Grokbot. The brief you give it matters far more than which tool you pick.

Will customers know the quote was written with AI?

Not if you do it properly. Because the draft starts from your own notes and you edit it before sending, it reads like you on a good day. The personal intro and the details from the visit are what make it feel human.

Do I need to change my quoting software?

No. You can paste the AI’s draft into whatever you use now, whether that’s a Word template, your accounting software or your CRM.

How long does it take to set up?

About fifteen minutes. Write your brief once, save it somewhere handy, and try it on your next quote.

Want help getting quotes out faster?

If you’d like to see where AI could save you the most time, from quotes to follow-ups to admin, book an AI audit and we’ll map it out together. Or, if you’d rather get started yourself, grab the AI agents pack and have your first agent running this week.