In the last few years, one of the leading new areas of development in JetBrains has been AI assistance. It started with simple access to an external large language model within IntelliJ IDEA—but we didn’t stop there. Today, JetBrains offers a wide range of new features and plugins that can make software developers work more quickly and productively. During this talk, we will go through the most important of them – AI Assistant, local and cloud completion, connecting to local LLMs, and more. We will discuss how these tools can boost your productivity and improve your coding experience. We will also delve into… sorry, I mean, we will talk about JetBrains Junie, AI agents in general, and the future of AI tooling. The talk will consist of animated infographics and live coding examples.

Overview of .NET 10 focusing on cloud-native and intelligent app development, productivity enhancements, streamlined deployments, and accelerated AI integration, highlighting features from the release.

Learn best practices and real-world examples for combining dbt, SDLC workflows, AI, and BI to improve analytical accuracy and deliver reliable, conversational insights. This session shows how aligning these tools and methods strengthens data lineage, automates documentation, and empowers true self-service.

Vector search is a fundamental technology accompanying modern AI solutions such as agents. In this session, we’ll dive into how vector search works and how it solves real-world use cases for AWS customers. We’ll also discuss the challenges of implementing vector search at scale, and the mechanisms that OpenSearch provides to handle them.

Arno will explore the evolution of search technology in the age of AI. From large language models and “LLM Wars” to enterprise-scale challenges in observability and security, he’ll share practical insights on how Elastic customers are experimenting with AI, what works today, and why the answer often depends on context.

Discussion on using Gen AI to accelerate developer workflows in Logic Apps, including prompts to create test data, automated creation of maps, unit tests, custom code, and chat modes to ease development.

How are you taking advantage of Gen AI to make your developer life easier using Logic Apps? From prompts to create test data, to automated creation of maps, unit tests or custom code and anything in between.

Explores how to use Logic Apps features to implement intelligent application scenarios, including Agent Loops, Logic Apps exposed as MCP tools, and enhancing intelligent application knowledge in real time.

Tell us how you have been using Logic Apps features to implement intelligent application scenarios—from Agent Loops, to Logic Apps exposed as MCP tools, to improving your intelligent application knowledge in real time.

Discussion on using Logic Apps features to implement intelligent application scenarios, including Agent Loops, Logic Apps exposed as MCP tools, and real-time knowledge improvements.

Live demo and deep dive into GitMesh, an AI-powered project management platform for open source repositories. Topics include: core vision and architecture, AI-driven issue triage and contributor matching, origin story and rationale, benefits for the open source community, roadmap, beta access program, and opportunities for LFDT community involvement.

A live demonstration of GitMesh's AI-powered triage of issues and automatic contributor matching based on skills.

The origin story behind GitMesh and the motivation to build an AI-powered project management platform for open source.

Overview of GitMesh's core vision and architecture, including how it enables AI-powered project management for open source repositories.

AI Agents and using them for AI-assisted development can be powerful, save a lot of time, and shrink the time-to-value horizons. They even allow you to automate things that you would have never considered before. However, there are gotchas: code quality, architecture, code review, testing, and actual customer need. These concepts become real bottlenecks in the end-to-end business & customer value delivery via software development. In this talk, you’ll learn about the nature of the problem and how to mitigate and even overcome these challenges.

AI agents are rapidly evolving, from the early efforts to simulate human cognition and social behavior, to sophisticated multi-agent systems that can act as practical collaborators in everyday work. Building on nearly 75 years of AI and NLP research, today’s AI agents can plan, reason, communicate, and even coordinate. This talk explores the growing capabilities of AI agents as both mirrors and extensions of human cognition and behavior. I will discuss advances in multi-agent frameworks that simulate social reasoning, cooperation, and emergent communication, and explore how these capabilities are being translated into workplace applications supporting brainstorming, narrative development, and research design.

AI agents are rapidly evolving, from the early efforts to simulate human cognition and social behavior, to sophisticated multi-agent systems that can act as practical collaborators in everyday work. Building on nearly 75 years of AI and NLP research, today’s AI agents can plan, reason, communicate, and even coordinate. This talk explores the growing capabilities of AI agents as both mirrors and extensions of human cognition and behavior. I will discuss advances in multi-agent frameworks that simulate social reasoning, cooperation, and emergent communication, and explore how these capabilities are being translated into workplace applications supporting brainstorming, narrative development, and research design.

Dużo się dzieje w świecie AI i sam próbuję się w tym odnaleźć — ta prezentacja to sposób na zebranie myśli. Będę mówił o 60-letnim kryzysie oprogramowania, o AGI i końcu świata (albo nie), o moich doświadczeniach jako deweloper w zespole AGI w Amazon oraz jako użytkownik AI w codziennej pracy. Pokażę prawdziwe case'y i praktyczne wnioski. Poruszę też tematy, które tech community często przemilcza: uważność, obecność i kontakt ze sobą jako core skills (nie „soft”). Dlaczego „Go slow, slow is smooth, smooth is fast" bywa ważniejsze niż „velocity". A na deser — pół-żartem, pół-serio zaproponuję nową metodologię: Extreme Craftsmanship jako odpowiedź na Extreme Slop. Bo AI daje nam wybór: masz fundamenty (techniczne + mentalne) → AI daje supermoc; nie masz → powstaje chaos. Uczę się ciągle tego nowego świata i chcę się tym podzielić — ale równie mocno chcę uczyć się od Was. Ta prezentacja ma być wymianą, nie monologiem.

Exploration of AI agents and GraphRAG in platform engineering.