Software Applications - Lifecycle of a generative AI project

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

RAG updates the system