With Agentic PDLC, the agents no longer just writes or reviews code — it forms hypotheses and tests them in production. How do you re-architect for autonomous agentic loops that run 24/7 on systems serving millions of users? Drawing on enterprise experience, we'll break down how to move from human control to event-driven governance and explicit guardrails for agents.

Agentic engineering is maturing. We are moving beyond “ask an agent to write some code” toward factories — pipelines where a team of AI agents takes a project through the entire lifecycle: requirements → specifications → tests → implementation → adversarial review → quality evidence. In this talk, we’ll break down what such a factory actually consists of: an orchestrator and specialized sub-agents, deterministic quality gates, end-to-end traceability from requirements to tests, and verification loops that replace “it seems to work” with measurable evidence. The main challenge of autonomous development is not getting agents to write code. It is preventing the factory from confidently reporting success when the result is actually wrong. We’ll examine common mechanisms of pipeline self-deception: “soft” rules in prompts that disappear under the pressure of a real-world project; checks that silently pass when required evidence is missing; and requirements whose acceptance criteria were never implemented as executable checks. I’ll illustrate these problems with real-world artifacts, including a case where the factory passed every gate “green” yet produced a product that failed to meet a key requirement — and what it took to make the exact same run correctly turn red. A separate part of the talk will focus on self-improvement: how to build a loop where every discovered failure becomes a new gate that future projects can no longer bypass. We’ll cover three-state verification semantics (PASS / NOT-EARNED / FAIL), a process-defect registry, and a library of lessons inherited by every new project. Everything will be grounded in real artifacts: commits, metrics, and measurable results. What we’ll cover: • Anatomy of an agentic factory: orchestrator, sub-agents, deterministic gates, and end-to-end traceability • Pipeline self-deception mechanisms — and the forensics of a real “false done” • Maker ≠ checker in practice: adversarial review that actually catches defects • The self-improvement loop: correction → retrospective → new gate → lesson for the next project • What it costs: tokens, time, and where the factory still loses to humans Who is this talk for? Engineers and tech leads who already use AI agents in software development and want to move from “it works sometimes” to a predictable, evidence-driven engineering pipeline with verifiable quality.

Not everyone supports the new strategy. The AI initiative is being sabotaged. The architect is asking for two more quarters. Marketing wants to launch as early as next week. Sound familiar? The problem is that we often expect other people to follow the same logic we do. But in the product business, different “species” work side by side: those who champion people; those who champion experiments; those who champion stability; those who champion results. And until we learn to see these differences, any strategy risks remaining nothing more than a pretty slide. Using examples from product teams and AI transformations, we’ll explore how the framework of competing values works and how to use it for influence, negotiation, and change management. 📌 Key takeaways: Every stakeholder defends a value that is rational for them. “Everyone is right—but only partially.” How to read motives behind words and objections. Why the strongest products know how to switch between languages of influence. How to reduce resistance to change without pressure. How to build support around product decisions.

AI has already become part of the modern engineering landscape, but things are much more complicated in high-load production systems. GenAI works well in demos and copilots, but is it ready for real-time processing, heavy workloads, and critical production scenarios? In this panel discussion, we’ll talk about why AI has yet to become the standard for high-load architectures, where the line between ML and GenAI lies, why inference is expensive, and why FinOps is becoming a new headache for engineering teams. We’ll discuss on-prem vs. cloud for AI workloads and real-world production constraints.

A real-world-inspired architecture talk about embedding an AI agent into the operational workflow of a highload data pipeline. We walk through a cascade failure scenario: corrupted data enters the pipeline, Kafka queues get stuck, storage pressure grows, thousands of Kubernetes pods start failing and rescheduling, etcd degrades, and PostgreSQL becomes a secondary pressure point. Then we show how an agent built with AWS Bedrock AgentCore, LangChain, and MCP/Gateway could detect early signals, isolate corrupted messages, suggest human-approved fixes, protect cluster stability, and turn noisy telemetry into actionable recovery steps.

Just yesterday, AI was seen as a simple “assistant.” Today, it’s already reshaping hiring, salaries, career growth, and the role of the developer itself. Junior positions are disappearing, code generation is becoming cheaper, and companies are increasingly valuing adaptability and AI skills over years of experience. During this panel discussion, we’ll talk without rose-colored glasses: is AI really taking jobs, why senior-level experience no longer guarantees an advantage, who is winning the new AI race — engineers or prompt-native specialists — and whether software engineering itself is turning into a completely different profession. We’ll discuss what skills will actually matter for developers in the next 2–3 years, whether middle engineers will become the new juniors, and whether the Ukrainian IT market is adapting to AI-driven changes faster than the rest of the world.

What tasks should be delegated to AI right now, and what still requires human intervention? Using a streaming product as an example, we’ll discuss how AI copilots can help QA teams streamline technical routines, scale testing, accelerate releases, and free up time for people to focus on product research, UX, and complex user scenarios

Recently, Superhuman (formerly Grammarly) launched Superhuman Go, an AI assistant that works alongside you on every platform. To build it, we needed a scalable solution that supports an unlimited number of agents that dynamically shapes the user interface and looks similar across all supported desktop and mobile platforms. Join me to find out how we discovered solutions for this innovative new product.

Topics include: - Which growth challenges will define 2026. - How AI is changing the speed of MVP launches and product experiments — and why speed without strategic focus does not create sustainable growth. - Why CRO and performance marketing alone are no longer enough for scaling. - How to use AI for research, prototyping, product drafts, and faster solution launches.

This talk is about taming AI: the journey from a simple Plan Mode in Cursor/Claude to structured specification systems. We'll break down why GitHub Spec Kit turned out to be too heavyweight, how ADR (Architecture Decision Records) helps agents retain context across sessions, and why OpenSpec by Y Combinator (Fission-AI, W26) became sweet spot. The central thesis: code quality on output equals specification quality on input. Together we'll reflect on the transformation of the developer's role — from "coder" to "spec architect."