AI agent anti-patterns: how to burn a pile of tokens and get nothing [ukr]
Why do some teams speed up with the same AI tools while others drown in slop? We'll go through common anti-patterns of working with AI agents in development, from "generate everything at once" to blind trust in the output, what they lead to in practice, and what to do instead.
Kyrylo Sulimovskyi
Head of Development at GameInspire
- 15+ years in software development, from backend engineer to leadership roles
- Leads development at GameInspire (a high-load product with tens of millions of users worldwide, about 40 engineers) and drives the adoption of AI-agent-based development there
- Author of "Agentic Engineering", a course on building software with AI coding assistants (three cohorts, 600+ participants), and of workshops attended by 2,500+ people
- Consults companies on AI adoption: bringing AI agents into the SDLC and teams' daily work
- Creator of the Beer::Code Telegram and YouTube channels
- LinkedIn, Telegram, YouTube, Instagram, GitHub