# PyCon Lithuania — Full Export > Every confirmed talk's abstract, speaker, and time slot for the current and previous edition, plus every static page. For a curated index instead, see /llms.txt. ## 2027 — PyCon Lithuania 2027 ## 2026 — PyCon Lithuania 2026 # LLMs through my last 3 professions: an interdisciplinary approach > Talk, 25 min — April 10, 2026 at 12:00 **Speaker:** James Donahue **Track:** AI Day - Apr 10 **Day:** AI Day (2026-04-10) **Room:** Deimantas/Diamond (3rd building) ## Abstract We have heard a lot about LLMs from tech experts, but what do an economist, an English teacher, and a tourism manager have to say about it? Fortunately, I've been all three and would love to share my experience! --- # Quantum Machine Learning with Qiskit > Workshop, 45 min — April 10, 2026 at 11:00 **Speaker:** Artem Konotpchyk **Speaker:** Manta Ribkauskyte **Track:** AI Day - Apr 10 **Day:** AI Day (2026-04-10) **Room:** Inovation hall (4th building) ## Abstract Quantum Machine Learning (QML) combines quantum computing and classical machine learning, but its practical value is often misunderstood. In this hands-on workshop, we will explore QML using Qiskit, build and run real quantum machine learning models, and compare them with classical approaches. The session focuses on practical intuition, runnable Python code, and a clear discussion of current advantages, limitations, and realistic use cases of QML. --- # AI Day Intro > Talk, 25 min — April 10, 2026 at 06:00 **Day:** AI Day (2026-04-10) **Room:** Great hall, (3rd building) ## Abstract TBD --- # Exposing Greenwashing: Satellite ML for Carbon Credit Verification > Talk, 240 min — April 09, 2026 at 08:00 **Speaker:** Neeraj Pandey **Track:** Data Day - Apr 9 **Day:** Data Day (2026-04-09) **Room:** Inovation hall (4th building) ## Abstract The carbon market is set to reach 1T dollars by 2030, yet 84% of offsets fail to deliver real climate benefits. Verification still relies on sparse site visits and self-reported data. This poster shows a Python workflow that audits carbon projects using satellite imagery and ML, detecting over-crediting and leakage in REDD+ sites. With open data and open-source tools, anyone can compare claimed versus observed forest outcomes and verify what projects actually deliver. --- # Are we free-threaded ready? Looking at where free-threaded Python fails > Talk, 25 min — April 08, 2026 at 09:00 **Speaker:** Cheuk Ting Ho **Track:** Python Day - Apr 8 **Day:** Python Day (2026-04-08) **Room:** Great hall, (3rd building) ## Abstract Free-threaded Python aims to significantly improve performance, allowing multiple native threads to execute Python bytecode concurrently. In this talk, we will explore the current state of Python's free-threading initiative and assess its practical readiness for widespread adoption. --- # Leading Through the Shift: What Engineering Leadership Actually Looks Like > Talk, 25 min — April 09, 2026 at 08:00 **Speaker:** Justinas Kuizinas **Speaker:** Aurimas Griciunas **Speaker:** Karolina Griciunė **Speaker:** Tomas Peluritis **Track:** Data Day - Apr 9 **Day:** Data Day (2026-04-09) **Room:** Event hall (4th building) ## Abstract Building great engineering teams has never been straightforward — but the rules keep changing. Three back-to-back panel discussions with CTOs and engineering leaders covering the full spectrum: scaling teams and competing for talent in a small market, navigating a leadership role that looks nothing like it did five years ago (AI included), and making the hard calls on culture, tech debt, and architecture when there's no clear playbook to follow. --- # AI Lithuania Summit > Talk, 25 min — April 10, 2026 at 08:00 **Speaker:** Linas Petkevičius **Track:** Lithuanian Artificial Intelligence Association **Day:** AI Day (2026-04-10) **Room:** Event hall (4th building) ## Abstract Tutorial: Unsloth for Small Language Models Fine-Tuning Small Language Models (SLMs) can deliver strong performance with far lower computational demands than large LLMs, making them ideal for on-device, edge, or cost-sensitive applications. However, fine-tuning them effectively and quickly on limited hardware remains challenging. This hands-on tutorial on Unsloth, an open-source library that makes fine-tuning SLMs dramatically faster and more memory-efficient. --- # AI Agents: risks and legal > Talk, 25 min — April 10, 2026 at 09:00 **Speaker:** Linas Petkevičius **Speaker:** Karolina Griciunė **Speaker:** Jonas Lekevicius **Speaker:** prof. Paulius Pakutinskas **Speaker:** Neringa Gaubiene **Track:** Lithuanian Artificial Intelligence Association **Day:** AI Day (2026-04-10) **Room:** Event hall (4th building) ## Abstract With AI Agents there is multiple things from risks we need to take into account to, legal issues which might appear. We will have a panel discussion with Moderator: prof. Paulius Pakutinskas Panel Jonas Lekavičius, Du Bitai Karolina Griciūnė, SwirlAI Neringa Gaubienė, VU --- # Stats Meets ML - What I learned from my Machine Learning Certification > Talk, 25 min — April 09, 2026 at 08:30 **Speaker:** James Donahue **Track:** Data Day - Apr 9 **Day:** Data Day (2026-04-09) **Room:** Great hall, (3rd building) ## Abstract Statisticians and machine learning specialists have a lot to learn from each other (even if they don't think so). This talk lightheartedly awards points to both classical statistics and machine learning, with an attempt not to offend anyone (but to annoy everyone). Topics include: Are confidence intervals worth it? What is bias, anyway? Can I just code it in Python? --- # AI & Ethics > Talk, 25 min — April 10, 2026 at 08:30 **Speaker:** PJ Hagerty **Track:** AI Day - Apr 10 **Day:** AI Day (2026-04-10) **Room:** Krantas/Shore 213 (3rd building) ## Abstract It's been in the news, everywhere. Artificial Intelligence is the next thing in the evolution of technology. While it's probably not the end of everything as some sources say, it's likely true to change the face things for years to come. In this talk, we'll talk about what developers should focus on to build their AI knowledge and skills, what things we need to know outside of the technology to help our understanding, and some general ideas around AI itself. --- # Computer Vision, Meet Sports > Talk, 60 min — April 10, 2026 at 06:30 **Speaker:** Piotr **Track:** Keynote **Day:** AI Day (2026-04-10) **Room:** Great hall, (3rd building) ## Abstract What does it take to turn raw game footage into a full sports analytics dashboard? More than you'd think. This talk walks through the complete computer vision pipeline I built for basketball and football. From detecting players and tracking them through occlusions, to reading jersey numbers, mapping positions onto a 2D court, and