AI Chatbot Development Services

Chatbots that answer from your own content and hand off to a person when they should

Ask the assistant

What is my deductible?

→
  • What is my deductible?
  • What are the tuition fees for international students?
  • I need help booking an SUV.
  • Am I covered for this doctor's visit?

We build website, helpdesk and customer-service chatbots that answer only from documents you approve, show where each answer came from, and pass the conversation to your team when they are unsure. Three of them are live below: ask them anything.

What are AI chatbot development services?

AI chatbot development services design, build and run chatbots that answer questions for customers or staff. A well-built chatbot answers only from content you approve, such as help articles, policies and product documents, shows where each answer came from, and passes the conversation to a person when it is not sure. Metwaves builds them for websites, Microsoft Teams and customer service, and you can try three of our chatbots live before you talk to us.

Models and platforms we build chatbots with

  • Google Gemini
  • Dialogflow CX
  • Copilot Studio
  • Azure OpenAI
  • OpenAI GPT
  • Anthropic Claude
  • Azure AI Search
  • LangGraph
  • Microsoft Teams
  • SharePoint
  • Google Cloud
  • Microsoft Azure
WHEN TO CALL US

Signs your business is ready for an AI chatbot

If two or more of these sound familiar, a chatbot built on your own content will usually pay for itself in time saved.

  • The same 20 questions fill your inbox or helpdesk queue every week, and the answers already exist in a policy or help article.
  • Staff wait on IT or HR for answers that are written down somewhere in SharePoint, but nobody can find them.
  • Website visitors arrive after hours and leave because nobody is there to answer a simple question.
  • You tried an off-the-shelf bot and it gave generic or wrong answers, so customers stopped using it.
  • Your team wants answers inside Microsoft Teams or on your website, not in yet another tool.
  • Every enquiry lands with a person, including the ones that only need a link to the right page.
CHATBOTS WE BUILD

Custom AI chatbot development for support, staff and sales

Six kinds of chatbot, one way of keeping them accurate: approved sources, citations and a clear handoff.

Customer support chatbot

Answers product, order and policy questions on your website from your help centre and documents, and opens a ticket with the full conversation when it cannot help. Customers get an answer at any hour; your team gets fewer repeat questions and better tickets.

Internal IT and HR helpdesk bot

Runs in Microsoft Teams, answers from SharePoint policies and respects who may see which document. Built with Copilot Studio when your firm runs on Microsoft 365.

Document Q&A

Ask contracts, manuals and policy libraries questions in plain English and get the paragraph that answers it.

Sales and enquiry assistant

Answers pre-sales questions, collects what your team needs to know and books the call.

Booking and account assistants

Guides customers through reservations, plan details or course choices using your own data, like our car rental, healthcare plan and university demos.

Chatbot audit and rebuild

Already have a bot that gives poor answers? We test it against your real questions, show where it fails and fix the content, retrieval or model behind it.

HOW IT WORKS

How an accurate AI chatbot works

Most chatbots fail because they guess. Ours check what the person may ask, find the passages that answer it in your approved content, and only then let the language model write the reply. If the answer is not in your content, the bot says so and hands off.

How an accurate AI chatbot works: website, Teams and messaging channels pass through guardrails, retrieval from approved sources and a language model, ending in an answer with its source or a handoff to a person
Every answer comes from approved content and links to it. When the bot is not sure, a person takes over.
INTEGRATIONS

One assistant, connected to the systems you already run

The chatbot reads only from the sources you approve and writes only to the systems you allow, such as your helpdesk for tickets or your CRM for leads.

  • Website chat
  • Microsoft Teams
  • Messaging apps
Your chatbotguardrails, retrieval, model
  • SharePoint and policies
  • Helpdesk and ticketing
  • CRM and booking systems
LIVE DEMOS

Try three of our chatbots before you talk to us

Each demo answers from its own content. Ask the sample questions, then try your own. Demos accept messages up to 300 characters and 40 messages a day.

Live demo

Healthcare plan assistant

Explains plan benefits, deductibles and coverage, and helps find an appointment slot.

Try asking

  • What is my deductible?
  • Am I covered for this doctor's visit?

Gemini Pro on Google Cloud

Open the demo
Live demo

University helpdesk

Answers prospective and current students on courses, fees, deadlines and visas.

Try asking

  • What are the tuition fees for international students?
  • How do I apply for a master's program?

Gemini Pro on Google Cloud, trained on a public university website

Open the demo
Live demo

Car rental assistant

Helps customers choose and reserve the right vehicle for a trip.

Try asking

  • I need help booking an SUV.
  • I need to reserve a van.

Gemini Pro on Google Cloud

Open the demo

Results from a shipped chatbot

30–50%

of staff requests resolved without a person by our Teams helpdesk agent

8–12 weeks

from start to live, including content clean-up and a pilot group

3

chatbot demos you can try on this site today

Source: our Copilot Studio helpdesk case study for a UK professional services firm.

MEASURING RESULTS

How to measure whether your chatbot is working

Agree these numbers before launch, so the bot is judged on results rather than on how clever it sounds.

