How To Build High Performance AI Agents

This weekend, I gave a talk at the SingleStore X PyDelhi meetup, where I shared insights on building high-performance LLM agents.

This talk emerged from documenting optimization techniques that enabled Modulo AI (moduloware.ai) to process gigabytes of logs, code, and artifacts while delivering bugfixes in under a minute.

The Talk

Code and other artefacts from the talk are (here)

Expand PDF to Full Screen

If you're unable to view the PDF, you can download it here.

Pictures!

Diving into the technical architecture and optimization strategies

Demonstrating the performance improvements in action

PyDelhiites united!

Connect and Learn More

Try fixing a Github Issue: moduloware.ai
Join Our Discord Server

How To Build High Performance AI Agents - Insights from PyDelhi Talk

Kirti Rathore