Let’s be honest: in most teams, performance optimization only becomes a priority when something is already on fire. And even then, it’s usually handled by one or two people. Not because others don’t care — but because real optimization requires a lot of time, context, and expertise. At Temabit, we decided to experiment with a different approach: delegating part of the optimization work to agents. In this talk, I’ll share what came out of it: how we learned to frame optimization tasks so agents can produce useful results, how we validate their suggestions, and why optimization turned out to be much harder to delegate than writing code — but potentially far more valuable. Real cases, honest lessons, no hype. And one key question: how realistic is it to trust agents with the performance of your product?

AI development hits everyone, so hit us. Everybody wants AI agents to replace regular UIs. In this talk, I will describe the evolution of our multitool AI agent, built with Node.js on top of Google Vertex AI. I’ll dive into our journey of choosing the right models and scaling development through CI/CD, TDD, and performance monitoring. Is it even possible to achieve stable results for AI projects that can hallucinate and return various responses? Interestingly, we eventually decided to remove MCP servers and Zod schema validation—technologies often considered the "standard" for these tasks. Want to know why we moved away from them? Join my session to get these insights and ask your questions live!

AI video generation services are evolving extremely fast, effectively opening up a new way of creating video — at a moment when the standards, language, and rules of this industry are still being formed. It feels like a reinvention of cinema: there is no single “right” approach yet, but it’s already clear what prevents generation from becoming a controlled production process. I will share ideas on how existing platforms can be improved, drawing on directing experience: which director-level needs a product should account for, where modern services most often break the pipeline, and what product changes could significantly increase the quality of the final result. The focus is on a platform that works equally well for two audiences: experienced filmmakers who need control and predictability, and “native AI” creators who started their journey in video through generation and have no traditional production background. For both groups, I will outline the logic of a pipeline: "idea → generation → rough edit → export", including the minimum viable editing inside the service and professional export to Premiere or DaVinci for finalization.

Talking about something abstract is easy and fun — you can sound smart, and no one can really verify your claims because, well, it’s abstract. In a world where every other person is now an “AI visionary,” I want to speak about AI in a максимально concrete way, using my own work at GitLab as the example. It’s a perfect case. While many people describe a world of pink ponies — greenfield projects built from scratch — I want to share the hardcore brownfield reality: what actually happens when you introduce AI into a project that has existed for years. Here’s what we’ll cover: - How AI and JavaScript get along (or, more accurately, don’t) - My setup and “secret sauce” for agentic development - What I’ve achieved together with Opus (my favorite model) - How much JavaScript code I still write by hand - What prevents us from reaching the mythical 10x productivity — and what I’m doing about it My goal is simple: after this case study, everyone should walk away with a clear understanding of what they can implement in their own project to make life better — starting now.

Most people use artificial intelligence primarily as a productivity tool — to complete tasks faster and more efficiently. But can AI also help us grow faster and become better versions of ourselves? On the one hand, AI as a plan designer helps define the steps needed to achieve personal goals. AI as a reflective partner can analyze your voice journal — structuring chaotic thoughts, identifying patterns, and uncovering unexpected insights — and enable deeper reflection on articles, books, and videos. AI as a sparring partner creates a safe space to practice skills in simulations, from job interviews and difficult conversations to improving your English. AI as a tutor allows you to acquire new knowledge and skills at your own pace. On the other hand, there is a risk of the illusion of competence — how can you be sure you have truly mastered knowledge and skills with the help of AI if you are not an expert in the field? Moreover, some studies point to cognitive atrophy resulting from outsourcing thinking and relying on AI as a crutch for reasoning. So, is using AI about accelerated growth — or gradual degradation? During the talk, the speaker will present the results of a practical experiment with real cases and explore whether AI can help us become better versions of ourselves.

This talk demonstrates practical approaches to unified observability, where metrics, logs, traces, and profiles are integrated for rapid diagnostics in distributed systems. We will cover data correlation techniques using trace IDs and labels to enable instant navigation from errors to specific spans, setting up continuous profiling for preview environments, using flame charts for performance analysis, and leveraging dependency maps and service graphs to visualize architecture. Special attention is given to AI-specific aspects: applying AI assistants to automate root cause analysis and implementing AI Evals for systematic evaluation of the quality, correctness, and reliability of AI systems.

This session explores the evolution from simple LLM chains to robust cognitive architectures, focusing on deploying stateful agents within your own perimeter (On-Premise). We will compare modern orchestration frameworks, contrasting Google ADK (Agent Development Kit) for structured, model-agnostic agent design against LangGraph for granular state control and CrewAI for multi-agent role-playing. A key focus will be the Model Context Protocol (MCP) — the new standard for connecting agents to internal data and tools without vendor lock-in. We will demonstrate how to build a flexible runtime using Vercel AI SDK Core (deployed in Docker) to serve these agents, ensuring full independence from cloud providers. Finally, we will cover the AgentOps stack, detailing how to implement self-hosted observability (via Langfuse) and access policies to safely manage autonomous systems in production.

Updating core dependencies is often postponed for years due to the fear of “breaking everything,” causing the risk to grow exponentially. Andrii will present a workflow for jumping across multiple versions: AI analyzes breaking changes and generates transformation rules, AST-based tools handle the routine work, and technical debt becomes a manageable process.

When a system consists of dozens of independent repositories, a classic monorepo is not always the right fit. Dmytro will explain how a meta-repo built with Git submodules and AI-powered tools makes it possible to preserve service autonomy while working with them as a single ecosystem. You will see real-world scenarios where AI: • connects code, contracts, and documentation • assists with automated testing and integrations • simplifies collaboration for developers, QA, and product teams • accelerates prototyping and delivery