Glossary / AI and Machine Learning
AI Chatbot
An AI-powered conversational interface that handles customer questions, qualifies leads, and completes tasks around the clock.
Definition
An AI chatbot is a software application that uses artificial intelligence, typically powered by large language models, to simulate human conversation through text or voice interfaces. Modern AI chatbots go beyond scripted responses, understanding context, answering complex questions, and completing tasks such as booking appointments, processing orders, or providing customer support around the clock.
AI chatbot vs rule-based chatbot
| Feature | Rule-based chatbot | AI chatbot |
|---|---|---|
| Understanding | Matches keywords to pre-written answers | Understands intent, context, and nuance |
| Handling unknown questions | Shows "I don't understand" message | Generates relevant answer from knowledge base |
| Setup time | Hours to days | 1 to 3 weeks |
| Maintenance | Manual updates for every new question | Learns from new data automatically |
| Cost | Free to £100/month (SaaS) | £1,200 to £9,000 (custom built) |
| Conversation quality | Rigid, often frustrating | Natural, conversational |
| Multi-language | Requires separate setups per language | Handles 30+ languages from one setup |
What can an AI chatbot do for your business?
- Answer customer questions 24/7 using your product information, FAQs, and documentation
- Qualify leads by asking the right questions and scoring responses before passing to sales
- Book appointments by checking calendar availability in real time
- Process simple transactions like returns, order tracking, and account changes
- Collect feedback through conversational surveys that feel natural
- Reduce support volume by handling 60 to 80 percent of routine enquiries without human involvement
What does an AI chatbot cost?
| Option | Cost | Best for | Limitations |
|---|---|---|---|
| SaaS platform (Tidio, Intercom) | £0 to £100/month | Simple FAQ responses, small sites | Limited customisation, generic responses |
| Custom AI chatbot (basic) | £1,200 to £3,000 | SMEs needing branded, knowledgeable responses | Single channel, no CRM integration |
| Custom AI chatbot (advanced) | £3,000 to £9,000 | Businesses needing CRM integration, lead qualification, multi-channel | Requires quality training data |
Monthly running costs for custom chatbots are typically £20 to £120 covering API calls and hosting. Most businesses see ROI within 2 to 4 months through reduced support costs and increased lead conversion.
SaaS chatbot vs custom-built: which is right for you?
| Factor | SaaS (Tidio, Intercom, Drift) | Custom-built |
|---|---|---|
| Time to deploy | Hours | 2 to 4 weeks |
| Upfront cost | Free to low | £1,200 to £9,000 |
| Ongoing cost | £50 to £300/month | £20 to £120/month |
| Knowledge quality | Generic, template-based | Trained on your specific data |
| Brand consistency | Limited customisation | Fully branded experience |
| Integrations | Pre-built, limited | Any system your business uses |
| Data ownership | Stored on vendor's servers | You own everything |
When NOT to use an AI chatbot
- When all enquiries are complex and unique: If every customer conversation requires deep expertise, a chatbot will frustrate more than help
- When your customer base prefers human contact: Some industries and demographics strongly prefer speaking to a person
- When you have no training data: An AI chatbot is only as good as the information it is trained on. If you do not have documented FAQs, product info, or procedures, start there first
Our Experience with AI Chatbots
We build AI chatbots trained on your business data. Our chatbots handle 70 to 80 percent of routine enquiries without human intervention. Original Objective has been delivering AI-powered solutions since 2013, with over 100 projects completed for UK businesses across multiple sectors.
Related Terms
- AI Agent - Software that acts on your behalf, making decisions and completing multi-step tasks without constant human oversight.
- AI Voice Agent - An AI system that handles phone calls autonomously, answering, booking, and routing without human intervention.
- AI Automation - Using artificial intelligence to perform tasks that would otherwise require human effort.
- Prompt Engineering - The practice of writing instructions that get reliable, useful outputs from AI systems.
Ready to put AI to work in your business?
Book a free 30-minute discovery call. We will look at your current customer service setup, identify where a chatbot could save you time and money, and give you an honest assessment of whether it makes sense for your business.
Definition
An AI chatbot is a software application that uses artificial intelligence, typically powered by large language models, to simulate human conversation through text or voice interfaces. Modern AI chatbots go beyond scripted responses, understanding context, answering complex questions, and completing tasks such as booking appointments, processing orders, or providing customer support around the clock.