computing real-time stats. Every model is open-source. Every step solves a problem that creates the next one. --- # Reading the Mind of an LLM > Talk, 25 min — April 10, 2026 at 08:00 **Speaker:** Luca Baggi **Speaker:** Gabriele Orlandi **Track:** AI Day - Apr 10 **Day:** AI Day (2026-04-10) **Room:** Great hall, (3rd building) ## Abstract What if you could watch an AI’s thought take shape? For years, LLMs have been impenetrable "black boxes," but we are finally beginning to find ways to see how the ghost in the machine actually works. This talk explores \*\*mechanistic interpretability\*\*, a subfield of AI that aims to understand the internal workings of neural networks. Mapping these internal "circuits" is not only just a philosophical curiosity - or duty: it is a high-stakes engineering necessity for safety, debugging, and trust. --- # Python for Data Quality in 2025: Why tests alone are no longer enough > Talk, 25 min — April 09, 2026 at 08:00 **Speaker:** Artsem **Track:** Data Day - Apr 9 **Day:** Data Day (2026-04-09) **Room:** Krantas/Shore 213 (3rd building) ## Abstract In 2025, classic data tests via Python are not enough. During 25-30 minutes talk I will show how Python powers modern Data Quality: from real-time freshness checks to anomaly detection and orchestrator integration. No AI hype: starting with quick Data Quality overview and problem statement I will show practical code, architecture, and hands-on engineering for resilient pipelines from Data Engineer/Data Quality Engineer perspective. --- # Friend or Foe? AI at Play in Cybersecurity > Talk, 25 min — April 10, 2026 at 12:00 **Speaker:** Cheuk Ting Ho **Track:** AI Day - Apr 10 **Day:** AI Day (2026-04-10) **Room:** Krantas/Shore 213 (3rd building) ## Abstract AI is a double-edged sword in cybersecurity. This talk explores its dual role. Why AI excels: Vast open-source training data and profit-driven, coding-optimized models make AI a fast, multi-domain expert at writing and finding vulnerabilities in code. Gatekeeping: Projects like Claude Mythos and Project Glasswing raise hard questions about who should access these powerful tools. The asymmetry: AI is fundamentally reshaping the defense/offense balance—and demands responsible deployment. --- # Stop Guessing: Build Feedback Loop for Prompt Engineering > Talk, 25 min — April 10, 2026 at 11:00 **Speaker:** Tadas Goberis **Track:** AI Day - Apr 10 **Day:** AI Day (2026-04-10) **Room:** Deimantas/Diamond (3rd building) ## Abstract Most teams iterate on prompts by eyeballing outputs and hoping for the best. This talk presents a different approach: connect your prompt to a measurable downstream outcome, build a test set, and let metrics drive improvements. I'll walk through a complete feedback loop - from prompt to retrieval metrics to automated error analysis to LLM-powered iteration - and show how this turns prompt engineering from guesswork into something you can actually measure and improve systematically. --- # Documenting Python Code—and Whether AI Can Really Help > Talk, 55 min — April 08, 2026 at 08:00 **Speaker:** Christian Heitzmann **Track:** Python Day - Apr 8 **Day:** Python Day (2026-04-08) **Room:** Krantas/Shore 213 (3rd building) ## Abstract Good documentation doesn’t happen by accident. But it also doesn’t have to be painful. This talk shows how Python developers can integrate documentation naturally into their daily work. We’ll look at docstrings, turn them into readable docs with reStructuredText and Sphinx, and learn how few organizational measures, docs-as-code practices, and automation can help—or get in the way … --- # A Practical Guide to Testing with Pytest, Faker, and Hypothesis > Talk, 25 min — April 08, 2026 at 11:00 **Speaker:** Kader Miyanyedi **Track:** Python Day - Apr 8 **Day:** Python Day (2026-04-08) **Room:** Krantas/Shore 213 (3rd building) ## Abstract Writing tests is an important part of every project. In this talk, I will show how to improve your tests using Pytest, Faker, and Hypothesis. We will start with Pytest, a simpler and more readable way to write tests. Then we’ll look at Faker, which helps create test data more easily. Finally, we’ll explore Hypothesis, a tool that generates random test cases to help find hidden bugs. You will leave this talk with clear examples and useful tips to write better tests in your projects using modern tools. --- # Claude Code Conspiracies > Talk, 60 min — April 09, 2026 at 13:30 **Speaker:** Katharine Jarmul **Track:** Keynote **Day:** Data Day (2026-04-09) **Room:** Great hall, (3rd building) ## Abstract Just what does Claude Code need access to and why? In this talk, we'll dive into privacy and security concerns when using LLMs, code assistants and AI agentic workflows. Aside from making you more paranoid, you'll leave with some practical tips on how to cover your prompts in tin foil and avoid the worst types of mistakes. --- # From OpenAI to DeepSeek: New Scaling Laws for LLMs that can Reason > Talk, 25 min — April 10, 2026 at 11:30 **Speaker:** Luca Baggi **Track:** AI Day - Apr 10 **Day:** AI Day (2026-04-10) **Room:** Krantas/Shore 213 (3rd building) ## Abstract With o1, OpenAI ushered a new era: LLMs with reasoning capabilities. This new breed of models broadened the concept of scaling laws, shifting focus from train-time to inference-time compute. But how do these models work? What do we think their architectures look like, and what data do we use to train them? And finally - and perhaps more importantly: how expensive can they get, and what can we use them for? --- # From Sports Stats to AI Safety: The Ranking Renaissance > Talk, 25 min — April 09, 2026 at 11:30 **Speaker:** Gediminas Sadaunykas **Track:** Data Day - Apr 9 **Day:** Data Day (2026-04-09) **Room:** Great hall, (3rd building) ## Abstract In 1952, two statisticians proposed a simple model for comparing sports teams. In 1960, it became the foundation of chess ratings. Today, that same math powers everything from ChatGPT's alignment to Chatbot Arena leaderboards. But you don't need to be OpenAI to use it. I'll show how Bradley-Terry and preference-based ranking can solve everyday problems: comparing A/B test variants, ranking search results, evaluating ML models, prioritizing features, and more. --- # Why Git Still Matters > Talk, 25 min — April 08, 2026 at 12:00 **Speaker:** PJ Hagerty **Track:** Python Day - Apr 8 **Day:** Python Day (2026-04-08) **Room:** Deimantas/Diamond (3rd building) ## Abstract With more and more tools abstracting from a developer's workflows, understanding how git visualization tools help - not simply using it - is more important than ever. In this talk, we take a look at the history of git workflows, the basics of git, and the renaissance of understanding version control