Stockholm MLOps Community

#41 - AI & Cybersecurity

Thu, Nov 19 · 5:00 PM CET

Netlight Consulting AB, Regeringsgatan 25, 111 53 Stockholm, Sweden, Stockholm, SE

***Do note that you have to sign up to the Luma event in order to attend. Do so here: https://luma.com/dlkqt7i2***

All right!!!
​Meetup #41 will take place November 19 at Netlight's offices and will focus on "AI & Cybersecurity".

​I'm incredibly happy that we have Cybersecurity black-belt Zack Korman, self-proclaimed Cybersecurity Troll and CEO & Co-Founder of Embroidery on-board as one of our speakers! Zack has recently been featured in Time, Wall Street Journal and The Atlantic! More importantly, he provides an adult voice in the otherwise at times rather childish rooms where AI & Safety is discussed...

​I'm equally happy to have Alexandra Searle, an Executive Leader at Mission Critical Systems at global powerhouse Ericsson join us as well!

We now have a final list of speakers!
​Presentation titles & abstracts will be provided. Stay tuned!

​Event Program
- Doors open at 17:00 CET
- Talks begin at 17:45 CET
- There will be pizzas & drinks
- There may be a moderated Q&A session....

​Speaker Line-Up

• ​Zack Korman, CEO & Co-Founder of Embroidery. Title & Abstract to be provided.
• Alexandra Searle, Executive Leader at Mission Critical Systems at Ericsson. Title & Abstract to be provided.
• Anna Lewicka, AI Engineer, Lorena Torres Lahoz, Data Scientist both at Novo Nordisk and Alizé Papp, Associate Manager at Netlight will give a joint presentation. Title & Abstract to be provided.
• ​- Mahan Tourkaman, Founder & CEO of Speedrun. Title & Abstract to be provided.
• Hammam Wasfi, Founder of Nordic Institute for AI Risk & Resilience (NIARR). Title & Abstract to be provided.

​Looking forward to seeing you there,

​/Patrick & the Stockholm MLOps Team

#42 - Vultr Agent Runtime Hackathon

Fri, Nov 27 · 9:00 AM CET

Netlight Consulting AB, Regeringsgatan 25, 111 53 Stockholm, Sweden, Stockholm, SE

***Do note that you have to sign-up at the Luma event to be able to attend: https://luma.com/stockholm-nn3n***

All right!!!
​Meetup #42 will take the shape of a full day 12h Hackathon!!! Bring your laptops and your hacking chops and let's go! (And yes, there will be food, drinks and refreshments throughout the day!)

​The hackathon is centred around a single challenge:

​Build a web-based agent that performs real work - writing and running code, or operating a real browser - with every action contained inside a sandbox running on Vultr. Your system should act as a centralized control layer that plans a task, dispatches it to an isolated execution environment, and returns verifiable output.

​Projects should demonstrate multi-step agentic workflows, real executed results rather than described ones, and a production-style web application - all running on Vultr infrastructure.

​Containment-first is required. An agent that only chats is a demo; an agent that executes safely is a product.

​There will be a team from Vultr on-site to help guide you through the day! More detailed agenda will be provided. Stay tuned!

​Who should participate?
​Developers, AI/ML and platform engineers, and technical founders building agentic applications. Participants will work in teams of 2–4. If you show up solo, we'll help you join/form a team!

Pre-reqs
​Laptop and GitHub account, working Python (or TypeScript) and API experience, and basic LLM familiarity. No special hardware needed. Vultr will provide credits for cloud compute, and we'll share a short prep guide beforehand.

Prizes
​The three most impressive projects formally submitted will all receive cash prizes and additional Vultr credits! (More on this later... Stay tuned!)

Hackathon Infrastructure

• ​Deploy a VM-based backend on Vultr (mandatory)
• ​Agent LLM calls must go through Vultr Serverless Inference (mandatory)
• ​Vultr should be the central system of control and orchestration, not just static hosting
• ​Sandboxes run as containers or throwaway instances on Vultr, never inside your app process
• ​Open Source Sandbox example solutions:
• ​OpenSandbox
• ​gVisor
• ​E2B Sandboxes
• ​Microsandbox

Execution Pattern Integration​
Build against one or both patterns:
​Pattern A - Sandboxed Code Execution User asks → model writes code → code runs in a container → real output (chart, file, test log) returns → model explains it. On error, stderr is fed back for a retry.
​Examples:

• ​CSV Analyst - upload a spreadsheet, ask a question in plain English, get an actually-executed chart plus the code that produced it
• ​Prove-It Code Reviewer - paste a snippet or PR; the agent runs it and its tests in the sandbox and reports what really happened
• ​Chart Anything - natural language in, executed matplotlib or plotly image out
• ​File Fixer - messy CSV or JSON in, cleaned file out, with an executed before/after diff
• ​Self-Healing Runner - the agent runs code, reads the error, patches it, and retries, with the retry loop visible on screen

