In a deployed agent system, prompts and policies evolve frequently. How would you version and safely roll out prompt changes? How would you design rollback mechanisms if a new prompt causes regressions?

Agent systems can be expensive due to multiple model calls. How would you optimize for cost and latency without sacrificing quality? When would you introduce caching, batching, or model downgrades?

In a production system where agents operate over long time horizons (minutes to hours), how would you manage state persistence and recovery?

Agents generate a lot of "internal thought" and tool logs. How do you keep the context window from filling up with irrelevant logs during a long multi-step task?