in a world gone mad for “vibe coding”. --- # Beyond the Static 2D Plot - Spatial Data Storytelling in 4D > Talk, 25 min — April 09, 2026 at 08:00 **Speaker:** Kęstutis Gadeikis **Track:** Data Day - Apr 9 **Day:** Data Day (2026-04-09) **Room:** Deimantas/Diamond (3rd building) ## Abstract 2D static plots are great, but they are static. Data isn't - it changes. So we turn a plot into an animation. But we don't live in planes - we live in space. And we want to send a message, not just show an animation. This leads us to the 3D animated story! In this talk I will close the gap between abstract data and its physical reality. Through step-by-step examples using (Geo)Pandas, (I)Pydeck, PyVista, Blender etc., I will turn basic charts into 4D stories with custom models added to geospace. --- # Attacking Toughest and Messiest Tech Challenges with AI > Talk, 60 min — April 10, 2026 at 08:30 **Speaker:** Egidijus Pilypas **Track:** AI Day - Apr 10 **Day:** AI Day (2026-04-10) **Room:** Deimantas/Diamond (3rd building) ## Abstract Legacy migrations, tangled integrations, undocumented business logic – every team has that category of work nobody wants to touch. This talk shares practical lessons from using AI to tackle exactly those challenges. Through the example of a real IT system migration – normally a 2–4 year project – we will show how AI can compress the timeline to weeks, reduce the pain, and even make it fun. --- # Lightning Talks > Lightning, 30 min — April 10, 2026 at 13:00 **Track:** AI Day - Apr 10 **Day:** AI Day (2026-04-10) **Room:** Great hall, (3rd building) ## Abstract TBD --- # Networking drinks and music > Talk, 60 min — April 09, 2026 at 14:30 **Track:** Keynote **Day:** Data Day (2026-04-09) **Room:** Inovation hall (4th building) ## Abstract Networking --- # Cloud Data Solutions Are Overrated: Building a Pan-European Business Database for Lunch Money > Talk, 25 min — April 09, 2026 at 12:00 **Speaker:** Antanas Baltrušaitis **Track:** Data Day - Apr 9 **Day:** Data Day (2026-04-09) **Room:** Great hall, (3rd building) ## Abstract We are told that modern data engineering requires expensive cloud warehouses and enterprise SaaS. This talk challenges that narrative. I will show how I built scoris.eu - aggregating business data from hundreds of sources across Lithuania, Latvia, Estonia, Finland, and the UK - as a solo developer. Using a purely open-source Python stack (dlt, dbt, Prefect) on cheap infrastructure, I will demonstrate that with the right architecture, you can integrate data at scale without burning cash on the cloud. --- # Measuring Experiments in LLMs: A/B Tests and Automated Testing > Talk, 25 min — April 10, 2026 at 08:00 **Speaker:** Özge Çinko **Speaker:** Kader Miyanyedi **Track:** AI Day - Apr 10 **Day:** AI Day (2026-04-10) **Room:** Krantas/Shore 213 (3rd building) ## Abstract Even small changes in LLMs can impact output quality, safety, and user experience. In this talk, we’ll show how to log experiments with Langfuse, automate tests with Pytest, and enrich them using Hypothesis-generated random data scenarios. Participants will learn how to use code, tests, and data-driven A/B tests to improve LLM development. --- # Beyond the Prompt: Building Research Agents in Python > Talk, 25 min — April 10, 2026 at 11:00 **Speaker:** Simona Skiotytė **Track:** AI Day - Apr 10 **Day:** AI Day (2026-04-10) **Room:** Great hall, (3rd building) ## Abstract LLMs can answer questions, but can they conduct research? Real research requires planning, data gathering, synthesis, and refinement. This talk explores Python patterns for orchestrating multi-step workflow to create autonomous research agents. We'll deconstruct the agentic architecture, from DAG-based planning to reflection loops, and show how to implement these concepts using practical Python patterns. --- # Lightning Talks > Lightning, 30 min — April 08, 2026 at 13:00 **Track:** Python Day - Apr 8 **Day:** Python Day (2026-04-08) **Room:** Great hall, (3rd building) ## Abstract TBD --- # Technical Debt: When to Pay It Down vs. When to Just Live With It > Talk, 60 min — April 09, 2026 at 06:30 **Speaker:** Tomas Peluritis **Track:** Keynote **Day:** Data Day (2026-04-09) **Room:** Great hall, (3rd building) ## Abstract Every team has code that makes them cringe. Legacy pipelines nobody dares touch, "temporary" tables that became the source of truth, and SQL queries that outlived three team leads. We call it technical debt, and the instinct is always the same: fix it. But should we? After migrating from Redshift to Snowflake, learning PIG just to rewrite a pipeline deprecated months later, and surviving Airflow OOM kills, I have opinions. And maybe a framework slightly better than "it depends." --- # LLM Agent Patterns — A Python Developer's Vocabulary > Talk, 25 min — April 08, 2026 at 11:00 **Speaker:** Aidis Stukas **Track:** Python Day - Apr 8 **Day:** Python Day (2026-04-08) **Room:** Deimantas/Diamond (3rd building) ## Abstract Every agent framework (even Claude Code) is built from the same 26 patterns — loops, memory, tools, delegation, self-correction. This talk strips them down to ≤10 lines of Python each, building from a single LLM call to autonomous coding agents. No frameworks, no magic — just the patterns and the code behind them. --- # It’s Just Code: Library Dismantling 101 > Talk, 25 min — April 08, 2026 at 11:00 **Speaker:** Ekaterina Korolkoviene **Track:** Python Day - Apr 8 **Day:** Python Day (2026-04-08) **Room:** Great hall, (3rd building) ## Abstract At some point, every Python developer hits a library that no longer fits. The docs end, the abstraction leaks, and you’re stuck between “best practices” and shipping. This talk starts with a mistake: modifying a library’s source code and proudly posting about it. It worked - and it taught me a better way. This isn’t a tool talk. It’s about mindset. Libraries aren’t sacred. They’re code. Code you can read, understand, and extend. And learning to look inside is a skill, not a sin. --- # Software Development Now Costs Less Than Minimum Wage > Talk, 40 min — April 10, 2026 at 13:30 **Speaker:** Geoffrey Huntley **Track:** AI Day - Apr 10 **Day:** AI Day (2026-04-10) **Room:** Great hall, (3rd building) ## Abstract The cost of software development has fallen to $10.42 an hour—less than minimum wage. A burger flipper at Macca's earns more. What does it mean to be a software developer when everyone in the world can develop software? Tools like Cursor have commoditised the knowledge and skill of software development, enabling non-developers to build and ship. --- # Data versioning > Workshop, 55 min — April 09, 2026 at 11:00 **Speaker:** Federico Marchesi **Track:** Data Day - Apr 9 **Day:** Data Day (2026-04-09) **Room:** Inovation