https://news.ycombinator.com/user?id=hemangjoshi37aHacker News RSShttps://hnrss.org/hnrss v2.1.1Wed, 22 Apr 2026 17:06:33 +0000The interesting question isn't "can CF run agent inference" — it's what the routing layer needs to look like for multi-turn workflows. Shipping agent systems to enterprise clients the last year, the bottleneck is never raw tokens/sec. It's (a) state checkpointing betweentool calls, (b) cold-start latency on embedding/rerank models, (c) rate-limit coordination across concurrent agent loops. Does CF expose per-session state, or still stateless-per-request? Without that, you end up building the interesting part yourself.

]]>Fri, 17 Apr 2026 10:13:46 +0000https://news.ycombinator.com/item?id=47804324hemangjoshi37ahttps://news.ycombinator.com/item?id=47804324https://news.ycombinator.com/item?id=47804324