datnguyennnx
Contributions
- Evaluation guidelines for LLM applications
- Design feedback mechanism for LLM applications
- History of Structured Outputs for LLMs
- Evaluating search engine in RAG systems
- Logging
- Metrics
- Intro to Model Context Protocol
- Observability in AI platforms
- Thumbs up and Thumbs down pattern
- Tracing
- AI digest #1 Aider reasoning, OpenAI Realtime API, Cline - pre Claude-dev
- AI digest #2 New command Aider, OpenHands, Qwen2.5 Coder 32B, Predicted Output
- Salesforce use cases
- Yelp use cases