​Pattern B - Sandboxed Browser Use User gives a goal → model plans → Playwright in a container navigates, clicks, types → screenshots return → a vision model on Serverless Inference verifies the result → repeat, with a human approving anything final.
​Examples:

• ​Comparison Shopper - two or three product URLs in, screenshot-backed comparison table out
• ​Form Filler - structured data in, multi-step web form filled, with a screenshot trail and an approve-before-submit gate
• ​Site QA Sweep - point it at a web app and get back broken flows and links with screenshots and repro steps
• ​Research with Receipts - a brief where every claim links to a screenshot of its source
• ​Page Watcher - monitors listing or pricing pages, extracts structured data, and diffs against yesterday​

Containment Focus
​Address real safety and reliability challenges in agent execution:

• ​Process isolation - execution never touches the host or app runtime
• ​Secret hygiene - no API keys or credentials inside the sandbox
• ​Resource limits - time and memory caps on every run
• ​Lifecycle discipline - reset or destroy the environment after each task

​Show how isolation makes autonomous execution shippable.

Production-Ready Web Application

• ​Must be accessible via a public web browser
• ​Demonstrate a real product-style experience
• ​Clear user flows, not just a local demo​

Key Positioning

• ​Vultr is the central backend powering execution and orchestration
• ​Your application plans, dispatches, and verifies real work
• ​Focus on platform thinking, not just a one-off demo

Developer Expectations
​Each team must provide:

• ​GitHub repository with setup and documentation
• ​Vultr VM backend deployment, with agent LLM calls through Vultr Serverless Inference
• ​Public demo URL
• ​Recorded demo video
• ​One containment moment in the video - the sandbox absorbing something unsafe, such as an rm -rf, an infinite loop, or a hostile web page
• ​Clear explanation of architecture and use case

​Technology
Required

• ​Vultr VM backend
• ​Web application deployed on Vultr
• ​Vultr Serverless Inference for agent reasoning (OpenAI-compatible; base URL https://api.vultrinference.com/v1)
• ​A sandbox isolated from your application process

​Strongly Recommended

• ​Docker container as the sandbox boundary
• ​REST or WebSocket APIs for run status and streaming output
• ​Web dashboards showing the execution loop, retries, and screenshot trails
• ​Approve-before-submit gates on any irreversible browser action

​Optional

• ​Vultr API to spin up a throwaway instance per task and destroy it afterward, making Vultr itself the sandbox fabric
• ​Vision-capable models on Serverless Inference for screenshot reasoning
• ​Playwright in Docker for browser automation

Platform & App Acceleration
​To help teams ship faster, we recommend:
​Vultr Serverless Inference: https://docs.vultr.com/products/serverless/inference/provisioning
​Live model list: https://api.vultrinference.com/v1/models
​Vultr API (throwaway-instance pattern): https://www.vultr.com/api/
​How to Set Up Agent Sandboxing on Vultr Cloud Compute: https://docs.vultr.com/how-to-set-up-agent-sandboxing-on-vultr-cloud-compute

Access Method

• ​$200 in free Vultr credits per participant.
• ​Redemption guide: activate via the Vultr Setup Guide
• ​Redemption walkthrough video: https://del1.vultrobjects.com/tech-talk/redeem-vultr-credits-for-hackathons.mp4

​That's it! That's all! Good luck!!!

/Patrick & the Stockholm MLOps Team

#43 - AI & Gaming Industry

Thu, Dec 3 · 5:00 PM CET

Netlight Consulting AB, Regeringsgatan 25, 111 53 Stockholm, Sweden, Stockholm, SE

All right!!!

Meetup #43 will take place December 3 at Netlight's offices and will focus on "AI & Gaming Industry" and will feature speakers from King, ScyllaDB, Netlight our sponsor Nebius and others.

As you know, we are transitioning to Luma and so you need to register at the Luma event to attend. Full event program will be worked out here: https://luma.com/stockholm-rzxp.

Also, to keep up with future Stockholm MLOps events, do follow our Luma Calendar: https://luma.com/StockholmMLOps.

Looking forward to seeing you there,

/Patrick & the Stockholm MLOps Team

#44 - Stockholm MLOps Winterbash!!!

Thu, Dec 10 · 5:00 PM CET

HiQ Stockholm AB, Katarinavägen 15, 116 45 Stockholm, Sweden, Stockholm, SE

All right!!!

December 10, it’s once again time for another Stockholm MLOps Winterbash!!!

As those of you who have been around for a while know, we always try to give local start-ups some exposure as we end the year. This time we’ll once again team up with HiQ and the best view of Stockholm and try to do something special.

Do note that you have to sign up for the Luma event in order to be able to attend. Find it here: https://luma.com/stockholm-efhg.

Format
6 coolest startups × 8 minutes each
Demo. Pitch. Ask.

Event Program

• Doors open at 17:00 CET
• Talks begin at 17:45 CET
• Pizzas & drinks
• Speaker line-up TBD so stay tuned for updates as we select and onboard start-ups.

Looking forward to seeing you there!

/the Stockholm MLOps crew