Home / Cases
CASE STUDY · KNOWLEDGE PLATFORM · LEGAL EXPERT

Years of expertise, all in one place.

He's a legal expert in a niche corner of real estate, with books, a podcast, videos and decades of experience. I'm not sharing his name yet, because his platform is about to launch publicly on his own schedule. All that material existed, but it was spread all over the place. He came to me asking for a chatbot. We ended up building a full knowledge platform with a revenue model built in.

Client in BelgiumProject run in DutchWritten up in English for this page
3sides: reader, advertiser and admin
1place for articles, podcast, video and case law
5topic areas the chatbot sorts questions into
18admin modules he runs himself
What happens when someone asks a question
  1. 1Question in the chatbot
  2. 2Sorted into a domain
  3. 3Answer from the knowledge base
  4. 4Link to an article, podcast or video
  5. 5No answer? Onto the to-learn list
Read the full storyWhere things stood · No audit, just a clear idea · From chatbot to platform
01

Where things stood

He has written books in his field, hosts a podcast, gives talks and works as a mediator and expert. His audience is a mix of private individuals and professionals who come to him with very specific questions.

His knowledge was scattered. Some of it was in a book, some in a podcast episode, some in a video, some in case law. To find an answer you had to know where to start, and almost nobody did.

He had a clear idea from our first conversation: put as much as possible on each topic in one place, and add a chatbot that figures out what kind of question you're asking before it sends you to the right spot.

02

No audit, just a clear idea

This project didn't start with an audit day, and it didn't need one. When a client already knows exactly what he wants, he mostly needs someone to build it and think it through with him.

His first request was a chatbot trained on his knowledge and a secure area for his members. The revenue model was part of the plan from day one: sponsors and advertisers would fund the operation, with subscriptions added later. That shaped how we built it, because a platform that has to make money needs a different design than a nice-looking library.

03

From chatbot to platform

The project grew as we went, which often happens once a client sees what's possible. The chatbot turned into a knowledge base. The knowledge base got user roles, with free and paid content. The sponsors got their own login so he doesn't have to place every banner himself.

Halfway through, we moved the platform from a rapid prototyping tool to custom code and its own database, and we did a security and privacy review. You can't see that work from the outside, but it's what separates a prototype from something you can build a business on.

Is your expertise scattered everywhere too?

Books, videos, a podcast, twenty years of experience. That's a platform waiting to be built.

Tell me what you have →
04

What we built.

It's one platform with three sides: one for readers, one for advertisers and one for him.

01The knowledge base

Articles, videos, podcast episodes, publications and case law in one place. Readers can filter by topic, search, save things for later and pick up where they left off.

02The chatbot

It first sorts each question into one of five topic areas. Then it points to the right article, episode or text.

03A chatbot that learns

Questions it couldn't answer go onto a list. That shows him what's still missing, and he fills the gap by uploading a document.

04The advertising platform

Advertisers log in, build their own campaigns and see their own numbers. He approves each one, so nobody emails banners back and forth anymore.

05Payments and invoices

Orders and invoices run through a payment provider with no manual work.

06Publishing on his own

He uploads his own content from a Word file or a PDF and decides what's free and what's for members.

What runs on its own here

An agent out front, workflows behind it, and a platform holding it all up.

AGENTA chatbot that sorts and learns.

It works out what kind of question it's getting, answers from the knowledge base, and keeps a list of what it couldn't answer.

WORKFLOWFrom document to published article.

A Word file or PDF gets processed automatically into an article in the knowledge base.

WORKFLOWApprovals and notifications.

An advertiser's campaign goes to him for approval and then goes live on its own.

PLATFORMKnowledge base and advertising platform.

With roles, payments and numbers for each side.

05

How we worked together

We had a video call about once a month, a shared folder, a feedback document and WhatsApp for quick questions. He added the content himself and sent a screenshot whenever something looked off.

What I liked most about this project is that ideas came from both of us. He knows his field inside and out, and I know what's technically possible. The platform is where those two meet.

06

What he gets out of it

I don't publish member or revenue numbers, and they're his to share anyway. Here's what's in place:

One home for his knowledge.People with a question in his field no longer need to know which book the answer was in.
A chatbot that knows his content.It's a guide to his own work, built on his own material.
A revenue model built in.Sponsors and advertisers have their own space, with numbers they can check themselves.
He runs it himself.He publishes, approves and adjusts without needing me.
Something to show.A working platform wins over partners faster than a plan on a slide.
The platform is his.The code, the content and the data all belong to him.
Want this for your expertise?

Your own knowledge platform with a chatbot that knows your work. We start with what you already have.

Get in touch →
07

And it keeps growing

He's been on a maintenance retainer since October. The next round of features is ready to go: member subscriptions, video and carousel ads, a dashboard for the chatbot, and the same chatbot on partner websites.

The timeline

How an AI audit works

Most projects start the same way, and it doesn't take months to get going:

01Intro call

You tell me what you do and where you're stuck. I'll tell you straight whether an audit makes sense or whether something smaller would do the job.

02One day on site

I come to where the work happens and watch. How does work come in? Who decides what? Where does the time go? Which tools are you already paying for?

03The report

Within a week you get a report: where time and money are leaking, your priorities in order, a review of your tools, and concrete proposals in more than one size.

04You decide

Do all of it, part of it, or none of it. If you move ahead with a build, the audit fee is credited in full.

05We build in phases

Your team tests as we go. Nothing ships until the people who'll use it have tried it.

06Retainer

If you want it to keep running and keep growing, we look after it on a fixed monthly retainer.

An AI audit costs $2,000, credited in full if you move ahead with a build.

Book your audit day →

Wondering what this could look like for your business?

It starts with a conversation. You tell me where you're stuck, and I'll tell you what I'd do and what it would cost.