How To Build High Performance AI Agents - Insights from PyDelhi Talk
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 Modulo AI.
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 (fixbugs.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)
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: fixbugs.ai
- Join Our Discord Server