hall (4th building) ## Abstract One of the core fundamental pieces of technology every software-related tech stack is heavily dependent on is Git. The ability to version code and control the flow of development is the only common focus for every software project. We take for granted that everyone in the working industry can indeed properly version code. In this talk, we’ll explore the meaning of data versioning and how we could borrow methodologies from the software engineering field to better manage our data. --- # Python Day Intro > Talk, 25 min — April 08, 2026 at 06:00 **Day:** Python Day (2026-04-08) **Room:** Great hall, (3rd building) ## Abstract TBD --- # Vibe reverse engineering of old games and new hardware > Talk, 25 min — April 10, 2026 at 09:00 **Speaker:** Piotr Migdał **Track:** AI Day - Apr 10 **Day:** AI Day (2026-04-10) **Room:** Great hall, (3rd building) ## Abstract Reverse engineering binaries once required deep expertise. Today, AI models like Opus 4.6, GPT-5.3-Codex, and Gemini 3.1 Pro change the rules. Watch how pairing AI with the NSA's Ghidra decompiler or simple hex tools like xxd makes binary hacking accessible. We will dive into practical projects: hacking infinite lives into Atari’s River Ride, porting the legacy game Chromatron, decoding LED backpack protocols, and hunting for backdoors. Let me show how to add reverse engineering to your everyday skills. --- # Data Day Intro > Talk, 25 min — April 09, 2026 at 06:00 **Day:** Data Day (2026-04-09) **Room:** Great hall, (3rd building) ## Abstract TBD --- # Python, rust and arrow for data processing > Talk, 25 min — April 09, 2026 at 09:00 **Speaker:** Paulius Venclovas **Track:** Data Day - Apr 9 **Day:** Data Day (2026-04-09) **Room:** Deimantas/Diamond (3rd building) ## Abstract Python struggles with heavy data loads. Rust offers speed, and PyO3 makes bridging the two seamless. This talk shows how to build a shared Rust core to avoid code duplication. I will also cover using Apache Arrow for zero-copy data sharing and removing serialization costs entirely. Discover how this stack enables high-performance data processing in Python and Pyspark --- # XAI - Explainable AI tools and techniques > Talk, 30 min — April 10, 2026 at 09:00 **Speaker:** Viraj Sharma **Track:** AI Day - Apr 10 **Day:** AI Day (2026-04-10) **Room:** Krantas/Shore 213 (3rd building) ## Abstract In this talk, I propose to discuss the problem of building explainable AI with the two approaches - causal vs correlational. I will talk about what mech interp in LLMs. As a way to understand how models answer questions by looking inside them and checking which neurons activate when. I will discuss Anthropic's open sourced a python module - circuit-tracer, the Neuronpedia portal , will also talk about my own work with "activation cube" data structure (this is not a standard - I came up with it) --- # Infrastructure as Python: Pulumi for Cloud Deployments > Talk, 25 min — April 08, 2026 at 11:30 **Speaker:** Eric Thanenthiran **Track:** Python Day - Apr 8 **Day:** Python Day (2026-04-08) **Room:** Krantas/Shore 213 (3rd building) ## Abstract You use Python for your code why not use it to deploy code to the cloud too? Pulumi, an open source Infrastructure as Code library allows you to configure your cloud infrastructure using Python. In this session we'll deploy a data processing pipeline using Pulumi in GCP and talk through core concepts and fundamentals. Using this example we'll talk through practical best practice ensuring reliable and maintainable infrastructure that scales with your projects. --- # Creative Data Storytelling with Python > Talk, 25 min — April 09, 2026 at 09:00 **Speaker:** Purva **Track:** Data Day - Apr 9 **Day:** Data Day (2026-04-09) **Room:** Krantas/Shore 213 (3rd building) ## Abstract Python enables data professionals to move beyond analysis and transform information into clear, compelling stories. With various libraries, Python supports insightful exploration, expressive visualizations, and interactive elements that enhance communication. This talk highlights practical techniques for turning patterns, trends, and insights into engaging narratives, making data more understandable, impactful, and actionable. --- # Lightning Talks > Lightning, 30 min — April 09, 2026 at 13:00 **Track:** Data Day - Apr 9 **Day:** Data Day (2026-04-09) **Room:** Great hall, (3rd building) ## Abstract TBD --- # AI and Agency: As Developers, We Decide The Future > Talk, 45 min — April 10, 2026 at 12:00 **Speaker:** Tadas Korris **Track:** AI Day - Apr 10 **Day:** AI Day (2026-04-10) **Room:** Great hall, (3rd building) ## Abstract AI systems are not neutral; they encode values that are opaque and separate from people. As developers, we are making decisions that shape who has power, who is surveilled, who is replaced, and who gets a voice, often without intending to. This talk frames AI ethics as a software engineering problem, not just a philosophical one. We’ll examine how everyday technical choices can unintentionally reinforce authoritarian tendencies around disinformation, manipulation, and harmful automated decision making. --- # Master the Art of Schema Dissection: Operation Data Engineer > Talk, 25 min — April 09, 2026 at 11:00 **Speaker:** Antonino (Nino) Cangialosi **Track:** Data Day - Apr 9 **Day:** Data Day (2026-04-09) **Room:** Krantas/Shore 213 (3rd building) ## Abstract Have you ever faced an enormous, wide table? Sometimes you need to cope with it because it's faster in this form, and that's what your stakeholders need. Anyway, it’s hiding entities, metrics, and time semantics. Learn how the dissection framework reveals schema structure and turns risky rewrites into surgical precision. --- # From Data Collection to Partner Delivery: Shipping a Paraphrasing Skill on Small Language Models > Talk, 25 min — April 10, 2026 at 11:30 **Speaker:** Marat Saidov **Track:** AI Day - Apr 10 **Day:** AI Day (2026-04-10) **Room:** Deimantas/Diamond (3rd building) ## Abstract I'll discuss building capabilities on top of on-device language models, with Rewrite as a case study – a publicly available paraphrasing skill that is widely used across Microsoft's products. I'll cover comprehensive data collection strategies, carefully designed adapters training and evaluation. I'll discuss the engineering challenges we faced: achieving target latency while maintaining quality, hardening the system against edge cases, and how to deliver the technology to partners and the lessons learnt. --- # An Art of Privacy > Talk, 25 min — April 08, 2026 at 11:30 **Speaker:** Denis Filiakin **Track:** Python Day - Apr 8 **Day:** Python Day (2026-04-08) **Room:** Deimantas/Diamond (3rd building) ## Abstract This talk offers a