Book a call

03— AI systems

AI chatbot development based on your own content

Central Dev develops AI chatbots that answer from your documents and data, cite the source and hand over to a person when unsure. When answering is not enough, we extend them into agents that take actions.

A chatbot can serve customers on your website or in your app, or answer your own team's questions internally. You choose the content it answers from and the point at which a person takes over.

01— What we build

Chatbots grounded in your own content

We build chatbots that answer from your own documents and data, and hand the conversation to a person when they are uncertain. When answering is not enough, we extend them into agents that act.

1CHATCan I change my plan?Yes, in your accountsettings, under Billing.1Source 1: Billing guide, p. 2Unsure? A person takes over
FIG. 03  Illustration: answers come from your documents with the source shown; uncertain questions go to a person.
  • 01

    Customer support chat on your website or in your app

    A chat on your website or in your app that answers customer questions from your policies, help articles and product information, and transfers to your team when needed.

  • 02

    Internal knowledge assistants for your team

    An assistant that finds answers in internal HR, IT and operations guides, so recurring questions no longer reach your colleagues.

  • 03

    Onboarding and pre-sales assistants

    An assistant that guides new users and prospects through your product and answers their questions from your own material.

02— Where it fits

For teams that answer recurring questions

Who it is for

  • Support teams that answer the same questions every day
  • Companies with large knowledge bases, policies or product documentation
  • Internal help desks for HR, IT and operations

When another service fits better

When users need tasks completed, such as updating a record, an AI agent or a deep agent is the better fit. Adjusted's chatbot began as a question-answering tool and was rebuilt as a deep agent.

03— Client work

Client work in this area

Each client is named with permission. Below is the scope of our work and its current status.

Adjusted

Delivered

AI agent · CRM · Web app · Mobile app

Adjusted's original chatbot answered basic questions only. We rebuilt it into a deep agent that understands the platform and takes actions on the user's behalf.

Read the Adjusted case study

04— How it starts

How an engagement starts

It starts with a sample of real customer questions and the documents that should answer them. Scope, estimate and timeline are agreed with you after the first conversation.

  1. 01

    Introductory call

    A 30-minute conversation about the questions your users ask and where the answers are documented today.

  2. 02

    Project discussion

    We review a sample of real questions and the source documents, and agree which questions the chatbot should handle.

  3. 03

    Agreement and NDA

    We sign an NDA and agree the engagement model, scope, estimate and timeline with you.

  4. 04

    Kickoff

    Work starts on the date we agree together.

  • Ongoing product work

    Dedicated team

    A team of Central Dev engineers working exclusively on your product, within your tools and processes.

  • Defined scope

    Fixed price

    A defined scope, an agreed price and a clear list of deliverables, all set before work begins.

  • Evolving scope

    Hourly (time & materials)

    You are billed for the hours worked, and priorities can change as the product evolves.

05— FAQ

Questions about chatbot development

Answers to common questions about this service. For anything not covered here, book a call or email us.

Email us

Do we need a chatbot or an AI agent?

If your users need answers, start with a chatbot; if they need tasks completed, you need an agent. A chatbot answers from your documents. An agent takes actions in your systems, such as updating a record, usually with an approval step for sensitive actions.

Where do the chatbot's answers come from?

From the documents and data you select for it. Each answer shows the source it used. When the chatbot cannot find a reliable answer, it hands the conversation to a person instead of guessing.

What do you need from us to get started?

A sample of real user questions and the documents that should answer them. With these, we can assess which questions a chatbot will handle well and where a person is still needed, and agree the scope with you.

How is our data handled?

We sign an NDA and talk through how your data is handled in the first conversation.

Can a chatbot be extended into an agent later?

Yes, and that is how the Adjusted project developed. We rebuilt Adjusted's question-answering chatbot into a deep agent that is fully integrated with the backend and takes actions on the user's behalf.

Book a call

07— Start a project

Let's discuss your chatbot project

Book a 30-minute introductory call or send us a sample of the questions you receive. Scope, estimate and timeline are agreed with you after the first conversation.

Book a call

Choose a 30-minute slot on Cal.com. Times are shown in your own time zone.

  1. 01Choose a time slot and add a few lines about your project.
  2. 02Discuss your goals, constraints and the right engagement model with our team.
  3. 03Agree scope, estimate and timeline together.

Prefer email?

Describe your project in a few lines, and we will continue the conversation by email.

Hours
09:00–19:00 Moldova time