What changes when we approach the software factory as an operating model? How do we improve it while it builds our software? Product teams need a factory they can reshape while working inside it.
It’s about agentic engineering (of course). But it’s also for the whole team working on software products as well as practicing knowledge work.
Are people using AI, or is the organization learning from it? What changed because we spent those tokens? And who moves discoveries from individuals to teams to organizational capabilities?
Running a personal agent breaks every comfortable assumption about what “agent-ready” means. When enterprise platforms show up, who on your team will actually know how agents fail?
Your employees will run agents anyway. A ban just pushes the learning into the shadows. Enable it and you get people who can integrate AI with real systems and argue for sane guardrails.
What if every ceremony in software development was a workaround for expensive human iteration? What happens when juniors learn architecture on day one and spec-driven development turns out to be waterfall in disguise? Are we in the best restaurant in the world, but there’s no menu?
ThoughtWorks’ agentic engineering retreat findings and the elastic loop
Agentic engineering fails when loops don’t close. A talk about tight feedback, loose delegation, and what your organization’s mirror actually reflects.
Three weeks with OpenClaw on a Raspberry Pi. And a glimpse at what’s coming for software architecture.
Zweitausend Agenten bauen parallel einen Webbrowser – Tausende Commits pro Stunde. SQL schlägt Bash bei strukturierten Agenten-Abfragen mit 100 vs. 53 Prozent Genauigkeit. Plus: Selbst Karpathy fühlt sich im Agentic Engineering abgehängt.
Ein forschender Agent liest 1500 Papers und repliziert unveröffentlichte Alzheimer-Forschung. 90% von allem war schon immer Schrott – KI macht ihn nur sichtbar. Plus: Distributional Convergence erklärt, warum Modelle ohne Führung im Generischen landen.
Last week, I declared a clear winner: Gemini 3 Pro. Just one week later, Opus 4.5 shows comparable improvements when iterating on its zero-shotted pelican on a bicycle. I like how Opus 4.5 added improvements that make sense. Where 4.1 added a plate with a selection