brief overview of cryptographic algorithms, going through their evolution from antiquity to our days. We will explore the origins of encryption, from early ciphers to the beginnings of computer-based cryptography, and then focus on key modern algorithms such as RSA, AES, and IES. --- # Airflow Lessons They Don't Put in the Docs > Talk, 25 min — April 09, 2026 at 11:30 **Speaker:** Tomas Peluritis **Track:** Data Day - Apr 9 **Day:** Data Day (2026-04-09) **Room:** Deimantas/Diamond (3rd building) ## Abstract Airflow basics are well documented. Production Airflow is not. This talk covers the patterns, costs, and migration pitfalls that only show up after you've deployed: dynamic DAGs that scale, sensors that don't waste resources, CloudWatch bills that surprise you, and MWAA version upgrades that break in ways the changelog didn't mention. Practical lessons for teams running Airflow beyond the tutorial stage. --- # Quantum Machine Learning with Qiskit > Talk, 25 min — April 09, 2026 at 12:00 **Speaker:** Jonas Adomaitis **Track:** Data Day - Apr 9 **Day:** Data Day (2026-04-09) **Room:** Krantas/Shore 213 (3rd building) ## Abstract Unlock the power of Quantum Machine Learning (QML) with Python and Qiskit. You will explore the distinctions between classical and quantum machine learning and gain an understanding of data encoding, quantum kernels, and the training process of a Variational Quantum Classifier. You’ll also discover how Qiskit Functions integrate quantum into application workflows to solve complex challenges. Finally, you’ll explore IBM case studies showing the transition to practical "quantum utility." --- # How I mapped 10 000 illegal Airbnbs with Python > Talk, 25 min — April 09, 2026 at 08:00 **Speaker:** Juan Luis Cano Rodríguez **Track:** Data Day - Apr 9 **Day:** Data Day (2026-04-09) **Room:** Great hall, (3rd building) ## Abstract In the spring of 2024, a cry erupted across Spain: "The Canary Islands have reached their limit." Soon, massive demonstrations followed in other regions facing similar tensions: "Mallorca is not for sale," "Enough of Ibiza," "Cantabria will defend itself." Meanwhile, in Madrid, the capital, a similar discontent had been brewing for years. Could open data be used to understand the phenomenon, and do something about it? --- # Designing Python APIs for Data You Don’t Control > Talk, 25 min — April 09, 2026 at 09:00 **Speaker:** Saurav Jain **Track:** Data Day - Apr 9 **Day:** Data Day (2026-04-09) **Room:** Great hall, (3rd building) ## Abstract The web isn’t an API, but Python developers often treat it like one. This talk explores how to design Python interfaces for unstable data sources, focusing on schema evolution, defensive parsing, and protecting downstream users. --- # From experiments to systems: DS lessons for better software engineering > Talk, 25 min — April 08, 2026 at 09:00 **Speaker:** Jaunė Malūkaitė **Track:** Python Day - Apr 8 **Day:** Python Day (2026-04-08) **Room:** Krantas/Shore 213 (3rd building) ## Abstract Transitioning from data science to software engineering doesn’t mean starting over, it means translating the scientific method into systems work. In this talk I would share the DS habits that most improved my engineering. I would also cover the gaps that surprised me and the concrete techniques that helped me close them. The talk would include useful tools related to hpc, multi-agent systems that help improve the code and runtime. --- # Lessons Learned using FastAPI in the Wild > Talk, 25 min — April 08, 2026 at 08:30 **Speaker:** Graham Lyons **Track:** Python Day - Apr 8 **Day:** Python Day (2026-04-08) **Room:** Deimantas/Diamond (3rd building) ## Abstract This talk is for anyone curious about what it’s like to run FastAPI in production. An asynchronous web framework with automatically generated documentation and dependency injection, FastAPI has made huge gains in popularity and overtook Flask in the 2025 Stack Overflow Annual Developer Survey. FastAPI’s features are impressive and picking it up is easy, but beyond that what is it really like to run in production? What joys and pitfalls await those deploying the most popular Python web framework? --- # Context Engineering with DeepAgents: Write, Select, Compress, Isolate > Talk, 25 min — April 10, 2026 at 08:00 **Speaker:** Antanas Daujotis **Track:** AI Day - Apr 10 **Day:** AI Day (2026-04-10) **Room:** Deimantas/Diamond (3rd building) ## Abstract Context Engineering is the new prompt engineering. As agentic workflows grow, just appending messages to a list causes context poisoning and latency spikes. In this talk, we'll look at a better architecture using the \`deepagents\` library. We'll explore the four pillars of context engineering: Write, Select, Compress, and Isolate. You'll learn how to treat context as a finite resource and build autonomous agents that can solve complex tasks without crashing your context window. --- # Modern Python monorepo for Apache Airflow > Talk, 25 min — April 08, 2026 at 08:30 **Speaker:** Jarek Potiuk **Track:** Python Day - Apr 8 **Day:** Python Day (2026-04-08) **Room:** Great hall, (3rd building) ## Abstract Explore how Apache Airflow modernized its massive monorepo by transitioning from complex custom scripts to official Python packaging standards and tools like uv. This session breaks down the management of 120+ distributions, the implementation of modular pre-commit hooks, and a novel approach to "static" shared libraries within a single repository. Join us to see a real-world blueprint for large-scale modularity as we advocate for the formalization of a Python workspace standard. --- # The paradox of itertools.tee > Talk, 25 min — April 08, 2026 at 08:00 **Speaker:** Rodrigo Girão Serrão **Track:** Python Day - Apr 8 **Day:** Python Day (2026-04-08) **Room:** Deimantas/Diamond (3rd building) ## Abstract The module \`itertools\` provides 20 tools. There's 19 iterables and then there's \`tee\`... But what does \`tee\` do and why is it the only thing in the module \`itertools\` that's not an iterable? In this talk you will understand what \`tee\` does and when to use it, but most importantly, you will understand the paradox behind \`tee\`... See, the thing is that \`tee\` seems to go against the laws of iterators... --- # Multi-Model LLM Orchestration in Python: A Case Study in Research Automation > Talk, 25 min — April 09, 2026 at 08:30 **Speaker:** Mauro Pelucchi **Track:** Data Day - Apr 9 **Day:** Data Day (2026-04-09) **Room:** Deimantas/Diamond (3rd building) ## Abstract How do you turn thousands of PDFs into actionable insights? This talk shows how we built a Python-based AI assistant using LLMs and RAG to automate literature reviews: covering architecture, trade-offs, and real lessons from