Tag: system-design
All the articles with the tag "system-design".
Three hundred tokens a second
OpenAI now sells speed itself with Ultrafast. I guess at where 300 tokens a second comes from, then argue latency is the next price dial.
The smallest model in your agent stack
Decision models answer one question: what should the agent do next. Jev named the category, AWS and Cloudflare shipped open follow-ons, and I would rebuild my agent loop around one.
Price by thinking, not by token
Anthropic put a thinking dial on every model it ships, so I would set effort per tool call instead of per deployment.
HTTP for agents, sessions for nothing
MCP deleted its session handshake, so every agent tool call is now a plain stateless request, and I would build for that.