MeasureWhat it tells youWhy it matters
Resolution rateShare of conversations the bot finishes without a personThe main return on the project. Our Teams helpdesk agent resolves 30–50% of staff requests.
Answer accuracyShare of test questions answered correctly, from the right sourceMeasured on a fixed question set before launch and after every content change.
Handoff qualityWhether the ticket a person receives has the question, context and transcriptA bad handoff makes the customer repeat themselves, which costs more than no bot.
Unanswered questionsQuestions the bot could not answer, grouped by topicEach month this list tells you which content to write or fix.
Customer satisfactionThumbs up or down, or a one-question survey at the end of a chatRead alongside resolution: a bot that closes chats but annoys people is not working.
CASE STUDY

A Teams helpdesk agent that resolves 30–50% of staff requests

A professional services firm in the United Kingdom wanted staff to get answers to everyday IT, HR and policy questions inside Microsoft Teams. The answers already existed, spread across SharePoint sites where old and current versions sat side by side.

We cleaned up the content with the firm's owners, built a Copilot Studio agent that answers from SharePoint through an Azure AI Search index, cites the policy it used, respects document permissions, and opens a ticket with the conversation attached when it cannot help.

Read the full case study >

  • Client Professional services firm, United Kingdom
  • Built with Copilot Studio, Teams, SharePoint, Azure OpenAI, Azure AI Search
  • Result 30–50% of staff requests resolved without a person
  • Time to live 8 to 12 weeks
CHOOSING

Off-the-shelf chatbot, custom chatbot or AI agent?

Answer three questions to see what usually fits. We will tell you if a ready-made tool is enough.

Must it change records in your systems?
Refunds, bookings, updates in your CRM

Do answers come from many documents?
Policies, manuals, contracts, help articles

Do your staff work in Microsoft 365?
Teams, SharePoint, Outlook

What usually fitsTalk it through with us
INDUSTRIES

AI chatbots by industry

The job changes by industry, and so do the rules about what a bot may see and say.

IndustryCommon chatbot jobsWhat to watch
HealthcarePlan benefits, appointments, clinic informationPatient data rules such as HIPAA in the US: the bot answers general questions without personal data unless it is built and hosted for it. Healthcare demo
EducationCourses, fees, admissions, student servicesStudent records stay out of a public bot; account questions need sign-in. University demo
Professional servicesStaff IT, HR and policy questionsDocument permissions must carry through, so people only see what they may open. Case study
Travel and rentalBookings, changes, vehicle and trip optionsLive availability comes from your booking system, never from the model. Car rental demo
Retail and eCommerceOrder status, returns, product questionsOrder lookups need the customer to identify themselves before the bot reads the order.
Financial servicesProduct and account FAQs, document requestsNo account actions without strong sign-in, and every answer traceable to an approved source.
HOW WE WORK

How we build your chatbot, from content to production

Each step ends with something you can test, so you never wait months to see the bot answer a real question.

  1. 01
    First

    Scope and content audit

    We agree what the bot may answer, which sources it may use and where it hands off. We also collect a set of real questions your customers or staff ask; it becomes the test set.

  2. 02
    Next

    Prototype on your content

    A working bot on your real documents, not a demo dataset, so you judge it on the questions that matter to you.

  3. 03
    Before launch

    Test with real questions

    We score every answer in the test set for accuracy and source, fix the content or retrieval behind the failures, and repeat until the scores hold.

  4. 04
    Launch

    Go live on your channels with handoff

    Website, Teams or another channel, with a clear route to a person or ticket. Our Teams helpdesk agent went from start to live in 8 to 12 weeks.

  5. 05
    Every month

    Monitor and improve

    We review unanswered and low-rated questions, add or fix content, and re-run the test set before each change.

COST

What drives the cost of AI chatbot development

We quote after we have seen your content and channels. These are the factors that move the price most.

  • Number and state of content sourceshigh impact

    One clean help centre is quick to connect. Ten SharePoint sites with old and new versions side by side need clean-up first, as they did in our Teams helpdesk project.

  • Integrations and actionshigh impact

    Answering questions is one job. Looking up an order, booking a slot or opening a ticket in your system means building and testing each connection.

  • Channelsmedium impact

    Each channel (website, Teams, a messaging app) has its own setup, sign-in and testing.

  • Accuracy bar and testingmedium impact

    A bot that answers policy or health questions needs a larger test set and more review rounds than a product FAQ bot.

  • Languageslow impact

    Each extra language needs its own test questions, and sometimes its own content.

There is also a monthly running cost: model usage per conversation, hosting, and the monthly review that keeps answers current. Ask any vendor for both numbers.

WAYS TO WORK WITH US

Ways to work with us

Every engagement starts with a call about your questions, content and channels.

ModelBest forHow it is priced
Fixed-scope chatbot buildA defined set of sources, channels and handoffsFixed quote after scoping
Monthly improvement and supportA live bot that needs content updates, monitoring and new topicsMonthly
Audit of an existing botA bot that is live but gives poor answersFixed quote
TECHNOLOGY STACK

The models and platforms below run in our live demos, our Teams helpdesk agent and our AI agent projects. We choose per project and can change the model later without rebuilding the bot.

