Lifecycle of a generative AI project
- Scope project : what to do
- Build/improve system: using GenAI
- build a prototype quite quickly (take it into internal evaluation)
- plan to over time improve this software prototype
- Internal evaluation(iterative process)
- Deploy and monitor
Tools to improve performance
- Building Generative AI is a highly empirical (experimental) process - we repeatedly find and fix mistakes
- Prompting
- Retrieval augmented generation(RAG)
- Give LLM access to external data sources
- Fine-tune models
- adapt LLM to your task
- Pretrain models
- training LLM from scratch
- Prompting
RAG updates the system