Tech Events in Prilly

The event will be kindly hosted by Visium.
Please register using the form :
https://forms.gle/XKTFDoUdnUqAoxNQ7

👇 👇 Line-up 👇👇

AgentOps — The Next Layer After MLOps: Managing, Deploying and Monitoring AI Systems
by Andy Bermond (VISIUM)

LangChain's 2026 State of Agent Engineering survey put 57% of respondents with agents in production, 89% with observability in place — and only 52% running evals. Quality was the top barrier, named by nearly a third. Tracing has become table stakes; knowing whether the thing is any good has not. That gap is the interesting part.

The term AgentOps was coined in a 2024 paper out of CSIRO's Data61. Its argument: existing tooling mostly tracks LLM-specific metrics and prompt management, with little support for the artifacts that actually define an agent — its goals, its plans, its tools.
MLOps grew out of a similar observation: the model was never the hard part, the system around it was. Agents make the point again, louder. A model is a function — you version it, test it, roll it back. An agent is a process. It holds state, calls tools, spends money, retries, and occasionally decides something nobody specified.
So what is the deployable unit now? What does a release look like when behaviour changes without the artifact changing? What do you monitor when there is no accuracy number, and what does a rollback mean when the failure is a loop of tool calls rather than a bad prediction?

Eval-Driven Development for LLM Systems
by Lucas Eckes (VISIUM)

Testing traditional software and ML systems is reliable work. We assert: same input, same output, a hand-written expected value on the right-hand side, and a suite that still passes in five years.

So what happens when the feature under test is a language model? The same request returns a different string every run, all of them potentially correct. Ground truth rarely arrives because a user who gets a bad answer closes the tab rather than telling you. And the artifact that changed is a prompt, with no hash, no version bump, and no retraining run.

This is a talk about what replaces the suite, at the level of a single application. Where your test cases come from before you have production traffic, and why the ones you write on day three stop describing the system by month six. Which checks need a model to evaluate and which collapse back into plain Python. How to calibrate an LLM judge before you trust the numbers it produces.

Demonstrated end-to-end on a small application with Arize Phoenix, open source and local

Give your agent a local sandbox, not just tools
by Thibault Viglino (VISIUM)

LLMs are often faster, cheaper and more reliable when they write a short program that calls your tools instead of making a sequence of individual tool calls.

Pydantic Monty runs isolated Python with no container, VM or sandboxing service in the loop. Creating a sandbox and running ten commands in it takes 5 ms (Docker: 900 ms, a sandboxing service: 1900 ms).

In this talk we will motivate why a local sandbox is useful and showcase it with Monty. We will see how it interacts with the existing tooling and MCP ecosystems.

TL;DR: Nobody Reads Your Agent's Output
by Christian Abbet (VISIUM)

We hand more and more of our coding work to agents, and we consume what they produce everywhere: code review, documentation, and issue reports. Every run returns a wall of text that no human wants to read (and that machines don't need either) as most of it is often repetition or nitpicks.

This talk asks whether tooling can fix that: output that is short, sharp, and actually worth reading. Less text generated now means less text ingested by every downstream pipeline.

Or maybe one output was never enough. A second option is to have the agent emit different messages: adding context the agent needs and the human would find tedious, or dropping framing the human wants and the agent pays tokens for. Each reader gets what it needs, and neither pays for the other's format.

--- --- --- --- --- --- --- --- --- ---

NOTES

• PLEAS RSVP: If your status changes, change your RSVP accordingly! This enables us to manage reservations.
• If you are on the waiting list: we will do our best to increase the number of seats, so stay tuned

Dear product community: SAVE THE DATE! 🗓️

Our ProductTank Lausanne meetup October 2026 edition will take place on Thursday 01! 🚀

Special thanks to our host for this event: Nexthink 🙏

##############
Agenda
6:00 PM - Doors Open
6:30 PM - Welcome & Intro

6:40 PM - Talk 1: Aga Skraburska - "Why users ignore what you built and what learning science says about it"
Aga has spent two decades turning what organizations expect of people into learning they'll actually use: leadership and learning transformation programmes at ABB, UBS and startups. Now Head of Product Education at Nexthink, where she's rebuilt its educational products to be AI-driven. Trained in systems-psychodynamic coaching, she works where organizational strategy meets genuine human awareness.

7:15 PM - Talk 2: Chantal Estevez - "Product Management isn't the destination -- it's a stepping stone (How product management taught me to lead, take ownership, and ultimately build for myself)"
Chantal is a product leader, consultant, and entrepreneur with experience building technology and AI-driven products across startups and global organizations. As a Product Management Consultant, she has led product and innovation initiatives for international clients across AI, digital health, and emerging technologies. She brings her product experience to entrepreneurial and consulting ventures, using AI to turn ideas into reality and help businesses apply AI effectively.

7:45 PM - Drinks, Snacks & Networking
9:00 PM - Event Ends
##############

📍 Location: Nexthink Offices - Centre Malley-Lumières, Chem. du Viaduc 1, 1008 Prilly

Looking forward to seeing you there!
Follow us: Linkedin

##############

• Are you interested in hosting the next ProductTank event?
• Are you interested in speaking at the next ProductTank event? Please reach out to Claudia.

Découvrez comment la collaboration avec des designers peut transformer les idées en projets concrets et contribuer au succès d’entreprises.

Innovation by Design Challenge

Pour cette 9ème édition, Vaud et Valais unissent leurs écosystèmes créatifs et entrepreneuriaux pour donner aux designers une visibilité inédite et faire de la création un moteur pour notre société.

Pendant deux jours de sprint intensif, 5 équipes ont travaillé aux côtés de jeunes entreprises innovantes pour repenser leurs produits ou services sous l'angle du design. Venez découvrir le résultat de leur travail et assister à la remise des prix.

Au programme : présentation des pitchs par les 5 équipes, conférence d'Hervé Rigal, fondateur et CEO de Base Design, puis remise des prix du jury et du public. La soirée se conclura autour d'un apéritif dînatoire, l'occasion d'échanger avec les designers, les entreprises et les partenaires de cette édition.

Programme
18h00 : Ouverture de la soirée
18h05 : Pitchs : résultats des sprints des 5 équipes
18h30 : Conférence d'Hervé Rigal, fondateur et CEO de Base Design
18h50 : Remise des prix
19h15 : Apéritif dînatoire

📍 Auditoire IKEA, ECAL, Avenue du Temple 5, 1020 Renens

Partenaires : ECAL, PRISM, la Ville de Renens, le Canton de Vaud, le Canton du Valais, l'EPFL et Pro Helvetia