production use in policy research. --- # Serializing and displaying trees > Talk, 25 min — April 08, 2026 at 08:00 **Speaker:** Petras Zdanavičius **Track:** Python Day - Apr 8 **Day:** Python Day (2026-04-08) **Room:** Great hall, (3rd building) ## Abstract We at One Codex work in the microbiology field. This means that we deal with massive taxonomy trees all the time. It is impossible to cover everything, so in this talk, I am going to focus on the best data structure to: - store tree data - serialize it - display it on the frontend --- # Stop Using ORM > Talk, 25 min — April 08, 2026 at 11:30 **Speaker:** Roman Zaiev **Track:** Python Day - Apr 8 **Day:** Python Day (2026-04-08) **Room:** Great hall, (3rd building) ## Abstract SQL is an excellent DSL for relational data, but ORMs hide it behind their own leaky abstractions. This talk shows how to build a cleaner persistence layer and use Postgres to its fullest, without the overhead you never asked for. --- # Beyond SHAP: Diagnosing Vector Embeddings with Visual Explainable AI > Talk, 25 min — April 09, 2026 at 11:00 **Speaker:** Valdas Druskinis **Track:** Data Day - Apr 9 **Day:** Data Day (2026-04-09) **Room:** Deimantas/Diamond (3rd building) ## Abstract When your embedding-based classification model fails, should you collect more data or try a different approach? This talk shares a practical XAI workflow using UMAP visualization and prototype analysis to uncover systematic failures. We will explore how to use these tools to identify semantic overlaps and make evidence-based decisions when debugging high-dimensional similarity systems. --- # What You're Leaving on the Table > Talk, 60 min — April 08, 2026 at 13:30 **Speaker:** Mark Smith **Track:** Keynote **Day:** Python Day (2026-04-08) **Room:** Great hall, (3rd building) ## Abstract Developers are excited about AI, but not about the proven practices that would make them faster today. I'll explore the efficiency gaps hiding in plain sight – from debugging habits to testing strategies to software design – and argue that these fundamentals become even more essential when AI enters the picture. --- # AI-Assisted Development in Practice: Chatbot + Agentic Testing from Scratch > Workshop, 55 min — April 10, 2026 at 08:00 **Speaker:** Alex Marmuzevich **Track:** AI Day - Apr 10 **Day:** AI Day (2026-04-10) **Room:** Inovation hall (4th building) ## Abstract GenAI-based projects are easy to prototype, but hard to test. In this hands-on workshop, we will build a simple AI chatbot from scratch and, in parallel, create an AI agent that tests it during development. The testing agent will generate user scenarios, detect failures such as prompt issues, incorrect tool usage, etc., and then suggest concrete next steps for improvement. The core theme of the workshop is building AI systems with the help of AI itself, while keeping an engineering-driven approach to design --- # Death by a Thousand Prompts: Can Our Disclosure Standards Survive AI Slop? > Talk, 25 min — April 10, 2026 at 11:00 **Speaker:** Jarek Potiuk **Track:** AI Day - Apr 10 **Day:** AI Day (2026-04-10) **Room:** Krantas/Shore 213 (3rd building) ## Abstract AI-generated "slop" is overwhelming vulnerability triage and burning out maintainers. This session focuses on building a unified framework to identify and "black-hole" synthetic noise at scale. We will discuss practical, cross-platform strategies to automate the rejection of low-signal reports and protect engineers from the unsustainable volume of AI-augmented disclosures. --- # Python Power Tools: Hands-On from Decorators to Context Managers > Workshop, 55 min — April 08, 2026 at 11:00 **Speaker:** Neeraj Pandey **Track:** Python Day - Apr 8 **Day:** Python Day (2026-04-08) **Room:** Inovation hall (4th building) ## Abstract Let’s make your functions smarter with decorators, simplify operations using lambdas, save memory with generators, and handle resources like a pro with context managers. We’ll mix clear explanations with hands-on practice - so you can write code that’s cleaner, faster, and feels Pythonic. --- # Your Python has a public roadmap. Most engineers never read it. > Talk, 60 min — April 08, 2026 at 06:30 **Speaker:** Mia Bajić **Track:** Keynote **Day:** Python Day (2026-04-08) **Room:** Great hall, (3rd building) ## Abstract Python's technical roadmap is public, yet most engineers only find out about language changes when something breaks in CI. Python is one of the few languages at this scale governed entirely by its community, which means every decision gets made in the open, and that transparency is a real competitive advantage. This talk is about learning to use it and understanding why the community behind it is what makes that possible in the first place. --- # What It Means to Be a CTO in an AI Startup Today > Talk, 25 min — April 10, 2026 at 08:30 **Speaker:** Fabien Vauchelles **Track:** AI Day - Apr 10 **Day:** AI Day (2026-04-10) **Room:** Great hall, (3rd building) ## Abstract \*\*I haven't written a single line of code in over a year.\*\* As CTO of an AI startup, I've fully embraced vibe coding: orchestrating AI to generate production-ready code. 🔍 \*\*Highlights\*\* 1. \*\*The paradigm shift:\*\* from autocompletion to full project generation 2. \*\*My 3-step workflow:\*\* voice prompts, deep research, code generation 3. \*\*The judgment trap:\*\* why expertise matters more than ever You'll leave with practical techniques to ship 10x faster! --- # The year of [packaging your Python app for] the Linux Desktop > Workshop, 90 min — April 08, 2026 at 08:00 **Speaker:** Juan Luis Cano Rodríguez **Track:** Python Day - Apr 8 **Day:** Python Day (2026-04-08) **Room:** Inovation hall (4th building) ## Abstract In the last few years, we’ve seen amazing progress around Python packaging for library code. Packaging applications usually requires more work, but thanks to recent developments it’s getting easier than ever. Will this be the year of packaging your Python app for the Linux Desktop? --- # Engineering Complex AI solutions: Observability and Testing of multi-Agent Solutions > Talk, 15 min — April 10, 2026 at 11:30 **Speaker:** Dmitri **Track:** AI Day - Apr 10 **Day:** AI Day (2026-04-10) **Room:** Great hall, (3rd building) ## Abstract As AI agents evolve from simple chatbots to complex multi-agent systems utilizing Model Context Protocol (MCP), manual validation becomes impossible. During this talk, I will demonstrate the process of architecting a quality assurance loop for these solutions. No theoretical fluff: I will focus on the practical analysis of automated pipeline results, interpreting Langfuse reports for cost and performance, and ensuring reliability from an AI Architect/System Engineer perspective. --- # Streamline