AI for recurring everyday tasks
AI integration
AI assistants and automation that read documents, sort enquiries and draft replies, right inside the way you work.
Free intro callScope and timeframe depend on your project
A chatbot on its own rarely saves money. So our AI integration starts where time is lost in your day‑to‑day work. For example when writing quotes, analysing documents or sorting enquiries. The AI might read an order from an email and prepare it in your system. We usually set it up so that it passes unclear cases to a person. Our aim is for it to handle your data securely and for you to be able to trace what it has done.
- 01Assistants that look things up in your own documents
- 02Emails, PDFs and forms read and analysed automatically
- 03Copy, quotes and reports drafted automatically, modelled on your tone
- 04AI that works through multi‑step tasks on its own, with your approval built in if you want it
- 05Connected to your systems through interfaces or directly via the database
Technologies
- Claude API
- OpenAI
- LangChain
- Vektordatenbanken
- Python
- TypeScript
How it runs
What a project usually looks like
The work falls into four steps that build on each other. Depending on the project, each one can be bigger or smaller.
01
Workshop
We go through your processes together, looking for the places where AI could pay off most relative to the effort.
02
Prototype
Where it makes sense, we first build a simple prototype, for example with some of your data. That way the idea can be tested early.
03
Everyday use
Then we develop the solution for everyday use. This usually includes technical monitoring, access rights and a fallback for cases where the AI gets stuck.
04
Training and maintenance
We usually walk your team through it and document the solution. If you like, we can then look after running it under a maintenance contract.
Who has which role under the AI Act
Article 50 of the EU AI Act has applied since 2 August 2026. Among other things, it requires that people learn when they are dealing with an AI. For a company that develops software, this doesn't automatically create a duty to disclose. It depends on who has which role in the specific case. And that follows from the actual circumstances, not from what the contract says. So it pays to settle the roles early in a project.
- Provider
- Whoever offers the AI system or puts it into service under their own name. For software we build for you, that's usually you.
- Deployer
- Who uses the system in their own business, and which notices they then owe the people affected.
- Risk class
- How risky the specific use is, and which class under the AI Act it falls into.
- Documentation
- Who keeps which evidence, and where it lives.
- Human oversight
- Where a person decides, how they can step in and what gets logged.
Common questions
AI integration: common questions
We prefer data centres in the EU and providers that don't use your data for training. Depending on the project, AI models can also run entirely within your own IT. What applies to your project is set out in the quote.
That depends on the AI service and its contract terms. We prefer services that don't use your content for training. If you want even more control, AI models can also run within your own IT. Which service suits your project is something we work out together.
That depends mostly on the volume. The AI provider charges for each request it handles, and there's hosting and, where agreed, support on top. Running costs can be estimated in advance from your real volumes. That's best discussed before you start.
That's something to plan for. An AI can be set up so that in uncertain cases it doesn't decide on its own but hands over to a person. Approval before anything is sent or posted, and a log of each step, are possible too. How much control makes sense for your workflow is something we work out together.
Interested in AI integration?
Drop us a line about what you need. We'll get back to you as soon as we can.
Reach us directlyinfo@tscodeworks.de
We'll get back to you as soon as we can