Kaggle Competition

Women Techmakers Berlin and SPICED Academy are joining forces to host an evening focused on both building *efficient AI systems* and navigating the real challenges of building a *career in tech*—beyond just learning technical skills. ## Talks Talk 1: Confidence Beyond Skills - What Really Holds Women Back in Tech Careers - by Marina Matveevskaia Many women in tech keep investing in new courses, skills, and certifications, yet still feel stuck or “not ready enough” to take the next career step. In this talk, we will look beyond technical competence and explore the less visible factors that often shape career growth much more strongly — such as self-trust, fear of visibility, internalized expectations, and the emotional impact of burnout or layoffs. I will share common patterns I see in highly capable women and why “just improving skills” is often not the real barrier. Participants will leave with new perspectives and simple reflection tools to better understand what is holding them back and how to move forward in a more sustainable and aligned way. Talk 2: Efficient Agentic Systems - by Jane Waithira Let Classical ML Do the Heavy Lifting, Let Agents Do the Thinking There’s a temptation to throw an LLM at every problem—but the most effective systems take a different approach. This talk explores how to combine deterministic, classical machine learning for predictable tasks with LLM-powered agents for reasoning and decision-making—so you can build systems that are fast, cost-effective, and reliable. ## Speakers **Jane Waithira:** Jane Waithira is an innovative, solution-oriented developer working in AI/ML, currently at SAP in Germany, where she integrates applied AI and GenAI for SAP's own cloud infrastructure. With over five years of experience building production AI systems, Jane has established her skillset in practical applications of ML and GenAI. Her talk will provide attendees with a practical framework for building efficient agentic systems that combine deterministic classical ML with the flexibility of LLM-powered agents. [https://www.linkedin.com/in/waithira-macharia/](https://www.linkedin.com/in/waithira-macharia/) **Marina Matveevskaia:** Marina Matveevskaia is a Professional Identity and Transition Coach working primarily with women in tech and international professionals in Germany. With over 14 years of experience in the IT industry, including leadership roles, she understands the unique pressures and challenges women face in fast-paced, male-dominated environments. In her coaching practice, Marina focuses on burnout prevention, impostor syndrome, and career transitions, helping highly capable women build sustainable and fulfilling career paths. She also collaborates with the German Employment Agency (Arbeitsagentur) as an AVGS coach, supporting women in their return to the labour market. [www.linkedin.com/in/marina-matveevskaia](http://www.linkedin.com/in/marina-matveevskaia) ## Why Attend? * Learn from women working in Tech * Get inspired by real stories and practical advice * Connect with like-minded people in a supportive space * Discover career paths across Tech & AI * Network with the WTM & SPICED community Join us for an evening of inspiring talks, practical insights, and meaningful connections in the heart of Berlin’s tech community. ## About SPICED Academy SPICED Academy is a Berlin-based tech bootcamp that helps people transition into tech through intensive, hands-on training. They offer both in-person and online programs across data analytics, data science, web development, and AI, with a strong focus on real-world projects and career support. https://www.spiced-academy.com/en ## Inclusivity Statement Women Techmakers Berlin is committed to creating a **safe, inclusive, and welcoming space**. This event is open to people of all genders who support diversity in tech.

Get ready for a night full of laughs at **Big Berlin Comedy!** High Energy Hosting, great vibes and lots of wild crowd interaction! Whether you're a local or just visiting, this is the perfect chance to enjoy some top-notch comedy with friends. Don’t miss out on the fun – comedy fans unite and let’s make it a night to remember! Doors 8pm Showtime 9pm Tickets It's NOT A FREE SHOW. It's Pay What You Want. You just decide the amount you want to pay AFTER the show. Artists deserve to be paid. If you plan to not pay at all, please don't come to our show!! Free Entry + Donation based. We suggest a donation of 10€-15€. Students & unemployed 5€-7€. We accept cards & cash

​Informal meetup for people interested in OpenClaw and AI agents. We share what works/what doesn't and what we’re currently trying. Feel free to bring your laptop and half-working setup. We're all here to learn how to ride the tiger \-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\- ​Events usually unfold in two parts: 1st part - People showcase projects, tools, setups and discuss learnings 2nd part - Open discussion/networking