Python Package Release with uv, paws and trivia > Talk, 25 min — April 08, 2026 at 12:00 **Speaker:** Ąžuolas Krušna **Track:** Python Day - Apr 8 **Day:** Python Day (2026-04-08) **Room:** Krantas/Shore 213 (3rd building) ## Abstract Python packaging can be mysterious. This talk demonstrates how to streamline your Python package release process using modern tools and human-centric automation. We'll showcase uv for elegant, fast dependency management and CI/CD. Discover innovative GitHub Actions workflows integrating "paws-itive" feedback and trivia to boost motivation and engagement in PRs. We'll achieve universal distribution across PyPI, Homebrew, and Scoop. Ship high-quality Python packages in an efficient and fun way. --- # Python Tooling at Mozilla > Talk, 25 min — April 08, 2026 at 12:00 **Speaker:** Tadas Korris **Track:** Python Day - Apr 8 **Day:** Python Day (2026-04-08) **Room:** Great hall, (3rd building) ## Abstract The tools and workflows we use as developers are often as important as the code we write. The beauty of the Python ecosystem is that there are many options to the types of linters, formatters, type checkers, testing frameworks, and security scanners we can choose. However, too many options can paralyze decision making and often we use sub-optimal tools just because we've used them before. Learn some lessons from the tooling we use for maintaining, testing, and deploying our Python code at Mozilla. --- # Dataset Updates Without Losing Your Mind > Talk, 25 min — April 09, 2026 at 12:00 **Speaker:** Oleksii Liashuk **Track:** Data Day - Apr 9 **Day:** Data Day (2026-04-09) **Room:** Deimantas/Diamond (3rd building) ## Abstract Many teams work with datasets that evolve over time. What starts as simple setup, quickly turns into chaos once updates become regular. In this talk, I share a practical workflow for managing dataset updates by splitting the process into clear stages, each represented by a Python script. This approach was used in production for two years on image datasets from 2,000 to 200,000 samples and helps small teams reduce cognitive load and keep dataset and model updates predictable. --- # Beyond Basic RAG: Boosting Accuracy with Hybrid Search and Fusion Algorithms. > Talk, 25 min — April 10, 2026 at 09:00 **Speaker:** Piti Champeethong **Track:** AI Day - Apr 10 **Day:** AI Day (2026-04-10) **Room:** Deimantas/Diamond (3rd building) ## Abstract Retrieval-Augmented Generation (RAG) often produces incorrect results when relying solely on vector-based similarity. While vector search is strong, it fails on exact keywords, acronyms, and domain-specific terms. This talk shows how to build high-accuracy RAG pipelines with Hybrid Search and Re-ranking using LangChain, combining vector and full-text retrieval and applying cross-encoder scoring to deliver more relevant context and reduce hallucinations. --- # And now for something completely different > Talk, 25 min — April 09, 2026 at 08:30 **Speaker:** Rodrigo Girão Serrão **Track:** Data Day - Apr 9 **Day:** Data Day (2026-04-09) **Room:** Krantas/Shore 213 (3rd building) ## Abstract In this talk we’ll go over two quintessential features of Python programming (generators and duck typing) and you’ll learn how to use them effectively. We’ll also look at branchless conditionals and understand how this unusual idea can shape the way you think about coding. In the end, we’ll put the three together to write a powerful Python idiom and conclude I have terrible taste! --- # Behind Every Instant Loan Is Data Science: How Python Scorecards Decide Credit Risk > Talk, 25 min — April 09, 2026 at 11:30 **Speaker:** Zafarzhon Irismetov **Track:** Data Day - Apr 9 **Day:** Data Day (2026-04-09) **Room:** Krantas/Shore 213 (3rd building) ## Abstract Modern digital lending demands instant decisions, and behind those decisions is a Data Science workflow powered by scorecard. This talk explains how scorecards calculates credit risk in a transparent and scalable way, from feature engineering to production deployment. Using real examples from our company, models that enable fast, reliable loan approvals. --- ## Static Pages # About PyCon Lithuania **The biggest Python and PyData event in the Baltic and Nordic regions** PyCon Lithuania is a community-driven conference that brings together Python enthusiasts, developers, data scientists, and technology leaders from across the Baltic and Nordic regions. With over 600 attendees and 50+ sessions, we provide a platform for learning, networking, and sharing knowledge about Python applications in data, web development, and other domains. ## Our Mission To foster a vibrant Python community in the Baltic and Nordic regions by providing a platform for knowledge sharing, networking, and collaboration. ## Community We believe in building an inclusive community where everyone, regardless of their background or experience level, feels welcome and valued. ## Volunteer-Run PyCon Lithuania is organized entirely by volunteers who are passionate about Python and dedicated to creating an amazing conference experience. ## What to Expect - **Technical Talks** — Learn from industry experts about the latest developments in Python, data science, web development, and more - **Workshops** — Hands-on sessions to develop new skills and deepen your understanding - **Networking** — Connect with fellow Python enthusiasts, potential employers, and mentors - **Community** — Be part of a welcoming and inclusive environment that celebrates diversity ## Get Involved There are many ways to get involved with PyCon Lithuania. Whether you're interested in speaking, volunteering, or sponsoring, contact [info@pycon.lt](mailto:info@pycon.lt) to learn more. --- # Code of Conduct PyCon LT is a community conference intended for networking and collaboration in the developer community. We want everyone at the conference to have a great time and be able to learn and connect with others in the Python community. To make sure that happens, we ask that everyone be respectful and considerate of others. This means being friendly to each other, whether you're talking to another attendee, speaker, or volunteer. Let's all work together to make this a great event for everyone! ## Rules - Respectful and professional behavior is expected at all times. - Harassment, discrimination, or prejudice of any kind will not be tolerated. - Attendees must comply with all venue rules and regulations. - All attendees must respect the privacy and personal space of others. - Attendees must not take any action that would put themselves or others at risk of harm. - Attendees must not damage or steal conference property or equipment. - Attendees should be mindful of noise levels and be respectful of other attendees