Panenco

Name: Panenco
Address: Hyphen One Kolonel Begaultlaan 1A/51, Leuven, 3012, BE
Telephone: +32497863605

We’re a boutique product studio in Belgium.

We work shoulder-to-shoulder with our clients on next-gen B2B SaaS products and enterprise AI solutions, in a spirit of joint entrepreneurship.

01/09/2026

20 of the 30 seats are taken, so there's room for 10 more.

Our event is taking place on 30 September, the second in our series "Building in the age of AI". This time we'll be zooming in on product management and how we see its role evolving when AI speeds up both the development process and the decisions about what to build.
We open with some of the tensions we're seeing, and the way we are handling them. After that it's open discussion, and we're mostly there to see what other teams are encountering and to hear how they are managing it.

Wed 30 Sep at Panenco HQ in Leuven. Kick-off at 18h.
We hope to see you there!

Register here: https://www.panenco.com/event/product-ownershi

27/08/2026

Every team has someone who quietly makes everything work. At Panenco, that's Koen Verschooten.

As our Operations Manager, Koen owns a wide range of operational domains: finance, people operations, security, compliance, contracts, and internal processes. In practice, he's the person making sure the company scales without falling apart, keeping workflows tight, risks managed, and teams productive and aligned.

He'll tell you he loves the variety and the impact. The ability to work across every part of the business while building the structure that lets others do their best work. That combination of breadth and ownership is genuinely hard to find.

Oh, and he also makes sure the coffee machine never runs dry. Which, between you and us, might be what holds everything together.
Koen, you're our rock!

24/08/2026

We’re hiring an Engineering Manager!

We’re looking for an outstanding person who’s ready to steer the technical direction of one or multiple products in our portfolio. We look for grit, perseverance and a getting-things-done attitude.

You shape your own work with AI and we expect you to inspire your team(s) to do the same. You’ll be in a client facing role, with diverse challenges and limited reporting lines.

Become part of an inspirational environment with high talent density where you can be entrepreneurial in your daily work.

Location: Antwerp / Leuven (Belgium)

17/08/2026

We’re hiring a Product Manager!

We’re looking for an outstanding person who’s ready to steer the functional and business direction of one or multiple products in our portfolio. We don’t care much about years of experience. We do care about grit, perseverance, curiosity and getting things done.

You shape your own work with AI and we expect you to inspire your team(s) to do the same. You’ll be in a client facing role, with diverse challenges and limited reporting lines.

Become part of an inspirational environment with high talent density where you can be entrepreneurial in your daily work. We appreciate a humble and curious attitude and great depth in your abilities.

Location: Antwerp / Leuven (Belgium)

13/08/2026

You can get the benefit of an LLM on sensitive text without ever handing it the sensitive part, which is important for applications in highly regulated domains.

The personal data in a document is rarely what the model needs. It needs the context: who said what, in what order, about what. So before any call goes out, we run the text through a detection pass that finds the identifying details (names, phone numbers, addresses, dates of birth ...) and swaps each one for a surrogate token. Alice becomes PERSON_1, +32 16 79 20 79 becomes PHONE_1. The sentences around them stay exactly as they were.

The trick is that the swap is reversible, not redaction:
- A keyed cipher maps every real value to a stable surrogate, so the model still reasons about the same person or place consistently across the whole text
- One key per document, reused across every related piece, so the whole set de-identifies and re-identifies together

The model works on the full context with the identities masked. When its answer comes back, we reverse the mapping with the same key, and PERSON_1 becomes Alice again before anyone reads it.

This makes the message masked for the model, meaningful for the client.

One honest caveat: anything the model paraphrases away has no surrogate left to reverse. But for everything it carries through, you get full utility on the surface and no identities underneath.

10/08/2026

In June we ran the first evening in our event series "Building in the age of AI".

We talked through what changes when AI writes more of the code. The room stayed until closing time, so we're doing a second one.

This time: "Faster to build, harder to decide. What product ownership means now."

AI has made building more accessible. But accessible does not mean simple, it means the judgment calls that used to happen naturally over a long build cycle now have to happen faster, without the safety net of time.

That puts more weight on product, not less. What should we build, not just what can we. What "done" means when a demo looks finished in a day. How the product stays coherent when almost everything is within reach.

Panenco opens with what we're seeing, then hands the room over. It's an open discussion and we'd love to hear your experience and input.

We hope to see you there!

Wed 30 Sep, 18:00 to 21:00, Panenco HQ, Leuven.

Register: panenco.com/event/product-ownership

05/08/2026

We're proud to announce our collaboration with argenx!

Founded in Ghent, argenx has grown into a global immunology leader with Belgian roots, dedicated to improving the lives of people living with severe autoimmune diseases. We're excited to support argenx's growth and ability to scale with custom-built software and AI solutions.

Many thanks to Loes Bresseleers, Steven Van Broeck, Alessandro Fazio and the entire argenx team for the trust. Looking forward to everything we'll build together!

03/08/2026

We're launching a pragmatic, side-by-side program to help software teams actually build with AI agents and safely speed up development. No slides, just hands-on in the codebase. We sit directly with your developers, pair-program, set up agent-ready repos, and ship production code together.

Some of the core principles we set up:
- Agent-ready repositories: standardized rules, prompt configs, and guardrails built directly into and adapted to your repos.
- Centralized context: linking docs, tickets, codebases, error logs all together so AI agents have the exact context they need at any time in development.
- Pair programming: on-site coding sessions to upskill your team by doing it together, not just watching.
- Upfront specs, prototypes, PRDs: shifting focus to writing crystal-clear specs, PRDs, and functional prototypes before production development.
- AI review agents & E2E tests: automated testing and review workflows to keep quality high while accelerating output, and to avoid a bottleneck in PR reviews.

Ready to modernize and speed up your development workflows? Let's talk!

28/07/2026

Welcome to the team, Eray!
We’re glad to officially introduce Eray as a Software Engineer here at Panenco. Following a successful internship with us, he’s now joining the team full-time.

From his first weeks already, Eray has been shipping some seriously complex features to production. He has an extremely pragmatic mindset, can-do mentality and true passion for all things software, a perfect match with our values, so we're super glad to have him on board!

Let's continue building together!

13/07/2026

At Panenco, we built an internal Claude Code plugin. One install pushes our engineering rules and a library of custom workflows into every developer's session. The shared rules are enforced automatically: naming and commit conventions, a PR size limit, and a plan-first workflow before any code gets written.

Everyone also gets the same ready-made skills:
- /create-pr takes you from branch to PR to board update in one step
- /grill-me stress-tests your plan before you write a line of code
- A Slack bot that chases down stale PRs

We treat our AI tooling like a product. Versioned, shared, and shipped to the whole team, so everyone follows consistent rules for how we develop, from code review to delivery.

Adresse

Hyphen One Kolonel Begaultlaan 1A/51
Leuven
3012

Téléphone

+32497863605

Site Web

http://www.panenco.com/

Notifications

Soyez le premier à savoir et laissez-nous vous envoyer un courriel lorsque Panenco publie des nouvelles et des promotions. Votre adresse e-mail ne sera pas utilisée à d'autres fins, et vous pouvez vous désabonner à tout moment.