AI agents

Latency budgets and streaming behavior

• A Latency Scorecard for Streamed Answers: First Chunk and Tail
• Reconnecting a Stream Without Duplicating Tokens
• A Latency Budget per Agent Hop: Numbers and Triggers
• A Read Latency Budget: p95 Targets for Memory and Model Calls
• A Time Budget for Each Streaming UI State
• Choosing a First-Chunk Budget by Query Class: A Method
• Deadline Budgets That Survive Every Tool Hop
• Time to First Chunk, Chunk Gap and Close: Budgets
• Timeouts and Hedged Calls When the Chosen Model Is Slow