Come play Magic's most accessible competitive format! We meet every Tuesday at 18:30 at RuDi-Das Stralauer Kultur- und Nachbarschaftszentrum in Friedrichshain, \~10 minutes by foot from Warschauer Str. and Ostkreuz. **The best way to get in touch is to join the WhatsApp group:** https://unlock.ly/I7IhAbb *Even if Meetup has only 1 or 2 RSVPs, we are normally 20-30 people every week!* **FAQ:** **Do I need my own deck?** No, people that come bring extra decks, and you are free to borrow one if you want to test the format before buying into it! **Casual or Competitive?** We play casually to allow people to come late and leave early. Feel free to stay for any amount of time between 18:30 and 22:30. To this end, feel free to bring proxies, as long as it is clear what card you are proxying! **Why do you charge an entry fee?** Our 2 euro entry fee is a donation to the community center that we use to host our event.

BHNT #112: the fifth BHNT in 2026. The title is inspired by the issues around Bambulab (Boo). Your hacks do not have to be connected to the title (bonus points if they do though) Please RSVP and bring your hacks! There are 8 dynamically allocated Slots that consist of 5min presentation + 5min conversation with the audience. To refresh your memories or get familiar with the concept - see some old hacks here: [https://bhnt.c-base.org](https://bhnt.c-base.org/) Hope to see you - looking forward! [RSVP here](https://platform.openmeet.net/events/bhnt-112-bamboo-hacks-8zv0v)

🎤 **What Happens at a Toastmasters Meeting?** We change the time to 7pm please aarive 10 minutes earlier. Curious about Toastmasters? Come experience it for yourself! At **Toastmasters Center Berlin**, our meetings are designed to help you grow as a speaker, listener, and leader — in a fun, supportive environment. Here’s what you can expect: ✅ **Warm Welcome** – Guests are always greeted with open arms. No pressure to speak — just observe and enjoy! ✅ **Prepared Speeches** – Members deliver inspiring, informative, or entertaining speeches they've crafted. ✅ **Impromptu Speaking (Table Topics)** – A fun challenge where volunteers speak on surprise topics for 1–2 minutes. Great for thinking on your feet! ✅ **Constructive Feedback** – Every speaker receives thoughtful evaluations to help them improve. ✅ **Leadership & Roles** – Members take on meeting roles that build confidence and leadership skills. Whether you're looking to overcome stage fright, sharpen your storytelling, or simply meet like-minded people — this is the place to start. 🗓️ **Join us as a guest — no experience needed!** 📍 **Toastmasters Center Berlin** 💬 **Grow your voice. Share your story.**

## Learn Go and NixOS deployments with large language models Hello, 世界! When used sensibly, language models can be tutors, too. For meetup #60 on Tuesday [May 26, 2026 19:00 CET](https://www.meetup.com/leipzig-golang/events/312537727) we are really happy to have [Maxime](https://www.linkedin.com/in/plumps/) dive into Nix/NixOS with the help of language models. Nix is a functional package manager and its immutable traits enable robust, reproducable deployments of Go (and other) projects. The high level goals of Nix/NixOS are similar to other immutable Linux distributions, like [Silverblue](https://fedoraproject.org/silverblue/) or [Bazzite](https://bazzite.gg/). Becoming familiar with the Nix configuration language can be a challenge, but one that a well instructed tutor may help with. > Artificial intelligence techniques are increasingly used in education to enable personalized learning and intelligent tutoring [LLM Agents for Education: Advances and Applications](https://aclanthology.org/anthology-files/anthology-files/pdf/findings/2025.findings-emnlp.743.pdf) (11/2025) Why reproducible and immutable deployments play a role? [Justin Garrison](https://justingarrison.com/blog/state-of-immutable-linux/) says: > It’s 2026, if you’re not using something immutable (or at least reproducable) you’re doing more maintenance work than you should. [blog post recapping talk from [Southern California Linux Expo 23x](https://www.socallinuxexpo.org/scale/23x)], 03/2026, PASADENA, CA ### Schedule * 18:45 Doors open * 19:00 Welcome * 19:10 Dive into Nix/NixOS with LLMs * 19:50 Open discussion We’ll meet: * in person at [Basislager Leipzig](https://basislager.co), at [Peterssteinweg 14, 04107 Leipzig](https://maps.app.goo.gl/1fMkeDSPZ7Aauszh8) ([OSM](https://www.openstreetmap.org/node/3504864558)) * and online via [https://meet.google.com/drk-bptj-xss](https://meet.google.com/drk-bptj-xss) Join us to discuss robust Go deployments, language models as learning tools and more!

