Adding an AI Chatbot to an Existing Website

This real estate leasing company was already operating its own property-search website. However, staff members were spending a significant amount of time handling inquiries outside business hours and answering frequently asked questions such as, “How much are the initial costs?” and “How do I book a property viewing?” Reducing this operational burden had become a priority.

They asked us to introduce an “Ask via Chat” icon that stays visible in the bottom-right corner of the screen without requiring major changes to the existing website design. When a visitor clicks the icon, a chat window opens and an AI provides an automated response.

To keep changes to the existing site to a minimum, we proposed a widget-style chatbot that runs by embedding a single line of JavaScript.

To make a three-week delivery feasible, we kept the initial scope focused. Complex conversation branching, seamless handoff to human operators, and customer-database integrations were excluded. Instead, the chatbot was designed to reference the client’s existing FAQ materials—such as Q&A lists, rules, and guidance documents—and provide first-line answers in natural language. Questions it cannot resolve are directed to the existing inquiry form through a simple, reliable path.

On the assumption that the core FAQ materials and access to a test environment or the target page are available at the start, and that reviews can be completed in short cycles, we defined a scope that could be delivered for $2,000 in approximately three weeks.

Technical Configuration

An Option for Sensitive Data

This example uses an external AI API as its standard configuration. If there is a requirement not to send inquiry content or reference data to external AI services, we can separately consider a private AI configuration using a locally run LLM on PCs or servers managed by the client. Learn more about our Private AI & Local LLMs service.

This option requires an assessment of available CPU, GPU, memory, network controls, and the response speed needed. Because hardware upgrades, network configuration, and additional validation may be required, it is not included in the standard $2,000 / three-week scope and is quoted separately according to the requirements.

The deliverables consist of three items: an “embed script” for adding the chatbot to the existing site, an “FAQ data administration screen” for updating the data the AI references, and an “operational manual.”

The implemented features are as follows:

• Sticky Bottom-Right Icon and Chat Window: An interface that remains in the bottom-right corner while the visitor scrolls and opens or closes on click.
• AI Automated Responses: A feature that references relevant registered FAQ data in response to a visitor’s free-text question and provides a natural-language answer.
• Chat History Viewing for Administrators: A simple view that lets administrators check the types of questions being asked most often.

This project was completed in approximately three weeks, on the assumption that the core FAQ materials and the information needed to install the widget on the existing site were provided at the start. Limiting the initial scope to first-line FAQ responses allowed rapid review cycles while retaining time for answer tuning and integration testing.

Payment Terms

As a general rule, we do not require an upfront payment. There was no advance payment at the time of contract; the full amount was invoiced only after all development work and the client’s acceptance were complete.

The following costs cover requirements alignment within the initial scope, chatbot UI implementation, integration with an external AI API, and integration testing on the existing website. They do not include advanced human-support systems, complex conversation branching, customer-database integrations, or a private AI / local LLM environment.

Currency and Invoicing

All amounts on this page are approximate U.S. dollar (USD) figures, converted from the original Japanese yen (JPY) estimate at an assumed exchange rate of around JPY 150 per USD and rounded for readability. Quotations and invoices can be issued in USD, JPY, or other currencies upon request; the applicable exchange rate, conversion basis, and any bank or payment-provider fees will be confirmed in advance for each project. For clients outside Japan, payments are generally handled as transactions exempt from Japanese consumption tax.

Supplement: Estimated Third-Party Service and Maintenance Costs After Launch

Because this system uses external AI models to generate answers, the following monthly costs are required after production launch, separate from the initial development fee.

• The total monthly cost is estimated to be around $100–$200.
• Third-party service charges may fluctuate depending on usage and exchange rates.

Third-party cloud-service costs are model estimates based on published pricing structures for common serverless platforms and AI models.

The three-week timeline was possible because we avoided major changes to the existing website and limited the role of the chatbot to first-line FAQ responses. Trying to build an AI that answers every possible question perfectly, or implementing complex links to human support from the beginning, substantially increases the work required for conversation design, data preparation, and validation.

In this case, we kept the solution focused: reference existing FAQ data, answer through the bottom-right widget, and direct unresolved questions to the existing form. This allowed the client to automate first-line inquiry handling, including outside business hours, while keeping the initial development cost to $2,000.

The standard configuration uses an external AI API. For organisations that prefer to avoid external AI services because of internal policy or the sensitivity of the inquiries they handle, we can also discuss a Private AI & Local LLMs configuration that operates on PCs or servers they manage. This requires a separate design based on hardware capacity and network requirements, but it can be considered as a future option.

Typical Scope for Common Add-Ons

Once operations are established, a common next step is a human-chat handoff feature and an operator administration screen so that staff can take over a conversation directly. Because this requires a real-time communication foundation and operator-status management, it typically involves an additional $3,300–$5,300 and approximately 1.5–2 months of development.

Starting with AI-powered first-line FAQ responses and expanding step by step into human support or a more advanced AI configuration lets a business reduce initial investment risk while building an inquiry-handling system that fits its needs.