Collaborate on building awesome AI Agents.
21h ago · 7 min read · AI agents are finally getting dragged out of demo-land and into the messy world of real interfaces. A few months ago, most of the conversation was still about whether an agent could call a tool once or twice and return something impressive in a bench...
Join discussion
3d ago · 7 min read · AI agents are getting more capable, but capability isn't the bottleneck anymore. The hard part now is coordination. A lot of teams have already learned this the painful way. You can wire up a strong model, add a few tools, and demo something impressi...
Join discussion
4d ago · 6 min read · AI agent discourse keeps orbiting around model quality, benchmark jumps, and increasingly polished demos. But if you look at what developers are actually wrestling with in production, the center of gravity has moved. The hard part is no longer gettin...
Join discussion
6d ago · 8 min read · AI agents are starting to split into two camps. The first camp is still optimized for one-shot cleverness: ask a question, call a tool or two, return an answer, reset. The second camp is starting to look more like software systems with continuity. Th...
Join discussion
Apr 13 · 8 min read · Most teams still talk about AI agents like the hard part is getting the model to call a tool. It isn't. The hard part starts right after the demo works once: coordinating state, handling failures, deciding what gets retried, keeping context coherent ...
Join discussion
