
High-performance AI agents are distributed systems
A technical case study on making FixBugs faster by treating LLM agents like distributed systems: chunking, streaming, queues, token math, and concurrency limits.
K
Kirti Rathore
11 min read
3 articles found

A technical case study on making FixBugs faster by treating LLM agents like distributed systems: chunking, streaming, queues, token math, and concurrency limits.
Kirti Rathore
11 min read

Discover why Big Tech performance engineering practices can destroy startup velocity. Learn when to optimize and when to move fast, with real examples from Figma and Stripe.
Kirti Rathore
7 min read
Key insights and strategies from my PyDelhi talk on building high-performance LLM agents that can process gigabytes of data and deliver results in under a minute, with lessons learned from optimizing FixBugs.
Kirti Rathore
2 min read