| |
|
| |
|
Your CLAUDE.md file is more powerful than you think. In this talk, we'll walk through how we applied Prompt Learning an RL-inspired prompt optimization technique to improve Claude Code's performance on SWE-Bench Lite by up to 11%, purely by optimizing the system prompt instructions. No fine-tuning, no new tools, no architecture changes. Just better prompts, driven by real performance data & LLM-as-a-judge feedback.nWe'll cover the full optimization loop (rollouts LLM evals meta-prompting), show results for both general coding improvement & repo-specific specialization, & share practical takeaways you can apply to your own coding agent workflows today.nAgendan6:00 - 6:30 PM | Check-in & Networkingn6:30 - 7:30 PM | Presentation & Q&An7:30 - 8:30 PM | NetworkingnFood & drinks will be provided. Space is limitedregister soon to secure your spot!
|
|
|
|
|
|
|
|