**⚠️ IMPORTANT: REGISTRATION MANDATORY ⚠️** Registration on **Luma** is **REQUIRED** to attend this event. **Link: https://luma.com/1sre8dy7?utm_source=meetup** Your registration is subject to host approval. You must complete the registration process on lu.ma to receive the full event location details and confirmation of your attendance. **Please note: Without approved registration on Luma, you will NOT be able to access the event location or attend.** We are excited to host a **BLISS x dida workshop** featuring **Lazar Obradović (Lead Data Scientist @ cognee.ai)**, who will guide us through an interactive session on Agentic AI. ​Title: Explainable Scientific Discovery with AI Memory: Hypothesis Generation and Validation with Cognee and Bayer 📅 Date: 27.05.2026 🕕 Time: 18:00 📍 Location: TU Berlin Marchstrasse 23 [Room 0.011] ​The session will last around 2 hours, followed by a networking session with dida and fellow AI enthusiasts (and free pizza!🍕). Bring your laptop! **​Abstract: Building "AI scientist"** systems that can reliably generate and evaluate research ideas remains effectively an open problem. While LLMs make hypothesis generation cheap, current systems still struggle to connect evidence across papers, domains, and mechanisms in a structured and reusable way. Evaluation is equally difficult, often relying on opaque “LLM-as-a-judge” methods that are hard to interpret or reproduce. We use Cognee to ingest scientific literature and construct a graph-based representation of papers, claims, and entities with associated vector embeddings. We then use this structure to select and organize the context used for hypothesis generation. Candidate hypotheses are evaluated using explicit graph- and vector-based metrics grounded in the underlying corpus. Initial evaluations by Bayer across targeted biomedical domains demonstrated that graph-based AI memory can reliably support scientific hypothesis generation and validation. **⚡ FINAL REMINDER ⚡** **You MUST register and be approved on Luma to attend. The event location will only be visible after your registration is confirmed by the host. Link: https://luma.com/1sre8dy7?utm_source=meetup** *** We are **BLISS e.V.**, Berlin’s AI community connecting like-minded individuals passionate about machine learning and data science. Our **BLISS Workshops** connect **students and young professionals with industry partners**, offering an inside look into **how machine learning is applied in real-world settings** \- from research and development to deployment\. ​We are **dida**, scientific engineers who believe that **reliable AI** should not be a **"black box".** That is why we prioritize transparency, mathematics, and code over hype. By **bridging the gap between theoretical research and production**, we develop custom white-box AI solutions that are fully explainable, rigorously engineered, and free of "magic". ​​​dida Website: [https://dida.do](https://dida.do/?utm_source=luma) ​​dida Youtube: [https://www.youtube.com/@dida-do](https://www.youtube.com/@dida-do?utm_source=luma) ​​​BLISS Website:[ https://bliss.berlin](https://bliss.berlin/?utm_source=luma) ​​​BLISS Youtube:[ https://www.youtube.com/@bliss.ev.berlin](https://www.youtube.com/@bliss.ev.berlin?utm_source=luma)

