Customer support chatbot
Answers product, order and policy questions from your help content, and opens a ticket when it can’t.
Who it’s for
Who this is for and the problems it solves
Typical clients
- Businesses answering the same customer questions every day
- Support teams that want to handle routine enquiries outside working hours
- Sales teams qualifying website enquiries before a call
- Healthcare organisations offering patient-facing information and booking help
Common problems
- Customers wait for answers that already exist in your help content
- Rule-based chatbots break as soon as a question is phrased differently
- Generic chatbots make up answers about your products or policies
- Conversations end without a clear handover to your team
Use cases
What we can build
Examples of our capabilities, not descriptions of specific client projects.
Website enquiry assistant
Answers visitor questions, collects the details your team needs and books a call.
In-app help assistant
Helps users inside your product with how-to questions, using your documentation.
Patient information assistant
Answers general questions about services, preparation and appointments, and routes clinical questions to staff.
Scope
Scope, deliverables and what we need from you
What we deliver
- Conversation design: what the chatbot should and shouldn’t answer
- Knowledge base built from your approved content, with source links
- Chat interface for your website or app, or an API for your own front end
- Handover to people through your helpdesk, CRM or email
- Guardrails for off-topic, sensitive and out-of-scope questions
- Evaluation set, conversation logs and monitoring
Data & integration requirements
- The content the chatbot may answer from (help pages, FAQs, policies, product data)
- Real customer questions, such as past tickets or chat transcripts
- Topics it must not answer, and when it should hand over
- Where it will run and which systems it connects to
Delivery
How we deliver and evaluate
Discovery
Understand the workflow, the data and what success looks like. Agree scope and measurable targets.
Prototype & evaluate
Test the approach on a sample of your data against agreed criteria before a full build.
Build & integrate
Develop, connect to your systems and test with your team, with regular demos.
Deploy & support
Release to your chosen environment, hand over documentation and agree ongoing support.
We build a test set from real customer questions with agreed correct answers, including questions the chatbot should refuse or hand over, and review the results with you before launch. After launch, we review conversation logs to find gaps in the content.
Evidence
Relevant work
We don’t yet have a published client case study for this service. We can walk you through relevant work and our approach on a call.
Options
Ownership, deployment and support
Ownership
Ownership of the code, prompts, evaluation sets and any model weights we produce for you is agreed in the statement of work, subject to the licences of any third-party models or components used.
Deployment
Your own cloud account (AWS, Azure or Google Cloud), your on-premises environment, or hosting managed by Kubit’s.
AI models
Hosted models from major providers, open-source models run in your environment, or models fine-tuned on your data, chosen per use case for accuracy, cost and data handling.
Support
Post-launch support and maintenance are agreed per project, including monitoring, updates and response times.
FAQ
Questions about this service
How is this different from your AI agents service?
A chatbot talks with your customers and answers their questions. An AI agent carries out multi-step work across your internal systems. Some projects combine both.
How do you stop the chatbot making things up?
It answers from your approved content using retrieval, shows sources where useful, and is tested on questions it should decline. When it isn’t confident, it hands over to a person.
Can it hand conversations over to our team?
Yes. We connect it to your helpdesk, CRM or email so your team gets the conversation and the customer’s details.