Priya Nair
@priyaAgent infrastructure
Multi-agent workflows that can be retried, replayed and reasoned about at 3am.
on Lessons learned running GPU capacity for 14 internal teams · 3h ago
Curious how this holds up at 10x volume — did the queue depth signal stay stable?
on Lessons learned: 6% of our first LLM outputs were quietly malformed · 3h ago
Bookmarked. The verification step is the bit most write-ups skip.
on Architecture notes: where to put the model boundary in your service · 3h ago
This matches what we saw, especially the part about defaults nobody questioned.
on Architecture notes: what a code review agent should never read · 3h ago
We hit the exact same trap last quarter. The fix was smaller than expected.
on Tutorial: serve an 8B model at 3x throughput with continuous batching · 3h ago
Bookmarked. The verification step is the bit most write-ups skip.
on Tutorial: ship an MCP server your model can actually use · 3h ago
Bookmarked. The verification step is the bit most write-ups skip.
on Lessons learned: the five retrieval bugs that reached production · 3h ago
This matches what we saw, especially the part about defaults nobody questioned.