Tickets start at 12€: [https://fienta.com/comedy-comfort-berlin-182152](https://fienta.com/comedy-comfort-berlin-182152) A night of real laughs, good energy, and the kind of comedy that feels right. Comedy Comfort is a warm, laid-back English comedy show in the heart of Friedrichshain. Featuring some of Berlin's best comedians and ones to watch. Whether you're a comedy regular or haven't been out in a while, this is the easiest yes of your week. Come out, grab a drink, and settle in for a night that's exactly what it sounds like. Comfortable, funny, and very Berlin. Perfect for a night out with friends, a low-key date, or a good excuse to leave the house. 📅 Date & Time: 28.May.2026 Seating Starts: 7:30pm Show Starts: 8:00pm 🏢 Venue: The Wall Comedy Club Grünberger Straße 84, 10245 Berlin Hosted by: Nya Yeanafehn Nya Yeanafehn is a stand-up comedian, host, and podcaster who began his comedy career in New York City. He is now based in Berlin. He's known for sharing stories about his experiences in Europe and his unique view of life. Nya is also the producer and host of the "Third Culture Talk Podcast,". Where he talks with people who grew up in cultures different from their current one. Including people from all kinds of backgrounds, sharing their unique stories. The podcast was recently featured in Stern, a popular newspaper in Germany.

Join us for an evening on the practical side of AI agents. We'll dig into context engineering and why relevance matters more than prompt tricks, then look at what it takes to run autonomous agents safely alongside humans. Food and drinks provided — stick around after for networking. ✍️ RSVP asap as capacity is limited so grab your spot asap! 📅 **Date and Time** Wednesday, May 27, 2026 from 18:00-20:45 📍 **Location** [EBCONT office, beyond Quartier Heidestrasse, 34, 10557 Berlin](https://maps.app.goo.gl/aQGPgteqhQ2yrmx96) 📝 **Agenda** 18:00 – Doors open, arrivals and check-in 18:20 – Welcome note by EBCONT 18:30 – **Agent Builder Hope is not a strategy — relevant context for data driven agents** by Anderson Queiroz — Elastic *What are agents and context engineering? And why we think the "center of gravity" for context engineering is much more about relevance and your data than only prompts and memory management.* 19:00 – Q&A & quick break 19:15 – **Adapting to AI in Security** by Jenny Pinheiro — Tines *Best practices for autonomous AI and human interaction in the context of workflows.* 19:45 – Pizza, drinks & networking \*\*\* Invite your friends and join us for an evening of learning and networking with fellow engineers and speakers! Thank you to **EBCONT** for hosting and to **Tines** for teaming up with us on this one!

**Berlin’s Only Comedy Show That Fixes Your Problems (Kind Of)!** Stand-up comedy meets hilarious, unqualified life advice! Comedians tackle your anonymously submitted problems live on stage—roasting, dissecting, and turning them into comedy gold. **Where?** The hidden Mitte gem —**Art.City.People** in **Heckmann-Höfe!** **When?** Doors: **8:00 PM** \| Show: **8:30 PM** Come for the stand-up, stay for the therapy—just bring your problems (or a friend with worse ones). Every show is a fresh mix of **four experienced comedians and new audience problems**—so you never know what to expect! Hosted by **Lena Stolby** — she’s Russian, so she *really* knows about problems! **&** We are a free entry pay-what-you-want show, and **have been running solely thanks to the support of the audience**, so to help us keep making this world a drama free place we **suggest a contribution of €12-15!** **Seats are limited, so book now!** The room gets very busy, so, to make sure you get a seat please book a seat via Eventbrite here (it’s free): https://www.eventbrite.com/cc/comedy-therapy-events-1626059

