← All drillsBuild vs. Buy vs. Prompt
What you'll be able to do- ✓Reframe a vague "we want AI to do X" ask into a real problem statement
- ✓Sort a client's request into one of the four honest AI patterns, and catch when it's secretly two
- ✓Decide between prompt engineering, RAG, and fine-tuning with a defensible decision tree
- ✓Write a recommendation memo that pre-empts the client's two hardest follow-up questions
Turn a vague AI request into a problem statement, a build/buy/prompt call, and a one-page memo the client's technical lead can't immediately push back on.
⌁ How a consultant or solutions architect scopes an AI request in the first client meeting, before any vendor conversation or cost estimate is possible.
Start this internshipCreate an account to unlock the 5 sections, the workbench, and AskThili.
BeginSections
1. Build vs. Buy vs. Prompt
🔒 locked2. The Wrong Question
🔒 locked3. The Four Honest Patterns
🔒 locked4. Prompt, RAG, or Fine-tune
🔒 lockedDig deeper
🔗The prompt / RAG / fine-tune decision tree (template pack)
code📄Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (Lewis et al., 2020)
paperPart of these learning paths
I'm a leader and I want to evaluate and govern AI investments in my organization
View path →