trying to focus or sleep. - Attendees must not record or photograph other attendees without their express consent. - Attendees are expected to be punctual and respectful of other attendees' time during scheduled events and activities. - Attendees should be respectful of speakers and presenters, and refrain from interrupting or disrupting their presentations. ## Contact Information If you believe that someone is violating the code of conduct during a PyCon Lithuania, or have any other concerns, please contact a member of the event staff immediately. [info@pycon.lt](mailto:info@pycon.lt) --- # Volunteer with Us Help make PyCon Lithuania an amazing experience for everyone! PyCon Lithuania is organized entirely by volunteers who are passionate about Python and the community. We're always looking for enthusiastic individuals to join our team and help make the conference a success! ## Why Volunteer? - Meet amazing people from the Python community - Get behind-the-scenes conference experience - Give back to the community - Receive a volunteer t-shirt and perks - Free conference access ## Volunteer Roles - Registration desk support - Room monitors and A/V assistance - Speaker liaison - Setup and teardown crew - Social media and content creation ## Time Commitment Most volunteer shifts are 2-3 hours long. We try to schedule shifts so you can still attend talks and participate in the conference. You can choose shifts that work best for your schedule. ## Volunteer Benefits - Free conference ticket - Exclusive volunteer t-shirt - Meals and snacks during shifts - Volunteer appreciation event - Certificate of volunteering ## How to Apply Interested in volunteering? We'd love to have you on the team! Send us an email at [info@pycon.lt](mailto:info@pycon.lt) with: - Your name and contact information - Why you want to volunteer - Any relevant skills or experience - Your availability during the conference dates --- # Contact Us Have questions about PyCon Lithuania? We'd love to hear from you! ## Email Send us an email and we'll get back to you as soon as possible. [info@pycon.lt](mailto:info@pycon.lt) ## General Inquiries For general questions about the conference, including: - Conference schedule and talks - Ticket sales and registration - Venue information - Sponsorship opportunities ## Location PyCon Lithuania takes place in Vilnius, Lithuania. Event venue details are announced closer to each conference date. ## Social Media Follow us on social media for the latest updates: - [LinkedIn](https://www.linkedin.com/company/pycon-lithuania/) - [Facebook](https://www.facebook.com/pyconlt) - [YouTube](https://www.youtube.com/@pyconlt) - [X / Twitter](https://x.com/pyconlt) --- # Terms of Service ## 1. Acceptance of Terms By registering for and attending PyCon Lithuania, you agree to comply with and be bound by these Terms of Service. ## 2. Registration and Tickets All ticket sales are final. Refunds may be issued at the discretion of the organizers under exceptional circumstances. Tickets are non-transferable without prior approval from the organizers. ## 3. Event Conduct All attendees must adhere to our [Code of Conduct](/code-of-conduct). Violation of the Code of Conduct may result in removal from the event without refund. ## 4. Content and Materials Presentations, talks, and materials shared at PyCon Lithuania may be recorded and published. By presenting or attending, you consent to such recording and publication. ## 5. Liability PyCon Lithuania organizers are not liable for any loss, damage, or injury sustained during the event. Attendees participate at their own risk. ## 6. Changes to Terms We reserve the right to modify these terms at any time. Continued participation in PyCon Lithuania constitutes acceptance of any changes. --- For inquiries regarding these terms, reach out to [info@pycon.lt](mailto:info@pycon.lt). --- # Privacy Policy ## 1. Information We Collect When registering for PyCon Lithuania, we collect personal details including name, email address, and payment information, along with data regarding event participation. ## 2. How We Use Your Information We use collected information to: - Process registrations and ticket purchases - Communicate event-related updates - Deliver event materials and information - Enhance future events - Meet legal requirements ## 3. Information Sharing We do not sell your personal information. We may share data with event sponsors (with your consent), service providers assisting with operations, and law enforcement when legally obligated. ## 4. Data Security We implement security measures to protect personal information, though internet transmission cannot guarantee complete security. ## 5. Your Rights You may: - Access your personal information - Correct inaccurate details - Request information deletion - Opt out of marketing communications ## 6. Cookies Our website uses cookies to enhance user experience. You can control cookies through your browser settings. ## 7. Changes to This Policy We may update this policy periodically and will notify you of significant changes. --- Questions? Contact [info@pycon.lt](mailto:info@pycon.lt). --- # AI & Agents PyCon Lithuania is built for people, but we also make the site — and parts of the organizer backend — usable by AI assistants and agents. ## For AI crawlers and agents If you're an AI agent or crawler visiting this site, start here: - [/llms.txt](/llms.txt) — a curated index of what's on this site. - [/llms-full.txt](/llms-full.txt) — every confirmed talk abstract and speaker bio for the current and previous edition, in one file. - [/agents.md](/agents.md) — the rules and capabilities for agents interacting with this site. - Any page on this site has a clean markdown alternate — just append `.md` to its URL (e.g. `/2026/schedule.md`). Ticket purchase requires a human — there is no agentic checkout endpoint. Please respect `/robots.txt` and don't scrape or infer attendee personal data. ## For organizers: connect an AI assistant PyCon LT exposes an MCP ([Model Context Protocol](https://modelcontextprotocol.io)) connector so an AI assistant — Claude.ai, a ChatGPT connector, or a local `mcp-remote` setup — can help run the conference on your behalf: reviewing CFP submissions, checking ticket sales, drafting blog posts, managing sponsors and orders, tracking financial aid and volunteers, and more. To connect: 1. In Claude.ai (Settings → Connectors) or ChatGPT (Connectors), add a custom connector pointing at `https://pycon.lt`. 2. Sign in with your PyCon LT admin Google account when prompted. 3. Approve the requested access. This requires an admin account — it will not work for a regular attendee or speaker login. The assistant only sees and does what your admin account is already allowed to. ---