Welcome to the PyData Berlin May meetup! We would like to welcome you all starting from 18:00. There will be food and drinks. The talks begin around 18.30 and the doors will close at 18:45. **Make sure to arrive on time!** Please provide your first and last name for the registration because this is required for the venue's entry policy. If you cannot attend, please cancel your spot so others are able to join as the space is limited. **Host**: **GetYourGuide** is excited to welcome you to this month's version of PyData. \*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\* The Lineup for the evening **Talk 1: Text2SQL in the Wild — Agentic Workflows & Semantic Models on Customer Data** **Abstract**: Translating a business user's natural language question into a reliable SQL query has huge value for business analysts, but doing it accurately at scale, on messy enterprise data, for complex queries, is incredibly difficult. This talk walks through a production Text2SQL system built on four pillars: semantic models built on customer data, RAG-based semantic search, an agentic verification and correction loop for building the SQL, and an evaluation framework for the entire process. Raw schema information is not enough for text2sql to work. Rather, thorough documentation including business metrics, synonyms, and qualified example queries, are required. We'll cover how to automate this documentation pipeline by mining query logs, generating descriptions with LLMs, and organizing everything into a knowledge graph and vector search index. From there, we'll dive into the agentic flow that takes a user question and iteratively generates, validates, and fixes SQL against a live database. The agentic framework analyses syntax errors and execution results to help it fix the SQL. Participants will leave with practical takeaways on RAG architecture for structured data, agentic retry patterns, and how to think about evaluation for Text2SQL systems in production. **Speaker**: Oren Matar **Bio**: Oren Matar is a principal data scientist and algorithms developer, with a background in social sciences and Bayesian methods. He specializes in NLP and time series forecasting, as well as agentic methods for data retrieval and processing. **Talk 2: Interpreting and Communicating Statistical Models** **Abstract**: Extracting actionable insights from complex statistical models remains a challenge, as raw coefficients are often uninterpretable due to nonlinearity, interactions, or hierarchical structures. This talk introduces a unified framework for model interpretation based on the principles of the Marginal Effects project ([https://marginaleffects.com/](https://marginaleffects.com/)). We move away from internal model parameters toward quantities of interest, such as marginal effects and adjusted predictions that translate statistical output into the "natural language" of the data. We will demonstrate these concepts in Python using the Bambi interpret module, showcasing a seamless workflow for interpreting Bayesian models built on PyMC. The audience will learn how to use the four primary interpretative pillars: Predictions, Comparisons, Slopes, and Marginal Means to compute average marginal effects and visualize conditional relationships. By the end of this session, you will be equipped to turn sophisticated GLMs and multi-level models into clear, rigorous narratives that are easily communicated to stakeholders. **Speaker**: Juan Orduz **Bio**: Juan is a Mathematician (Ph.D. Humboldt Universität zu Berlin) and Principal Data Scientist at PyMC Labs. He is interested in interdisciplinary applications of mathematical methods. In particular, time series analysis, Bayesian methods, and causal inference. **Lightning talks** There will be slots for 2-3 Lightning Talks (3-5 Minutes for each) between the two main talks. Kindly let us know if you would like to present something :) \*\*\* NumFOCUS **Code of Conduct** THE SHORT VERSION Be kind to others. Do not insult or put down others. Behave professionally. Remember that harassment and sexist, racist, or exclusionary jokes are not appropriate for NumFOCUS. All communication should be appropriate for a professional audience including people of many different backgrounds. Sexual language and imagery are not appropriate. NumFOCUS is dedicated to providing a harassment-free community for everyone, regardless of gender, sexual orientation, gender identity, and expression, disability, physical appearance, body size, race, or religion. We do not tolerate harassment of community members in any form. Thank you for helping make this a welcoming, friendly community for all. If you haven't yet, please read the detailed version here: https://numfocus.org/code-of-conduct \*\*\*

In Bad Company is a one-hour stand-up show hosted by Sepideh Kaav, featuring 2–3 of Berlin’s best comedians at one of Mitte’s coolest bars, HIER WO DU STRAHLST. Expect a night of great comedy, terrible decisions, and the kind of socializing where by the end of the night we all somehow know each other a little too well. No topic is off limits. No one is fully safe. Come with friends, come with a date, come alone, honestly, especially come alone, maybe you meet your future best friend or soulmate here. 🍸 HIER WO DU STRAHLST 📅 Thursday 8:30 PM (CEST) Doors: 20:30 Show: 21:00 to 22:00

