About this event
Hosted by Arize AI, this talk will show how we used Prompt Learning — an RL-inspired prompt optimization method — to boost Claude Code’s performance on SWE-Bench Lite by up to 11%, without fine-tuning, new tools, or architecture changes. Just better system prompts, driven by real performance data and LLM-as-a-judge feedback. We’ll walk through the full optimization loop (rollouts → LLM evals → meta-prompting), share results across general coding and repo-specific tasks, and highlight practical tactics you can apply to your own coding agents.
As written in the listing.
Who it is for
- Technical builders
Technical orientation
What happens there
- Networking
Topics
- AI
Related listings
-
Mar 12, 2026
Business AI Forum
Same day, shared topic
-
Mar 12, 2026
Emerging Trends In Payments & AI
Same day, shared topic
-
Mar 12, 2026
The Next Wave of AI Roundtable by Lazo, AlleyCorp, Draper & The Yard
Same day, shared topic
-
Mar 12, 2026
Build Your First AI Agent
Same day, shared topic
-
Mar 12, 2026
Daytona x Databricks x Sentry: AI Builders Meetup
Same day, shared topic
-
Mar 12, 2026
Hardware Meetup
Same kind of event