Models
  • Google Gemini
    Google Gemini
  • OpenAI GPT
    OpenAI GPT
  • Anthropic Claude
    Anthropic Claude

Azure OpenAI


Platforms
  • Copilot Studio
    Copilot Studio
  • Microsoft Azure
    Microsoft Azure

Dialogflow CX · Google Cloud · LangGraph


Content and search

Azure AI Search · SharePoint · Retrieval-augmented generation (RAG)


Engineering
  • Python
    Python
  • Node.js
    Node.js
  • AWS
    AWS

CHOOSING A PARTNER

How to choose an AI chatbot development company

Questions that separate a team that has run chatbots in production from one that has only built demos.

Good signs

  • They let you try a working bot before you sign, not only slides or a video.
  • They ask for your real customer or staff questions in the first week and test against them.
  • They show how the bot answers a question it cannot answer, and where the handoff goes.
  • They tell you the monthly running cost (model usage, hosting, improvement), not only the build price.
  • You own the content, the configuration, the conversation logs and the code.

Warning signs

  • Accuracy is promised, but nobody can say how it will be measured.
  • The bot answers from the open internet or from the model's general knowledge, not only from your content.
  • No plan for who reviews unanswered questions after launch.
  • The design depends on one model or platform that you cannot change later.
  • The vendor recommends a custom build for a handful of FAQs that an off-the-shelf tool would cover.

Send us 20 questions your customers ask

We will show you how a chatbot built on your content would answer them, and tell you honestly whether a ready-made tool would do the job.

Book a Chatbot Call
QUESTIONS & ANSWERS

If you don't see an answer to your question, you can send us a message from our contact form.

It depends mostly on how many content sources the bot reads, which systems it must connect to and how many channels it runs in. A product FAQ bot on one website is a small project; a helpdesk agent that reads several SharePoint sites and opens tickets is a larger one. There is also a monthly running cost for model usage, hosting and improvement. We quote after we have seen your content and channels, so the price reflects your project rather than a package.

A first working version on your own content usually comes early in the project, so you can judge it on real questions. Our Microsoft Teams helpdesk agent went from start to live in 8 to 12 weeks, including content clean-up, testing and a pilot group.

The bot answers only from content you approve, shows the source for each answer, and says it does not know when the answer is not there. Before launch we test it against a set of real questions and fix the content or retrieval behind every wrong answer. After launch, unanswered and low-rated questions are reviewed every month.

Our live bots run on websites and in Microsoft Teams. Messaging apps such as WhatsApp connect through their business APIs, and we confirm the channel, sign-in and handoff during scoping.

A chatbot answers questions. An AI agent also takes actions in your systems, such as updating a record, booking a slot or posting an invoice, within the permissions you give it. If you need actions, see our AI agent development service.

You do. The content, configuration, conversation logs and any code we write belong to you and live in your accounts where the platform allows it.

Yes. We test your current bot against your real questions, show which answers fail and why, and fix the content, retrieval or model settings behind them, or recommend a rebuild if that is cheaper.

Retrieval-augmented generation means the chatbot first searches your approved content for the passages that answer a question, then has the language model write the reply from those passages only. It is what lets a chatbot answer from your policies and products instead of guessing, and it is how each answer can link to its source.

With the enterprise model services we build on, such as Azure OpenAI, your documents and conversations are not used to train the provider's public models. We confirm the data terms for the model you choose during scoping, and we keep your content in your own cloud account where the platform allows it.

Ask to try a bot they have built, ask how it handles a question it cannot answer, and ask for the monthly running cost as well as the build price. The checklist above lists the signs we would look for.

INSIGHTS & NEWS

Discover IT Industry Insights and Technology Trends

Nikit Nandan    Nikit Nandan November 12, 2026
Top AI agent development companies for small and mid-sized businesses (2026)

Nine AI agent development firms a small or mid-sized business can shortlist, with Clutch figures, minimum budgets and the weaknesses their own clients name. Published by Metwaves, which is not ranked.

Learn More >
AI Development 9 min read
Nikit Nandan    Nikit Nandan November 12, 2026
Enterprise AI Agent Platforms Compared (2026)

An architecture review of the four big enterprise AI agent platforms: where each one reasons, acts, finds its data and connects to outside agents, what it costs, and when a custom build is the better choice.

Learn More >
AI Development 9 min read
Nikit Nandan    Nikit Nandan November 01, 2026
Top custom software development companies for small and mid-sized businesses (2026)

Ten custom software firms a small or mid-sized business can shortlist, with Clutch figures, minimum budgets and the weaknesses their own clients name. Published by Metwaves, which is not ranked.

Learn More >
Software Development 8 min read

Let’s build your idea!

Let us help you with free analysis & estimate. Our product expert will contact you within 12 hours.

 All your information is kept confidential and protected by NDA.