**Bob on Tour – IBM Bob live erleben 💙** Wie fühlt sich ein agentischer Coding Assistant im echten Entwicklungsalltag an? Bei **Bob on Tour** kannst Du IBM Bob gemeinsam mit Expert:innen hands-on ausprobieren. In einem eintägigen, technisch fokussierten Format arbeitest Du an realistischen Coding-Aufgaben, von geführten Labs bis zur Anwendung auf eigene Use Cases. Dabei lernst Du, wie Bob Entwicklungsworkflows ergänzt, Codebasen verständlicher macht und mehrstufige Aufgaben unterstützt. **Das nimmst Du mit:** ✅ Sicherer Umgang mit den wichtigsten Bob-Funktionen ✅ Praktische Erfahrung mit agentischer Coding-Unterstützung ✅ Impulse für reale fachliche und technische Problemstellungen 👉 **[Jetzt anmelden und IBM Bob live erleben](https://luma.com/5g0x9318)**

**How does a TennisColumbus Season / League run?** The league advertises the season dates and builds a queue of committed players for the season. **Kickoff Day - June 10th** The start day of the season, players are sent a kickoff email that contains important information about the league, the link where your league standings and players contact information. We guarantee 6 playing partners at your playing level, but have been averaging closer to 15+ partners in most cities. The number of different levels we run is solely based upon the number of players enrolled for the league kickoff. Typically we are running a Skilled-3.0, Competitive-3.5 and Advanced-4.0 in most cities. **Your Task - "Flexible Scheduling"** After this kickoff email is sent, it is the **player's task to communicate with other players**. Players should work with their partners to find an agreeable time and location to play the match. While TennisColumbus doesn't mandate your playing schedule, it is recommended that players schedule at least one match per week. By request of the players, we started to allow players to play 1 rematch per season. The regular season is all about playing as much as you can. As of Feb. 10, 2026 we've had an amazing 2,017 players play more than [20 matches in a season](https://www.tenniscolumbus.com/info/MatchesInSeason). **Where to Play?** Play at your local free tennis courts, tennis parks, condo courts or tennis clubs. The league strongly suggests that players jointly try to pick a tennis court location convenient to both. We provide an extensive list of [tennis courts](https://www.tenniscolumbus.com/TennisCourts), including # of courts, lighting, hitting walls, etc. We strive to keep this list up-to-date. TennisColumbus sets up a must play dates to push players out on the courts. The final deadline is the date marking the end of the season, at which point players with 3-5 wins (Actually total is specified on the division page) will qualify for a post-season playoff to determine the league champion. **How to Play?** Players can use three mostly standard playing formats: 2 out of 3 sets, 2 sets with 10 point super tie-breaker or the 10-game pro set (First to 10, used when court time is limited). On Feb. 2018, we added Fast Tennis 4 game pro set format as a valid format. **Playoffs** Each season concludes with a playoffs where players with anywhere from 3 to 5 season wins qualifies for a single elimination tourney. The champion is awarded based upon the league [Prize Pool](https://www.tenniscolumbus.com/info/prize_pool3). Each singles league champion also receives a playing entry into one of two national championships we run. **[JOIN TODAY](https://www.tenniscolumbus.com/join)** Full price is $39.95 to play in a season. The earlier you sign up we typically offer discounts during these tough economic times. Just go to the [Join Page](https://www.tenniscolumbus.com/join) and complete the short form. We'd be happy to find you dedicated tennis playing partners.

Most people use AI like a search box: they type one sentence, hope for the best, and get frustrated when the answer is generic, wrong, or useless. But getting better results from tools like ChatGPT, Claude, Gemini, and other AI systems is not about memorizing magic prompts. It is about learning how to give the AI better context. In this beginner-friendly session, we’ll break down how to make AI dramatically more useful by improving the way you communicate with it. You’ll learn how to give clearer instructions, provide examples, set constraints, ask for better output formats, and use follow-up questions to turn a mediocre answer into a genuinely useful one. We’ll cover practical techniques you can use immediately for work, learning, writing, coding, planning, research, and everyday problem solving. We’ll also touch on why these same ideas show up in more advanced AI systems, including RAG, agents, evaluations, and AI workflows. No technical background required. Bring your curiosity, your questions, and maybe one real task you wish AI was better at helping you with. **What you’ll learn:** * Why “better prompting” is really about better context * How to structure requests so AI gives more useful answers * How to use examples, constraints, and output formats * How to iterate when the first answer is not good enough * How these skills connect to more advanced AI workflows This meetup is for anyone who wants to move beyond basic ChatGPT usage and start getting more practical value out of AI. LOGISTICS AND PARKING: The talk starts at 7:00 PM. The first half hour is reserved for everyone to get set up and mingle. Free pizza and drinks! The cheapest parking option is to find street parking, which will only cost you a few bucks. Otherwise, park in the nearby veteran's museum lot for $8. It's highly recommended you avoid the nearby $15 garage parking.

