Building Agentic Software Factories [ukr]

Agentic engineering is maturing: we are moving from “ask an agent to write code” toward factories — pipelines where a team of AI agents takes a project through the full 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 instead of “it seems to work.”

The main challenge of autonomous development is not getting agents to write code, but 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 examples, 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 the next project 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.