AI and LLM integration
LLMs are easy to demo and surprisingly hard to ship. I help teams cross that gap: pick the right model, build evaluation harnesses, and design around cost, latency, and the ways these systems fail.
Based in Groningen, working across the Netherlands and remotely for clients worldwide.
LLM-powered features for existing apps and new products: agent workflows, RAG pipelines, and integrations with OpenAI, Anthropic, and similar providers.
Integrations that make it to production. Prompt engineering, evaluation harnesses, and the unglamorous parts of running LLMs in production: cost, latency, and failure modes.
Good for
- RAG pipelines over private documents (search, support, internal Q&A).
- Agent workflows that have to take actions, not just answer questions.
- Existing apps that need a focused AI feature without rebuilding the whole product.
How I approach it
- Start from the workflow. The question is never which model is newest, but where language models actually remove work in your process. I look for the steps where they help and am honest about where they will not.
- Prototype on your real data. A small working prototype against your actual documents or tickets says more than any slide deck. That is usually the first milestone.
- Evaluate before shipping. LLM features fail in quiet ways, so I build evaluation sets and regression checks. A prompt or model change that makes things worse gets caught before your users catch it.
- Plan for the failure cases. Fallbacks, cost and latency budgets, and human review where the stakes require it. The goal is a feature you can put in front of customers.
Work I can show
- I use this daily. A large part of my own development work runs through LLM tooling I built and maintain myself, on the OpenAI and Anthropic APIs.
- Client work. For clients I've built transcription and content summarization tooling.
Tech I work with
Anthropic Claude, OpenAI, embeddings, vector databases, evaluation frameworks, prompt caching.
Frequently asked questions
Will my data be used to train a model?
Not by default. Under Anthropic's and OpenAI's current API terms, your input is not used for training. For private workloads we can also self-host an open-source model so the data never leaves your infrastructure.
How do you measure whether the AI feature is good enough?
With an evaluation harness built from real examples, ideally collected from your domain. Each release is scored against held-out cases for accuracy, latency, and cost so regressions show up before users do.
What about hallucinations and reliability?
I treat them as a design constraint. Outputs are validated, fallbacks are explicit, and high-stakes flows have a human review step. The goal is a feature that fails predictably rather than one that fails invisibly.
Can my data stay private or in the EU?
Yes. Depending on your requirements I use EU-hosted endpoints, self-hosted open-source models, or design the feature so sensitive data never leaves your systems. Privacy constraints go into the design from the start, which is also how GDPR requirements are usually met in practice.
When is an LLM the wrong tool?
When the task needs guaranteed exact results, when a simple rule or query already solves it, or when the volume makes per-request costs unreasonable. If that is your case I will say so and suggest something simpler.
Can you add AI to an existing app?
Yes, and it is a lot of what I do. Often the right move is one focused feature added to software that already exists, a search box, a summarizer, a support assistant, rather than rebuilding the product around a model.
Want to talk it through?
Tell me what you're trying to do. I'll let you know honestly whether I'm a good fit.
Get in touchOther services
- Custom application development End-to-end design and implementation of bespoke applications across web, native iOS, and backend systems, including MVP builds for early-stage products.
- Web, API and backend development Production websites, web apps, and APIs in React, Preact, Svelte, and vanilla web. Backends in Go and Python with REST or event-driven APIs.
- Legacy code modernization Refactoring and modernizing older codebases. Framework upgrades, careful test-driven changes, and migrations from end-of-life platforms.
- Native iOS apps Native iPhone and iPad apps in Swift and SwiftUI, including widgets, Live Activities, and App Store delivery.
- Browser extensions and integrations Chrome extensions, Thunderbird add-ons, and integrations between browsers and external services.
- Point-of-sale and retail software Custom POS systems, inventory and stock management tooling, and integrations with receipt printers and other store hardware.
- Performance-critical engineering Algorithms, audio and video processing, codec work, P2P networking, and other engineering-depth projects where performance and correctness matter.