Custom AI chatbot or off-the-shelf chatbot?

The short answer

Most businesses should start by asking what the chatbot is for. If the answer is "answer the same ten questions on our website", an off-the-shelf tool will do that for a monthly fee and can be live this week. If the answer is "turn enquiries into booked, qualified calls without my team typing anything up", you need something connected to the rest of your business, and that is where a custom build earns its cost.

Side by side

	Off-the-shelf chatbot	Custom AI chatbot
Time to launch	Days	Weeks, set out in the written scope
Upfront cost	Low	Projects start at £4,500
Ongoing cost	Monthly subscription, often by conversation or seat	AI usage paid to providers, optional support
Answers from	The pages and FAQs you load in	Your approved documents, services and rules
Qualification	Basic form-style questions	Your real qualifying questions, with routing by answer
Booking	Often a link to a calendar	Books inside the conversation
Channels	Usually website chat	Web chat, SMS and social messages
CRM connection	Depends on the tool's integrations	Every conversation logged against the contact
Handover to a person	Generic "contact us"	Rules you set, with the full conversation passed on
Ownership	You rent it	Built in your accounts

When off-the-shelf is enough

• Your questions are general and the answers are already on your website.
• You get a modest number of chats and a person reads them all anyway.
• You do not need the chat to book, qualify or update your CRM.
• You want to test whether visitors use chat at all before investing.

In those cases, start with a tool, watch the conversations for a month, and you will learn exactly what a better bot would need to do.

When a custom chatbot is worth it

• Enquiries arrive in several places. Website chat, SMS, Instagram and Facebook messages all need the same fast, accurate reply.
• Qualification matters. You need to know budget, timing, location or service type before a call is booked, and route people by their answers.
• The next step is a booking. A bot that sends a link loses people. One that books during the conversation keeps them.
• Your CRM is the source of truth. Every conversation should land against the contact with a summary, so your team starts the call already knowing the details.
• Accuracy has consequences. If a wrong answer about price, eligibility or policy could cost you money or a complaint, you need tight control over what the bot is allowed to say.

The part both options get wrong: accuracy

A chatbot speaks for your business. In Moffatt v Air Canada (2024), a tribunal held the airline liable for incorrect fare information its website chatbot gave a customer. Whichever route you choose:

• Give the bot a limited, approved set of information to answer from.
• Have it say it does not know, and pass the question to a person, rather than guess.
• Set clear handover rules for complaints, sensitive topics and anything involving money.
• Read a sample of conversations every week for the first month.

We build these rules into every chatbot, and they are covered on our conversational AI and chatbots page.

Questions to ask before you choose

1. What should happen after a good conversation: a booking, a quote request, a call back?
2. Which channels do your enquiries actually arrive on?
3. What questions does your team ask before a call is worth booking?
4. Which answers must never be improvised: prices, policies, eligibility?
5. Where should the conversation be recorded so your team can see it?

If your answers are short and simple, a tool will serve you well. If they involve your calendar, your CRM and several channels, talk to us.