As the classic once said, “life should be interesting.” Especially in interesting times. And especially when AI barges into our cozy little bubble uninvited and starts threatening to take our jobs. But if you can’t beat them, lead them. So I decided to be the first to voluntarily give AI some of my work. Well, not exactly give it away — more like pass on the honorable title of React monkey. Somewhere along the way, though, I got carried away and ended up building an entire troop of AIpes, each with (almost) clearly defined roles, (almost) well-defined responsibilities and constraints, and the ability to handle my tasks with (almost) a single command. That’s what I want to talk about: how a simple idea of making an LLM write routine code turned into a whole team of specialized agents; how I built my own agent harness in Claude Code; what worked, what broke, and what workarounds I had to invent along the way. And finally, what training my AIpes taught me about models, prompts, and why adding “pwetty pwease” to your prompt still won’t make a rule actually bind.

Description of the talk: - Background. Why we decided to add an assistant to the standard search. - Market Trends: How Agentic Commerce Is Evolving and Why It Matters Now. - Implementation: How we technically built and integrated the AI agent into Prom’s infrastructure. - MVP and experiment results. What the initial tests revealed and how users interacted with the assistant. - Key insights and conclusions. The main takeaways we identified during development and launch. - What's next. Plans for developing AI tools on the marketplace.

In this talk, we will raise several important topics: - Is code really such an important business asset? And if not, why are developers still getting paid. - How exactly Node.js developers can increase their efficiency using "stupid" AI based on GPT-4 to perform their tasks. And we have to go beyond "Write the documentation on this code". - Who are the Prompt Engineers, and why can you be fired in a year because of them?