AI agency in Leiden
AI on your own knowledge,
for organisations in Leiden.
In Leiden a lot of knowledge lives in documents: manuals, protocols, case files, reports. AI only becomes useful when it can use that knowledge and answer inside your own systems, with a source attached. That is what I build. I am Bas, a solo developer from Berkel en Rodenrijs, about 35 minutes' drive from Leiden.
What holds Leiden teams back with AI.
The answer is in a PDF nobody can find
Procedures and work instructions are spread over a shared drive, SharePoint and old emails. So new colleagues just ask the long-serving one.
An internal helpdesk that keeps explaining the same thing
How do I file expenses, where is the template, which version applies. Questions that take seconds to answer with the documents at hand.
Reports put together by hand
Every month copying figures from three exports into a spreadsheet, and then explaining what changed.
Systems that do not talk to each other
Planning, administration and CRM live apart. An AI tool without access to that data stays a separate toy.
Worries about confidential material
You work with data that cannot just go into a public AI service. So nothing happens, or it happens out of sight.
A pilot that never reached production
Someone built a demo in an afternoon. It works on their laptop, but nobody knows how to give it to the whole team safely.
From scattered documents to a working system.
Taking stock of what is there
Which documents, which systems, who asks which questions. We do that on site in Leiden or over video, whichever suits you.
A scoped first application
For example the internal questions of one department, or one report. Small enough to test quickly, at a fixed price.
Building on your own sources
The AI reads only what you point it to and names where each answer comes from. Whoever may not see something does not get it as an answer either.
Testing with real questions
Your team uses it for a few weeks. What goes wrong we collect and fix. Only then do we extend to more sources or departments.
Three applications that fit how Leiden works
Leiden runs on knowledge: education, research, healthcare, professional services and the companies that grew up around them. The gain from AI there is mostly in finding and summarising what already exists, and less in sending something out automatically.
An assistant on your own documents is worked out on your own ChatGPT for your business. If you want to see figures and ask questions about them, look at having a dashboard built. If the data sits in separate packages, it starts with having integrations built.
Knowledge base and internal helpdesk
Staff ask a question in plain language and get an answer from your own handbooks and protocols, with a link to the document.
A dashboard you can question
The figures from your systems on one screen, plus a short written explanation of what is off this month. The software does the calculation, the AI only summarises.
Integrations with AI in between
An incoming form, email or document is read, classified and put into the right system. When in doubt it lands in a list for an employee.
Where my experience comes from
For a hospitality business I built an ERP where purchasing, stock and orders come together. There is no AI in it. What it did teach me: how data moves through an organisation, where it gets entered twice and which integrations have to be in place before smart features make sense.
My own product Avitly is software for AV and IT installers with an AI assistant that answers questions based on the data in the system. I use it daily in my own AV company. The lessons from it, such as citing sources and a person deciding when in doubt, are standard in what I build for others.
- An ERP built for a hospitality business
- An AI product of my own in daily use
- Used to permissions per role and sensitive data
- No lock-in to a single AI vendor
What an AI application in Leiden costs
We agree a fixed amount for the build. Below are the ranges. A dashboard without an AI layer is also possible, if that is enough. How I arrive at a price is on pricing.
Assistant on your documents or in an existing system · € 2,950 to € 5,500
A knowledge base or internal helpdesk for one department. Three to six weeks.
AI on data from several systems · € 4,500 to € 8,500
When integrations between packages are needed before the AI can reach the data.
Dashboard · € 1,450
Figures from one or two sources on one screen, in two to four weeks.
Meeting in Leiden
I am based in Berkel en Rodenrijs, about 35 minutes' drive from Leiden. I like to hold a first meeting in Leiden, Leiderdorp, Oegstgeest or Voorschoten on site; after that much of it runs over video and we meet in person again at delivery. Need a website as well? See website development in Leiden.
Clients rate me 5 stars on average.
“I am extremely happy with the result of my new website for DoubleStreet Australian Cobberdogs, made by Webframer. From first contact, Webframer radiated expertise and creativity.”
“Webframer helped me enormously with the Veldvisuals website. It is not only good to spar with Bas about building the site, but also in the aftercare and whenever changes have to be made. Recommended!”
“Great to work with. Listens carefully to what we want. When we ask for changes, they are made expertly.”
“Really pleasant to work with and short lines of communication!”
“The website looks great!! Definitely recommended!”
“Excellent! Fast service and good contact!”
Translated from the Dutch originals on Google.
I am Bas Voets. Since 2021 I have been building websites, client portals and business software for small and mid-sized companies, from Berkel en Rodenrijs in the Netherlands. From first call to launch you talk to me, not to an account manager.
Do you come to Leiden?
Is our data safe, including confidential documents?
What if the AI says something wrong?
What are the monthly costs on top of the build?
Do you work with education or healthcare institutions?
Do you also work in Leiderdorp, Oegstgeest or Katwijk?
You don't have to take my word for it.
Three pieces that show up in most websites and applications, as working examples instead of screenshots. Click into them, they actually run.
Price calculator
Visitor drags the size, picks options and sees what it costs right away.
Multi-step request
The same questions, but in three steps with a check per step. This one gets finished.
Dashboard
The numbers you now paste together from three systems, on one screen with filters.
One hour of looking before any building.
In the AI scan we spend an hour together on one process in your business. Afterwards you get a short plan: what AI gains you there, what it costs and how long building takes. Free, and you are not committed to anything.
Tell me what you want to build.
A half-hour call. You get an honest answer about what it costs, how long it takes and whether building it is smart at all.