We connect you with up to 30 Men or Women tennis partners close to your PLAYING REGION and skill level. This program is less competitive, no champions crowned, no league standings just dedicated tennis partners who want to meet up with you on the courts. Players will meet up to play a tennis match or just to hit around. Just go through the [Join Page](https://www.tenniscolumbus.com/partner-program) to enter this program. [https://www.tenniscolumbus.com/partner-program](https://www.tenniscolumbus.com/partner-program)

**Important time note:** Please plan on arriving between 5:30 and 6:00 as the elevators lock after 6 and you'll need to message us and we'll need to come get you. The building address is 4450 Bridge Park The entrance is 6620 Mooney St, Suite 400 You will need to scan your ID at the door to get a visitor badge. **Abstract** Like it or not, AI agents are now capable of turning a quickly written paragraph of requirements into a pull request that is ready to be integrated into real-world production applications and it's now our responsibility to make sure AI doesn't go rogue and take down prod - or corrupt our data by misunderstanding the requirements or our existing schemas. In this session we'll explore strategies to protect our codebases through unit and integration testing, documentation, and code review along with additional ways of providing context and guard rails to our AI agents as they carry out the work we've assigned them to do. By the time we're done, you'll have a firm grasp of the problem and understand some helpful options for protecting your codebase from vibe coding mishaps getting YOLOed into prod. **YouTube Link** https://youtube.com/live/BltmWMH1zG0?feature=share

QA or the Highway is a one-day, affordable, regional, professional conference featuring real-world experience and thought leadership in the QA and testing industry. This is a ticketed event please register here: https://www.qaorthehwy.com/ Featured Keynote Speakers: **Matthew-Hope Eland** **(Wizard at Leading EDJE)** \- An AI Specialist and Wizard at Leading EDJE who is known to teach software engineering\, AI\, and data science concepts in the most ridiculous ways possible\. Matt has used machine learning to settle debates over whether Die Hard is a Christmas movie\, reinforcement learning to drive the behavior of digital squirrels\, data analytics to suggest improvements to his favorite TV show\, and AI agents to play board games and create an AI agent with the personality of a dog\. Matt is the author of "Data Science in \.NET with Polyglot Notebooks" and "Refactoring with C\#" as well as several LinkedIn Learning courses\. Matt helps organize the Central Ohio \.NET Developer Group\, runs several blogs and a YouTube channel\, has a Master’s of Science in Data Analytics\, and is a current Microsoft MVP in AI and \.NET\. **Tatyana Arbouzova** **(CEO at Innovate QA)** \- Tatyana Arbouzova is an engineering and business leader with a strong background in Quality Engineering across multiple industries\, including Big Tech\, Healthcare\, and Entertainment\. She has held leadership roles at world\-class companies such as Microsoft\, VMware\, Disney\, and The Pokémon Company International\, where she focused on building quality\-driven cultures and scaling teams to deliver high\-impact products\. With decades of experience\, Tatyana has helped organizations transform their quality practices so teams can deliver software efficiently\, confidently\, and with measurable business outcomes\. Today\, Tatyana advises software companies on adopting AI to optimize quality practices and improve how software is delivered at scale\. She is also a passionate community builder and the founder of Innovate QA\, a thriving Seattle\-based community and conference for quality professionals\.

Couldn't make Knowledge? Or want to debrief the dancing robots or Autonomous Workforce? Join us for a Knowledge '26 recap, insights sharing, a couple rounds of golf, and fun at Topgolf. As always, drinks and food will be provided. More details to come — mark your calendar, RSVP, and save your spot today!