AI chatbot vs rule-based chatbot
| Feature | Rule-based chatbot | AI chatbot |
|---|---|---|
| Understanding | Matches keywords to pre-written answers | Understands intent, context, and nuance |
| Handling unknown questions | Shows "I don't understand" message | Generates relevant answer from knowledge base |
| Setup time | Hours to days | 1 to 3 weeks |
| Maintenance | Manual updates for every new question | Learns from new data automatically |
| Cost | Free to £100/month (SaaS) | £1,200 to £9,000 (custom built) |
| Conversation quality | Rigid, often frustrating | Natural, conversational |
| Multi-language | Requires separate setups per language | Handles 30+ languages from one setup |
What can an AI chatbot do for your business?
- Answer customer questions 24/7 using your product information, FAQs, and documentation
- Qualify leads by asking the right questions and scoring responses before passing to sales
- Book appointments by checking calendar availability in real time
- Process simple transactions like returns, order tracking, and account changes
- Collect feedback through conversational surveys that feel natural
- Reduce support volume by handling 60 to 80 percent of routine enquiries without human involvement
What does an AI chatbot cost?
| Option | Cost | Best for | Limitations |
|---|---|---|---|
| SaaS platform (Tidio, Intercom) | £0 to £100/month | Simple FAQ responses, small sites | Limited customisation, generic responses |
| Custom AI chatbot (basic) | £1,200 to £3,000 | SMEs needing branded, knowledgeable responses | Single channel, no CRM integration |
| Custom AI chatbot (advanced) | £3,000 to £9,000 | Businesses needing CRM integration, lead qualification, multi-channel | Requires quality training data |
Monthly running costs for custom chatbots are typically £20 to £120 covering API calls and hosting. Most businesses see ROI within 2 to 4 months through reduced support costs and increased lead conversion.
SaaS chatbot vs custom-built: which is right for you?
| Factor | SaaS (Tidio, Intercom, Drift) | Custom-built |
|---|---|---|
| Time to deploy | Hours | 2 to 4 weeks |
| Upfront cost | Free to low | £1,200 to £9,000 |
| Ongoing cost | £50 to £300/month | £20 to £120/month |
| Knowledge quality | Generic, template-based | Trained on your specific data |
| Brand consistency | Limited customisation | Fully branded experience |
| Integrations | Pre-built, limited | Any system your business uses |
| Data ownership | Stored on vendor's servers | You own everything |
When NOT to use an AI chatbot
- When all enquiries are complex and unique: If every customer conversation requires deep expertise, a chatbot will frustrate more than help
- When your customer base prefers human contact: Some industries and demographics strongly prefer speaking to a person
- When you have no training data: An AI chatbot is only as good as the information it is trained on. If you do not have documented FAQs, product info, or procedures, start there first
Our Experience with AI Chatbots
We build AI chatbots trained on your business data. Our chatbots handle 70 to 80 percent of routine enquiries without human intervention. Original Objective has been delivering AI-powered solutions since 2013, with over 100 projects completed for UK businesses across multiple sectors.
Related Terms
- AI Agent - Software that acts on your behalf, making decisions and completing multi-step tasks without constant human oversight.
- AI Voice Agent - An AI system that handles phone calls autonomously, answering, booking, and routing without human intervention.
- AI Automation - Using artificial intelligence to perform tasks that would otherwise require human effort.
- Prompt Engineering - The practice of writing instructions that get reliable, useful outputs from AI systems.
Ready to put AI to work in your business?
Book a free 30-minute discovery call. We will look at your current customer service setup, identify where a chatbot could save you time and money, and give you an honest assessment of whether it makes sense for your business.
Frequently Asked Questions
Common questions about AI chatbots for business.
Can an AI chatbot handle customer complaints?
For routine complaints (order tracking, refund requests), yes. For complex or emotional complaints, the chatbot should detect the sentiment and escalate to a human immediately. Well-built chatbots include escalation rules that ensure no customer gets stuck in a loop with an AI when they need a person.
How much does an AI chatbot cost per month to run?
Custom AI chatbots typically cost £20 to £120 per month in running costs, covering API calls to the language model and hosting. SaaS platforms like Tidio or Intercom charge £50 to £300 per month on subscription. The custom-built option has higher upfront costs but lower ongoing costs, and you own the system outright.
What percentage of customer queries can a chatbot handle?
A well-trained AI chatbot typically handles 60 to 80 percent of routine customer enquiries without human involvement. This includes FAQs, order tracking, appointment booking, and basic product questions. The remaining 20 to 40 percent get escalated to your team, who can then focus on the complex, high-value conversations.
Do customers dislike talking to chatbots?
Customers dislike bad chatbots. The old-style rule-based bots that could not understand questions were frustrating. Modern AI chatbots that understand context, give accurate answers, and know when to hand off to a human are well received. The key is transparency (let customers know they are speaking to AI) and quality (make sure the bot actually helps rather than creating another obstacle).