38 posts found
Xesca Alabart explores why the bottleneck has shifted from coding to requirements – and how AI-native requirements management can keep pace with agentic development.
Fabian Meyer shares how eventim onboarded their coding agent like a new engineer – giving it access to GitLab, Jira, and their workflows.
Wolf Brüning from OTTO shares what changes AI brings to Product Discovery – what they've tried, where AI can take us further, and which paths are dangerous.
Leo Peters opens a real factory from a real client project and walks through how to go from AI-assisted to genuinely autonomous software delivery.
Harshil Agrawal from Cloudflare dives into the practical architecture of sandboxing AI-generated code – how to integrate an LLM to generate code and run it in a secure, isolated environment.
Christoph Hübner and Waqas Ahmed share how MOIA builds a cross-functional community of practice to turn individual LLM experiments into collective, high-impact tools for urban mobility.
Björn Rochel built a 77,000-line full-stack app without writing a single line of code – and shares the AI development harness that made it possible.
Aleksandr Lossenko shares how Remote.com built Sherlock App in a 3-day hackathon – a Phoenix LiveView tool that lets anyone query the codebase in plain English using OpenCode and MCP.
Tereza Iofciu leads a hands-on workshop where you configure an AI agent into a personal work companion that complements your strengths and challenges your blind spots.
hackers&wizards sponsors Agentic Conf Hamburg 2026 – helping engineering teams adopt AI tools with structure, not chaos, backed by data from 100+ enterprise teams.